diff --git a/.gitignore b/.gitignore
index a1dbdf7..35269b8 100644
--- a/.gitignore
+++ b/.gitignore
@@ -3,4 +3,6 @@ jdk-*/*
 tmp/*
 dacapo/*
 __pycache__/*
-scratch/*
\ No newline at end of file
+scratch/*
+summaries_*/*
+*logs
\ No newline at end of file
diff --git a/dataset_util.ipynb b/dataset_util.ipynb
index 91dd18c..4315edd 100644
--- a/dataset_util.ipynb
+++ b/dataset_util.ipynb
@@ -9,11 +9,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [],
    "source": [
     "import os\n",
+    "import glob\n",
     "import pandas as pd\n",
     "import numpy as np\n",
     "import seaborn as sns\n",
@@ -30,6 +31,13 @@
     "## Visualization"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### AVRORA"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 3,
@@ -54,7 +62,7 @@
     "y = df.iloc[:, 1].values\n",
     "z = df.iloc[:, 2].values\n",
     "# x, y, z = get_data_from_csv(\n",
-    "#     csv_dir= \"summaries_avrora\", \n",
+    "#     csv_dir= \"summaries_avrora/*\", \n",
     "#     goal = target_goal)\n",
     "\n",
     "plot_heatmap(x, y, z)\n",
@@ -71,6 +79,13 @@
     "# z.append(0.01106)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### KAFKA"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 4,
@@ -95,7 +110,7 @@
     "y = df.iloc[:, 1].values\n",
     "z = df.iloc[:, 2].values\n",
     "# x, y, z = get_data_from_csv(\n",
-    "#     csv_dir= \"summaries_kafka\", \n",
+    "#     csv_dir= \"summaries_kafka/*\", \n",
     "#     goal = target_goal)\n",
     "\n",
     "plot_heatmap(x, y, z)\n",
@@ -108,6 +123,156 @@
     "# kafka_df.to_csv(\"kafka_real_saved_states.csv\", index=False)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### H2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 500x500 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "target_goal = \"avgGCPause\"\n",
+    "\n",
+    "df = pd.read_csv(\"datasets/ext_h2_real_saved_states.csv\")\n",
+    "x = df.iloc[:, 0].values\n",
+    "y = df.iloc[:, 1].values\n",
+    "z = df.iloc[:, 2].values\n",
+    "\n",
+    "plot_heatmap(x, y, z)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### AVRORA XMX"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1500x1000 with 10 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import re\n",
+    "\n",
+    "fig, axs = plt.subplots(2, 3, figsize=(15, 10))\n",
+    "axs = axs.ravel()\n",
+    "\n",
+    "flags = [\"MaxTenuringThreshold\", \"ParallelGCThreads\"]\n",
+    "goal=\"Average GC Pause\"\n",
+    "i=0\n",
+    "\n",
+    "files = sorted(glob.glob(\"datasets/avrora/norm_ext*\"), \n",
+    "               key=lambda x:float(re.findall(\"(\\d+)\",x)[0]))\n",
+    "\n",
+    "for csv_file in files:\n",
+    "    df = pd.read_csv(csv_file)\n",
+    "    x = df.iloc[:, 0].values\n",
+    "    y = df.iloc[:, 1].values\n",
+    "    z = df.iloc[:, 2].values\n",
+    "    \n",
+    "    data = pd.DataFrame({\n",
+    "        flags[0]: x, \n",
+    "        flags[1]: y, \n",
+    "        goal: z})\n",
+    "    \n",
+    "    data_pivoted = data.pivot(index=flags[0], columns=flags[1], values=goal)\n",
+    "    sns.heatmap(data_pivoted, annot=True,  ax=axs[i], fmt=\".3f\") # ax=axs[i],\n",
+    "    axs[i].invert_yaxis()\n",
+    "    axs[i].set_title(os.path.basename(csv_file))\n",
+    "    i += 1\n",
+    "\n",
+    "fig.delaxes(axs[-1])\n",
+    "plt.tight_layout()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### KAFKA XMX"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABckAAAPeCAYAAADXqpL5AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzddVgU2xsH8O8Cy9JdKiqIrYiKXejPQMXAQMXGvrbYiIrdXRhXry32ta4NdhIq0i0p3c35/QGsLOwi4CKi7+d5eO515t0z5+zMmXfm7ASHMcZACCGEEEIIIYQQQgghhPyBJKq6AoQQQgghhBBCCCGEEEJIVaFBckIIIYQQQgghhBBCCCF/LBokJ4QQQgghhBBCCCGEEPLHokFyQgghhBBCCCGEEEIIIX8sGiQnhBBCCCGEEEIIIYQQ8seiQXJCCCGEEEIIIYQQQgghfywaJCeEEEIIIYQQQgghhBDyx6JBckIIIYQQQgghhBBCCCF/LBokJ4QQQgghhBBCCCGEEPLHokFyUmZ6enoYMGCA2MqLiorC8OHDoa6uDg6Hg927d+Off/4Bh8PB+/fvxbac31Hh9xQUFFTVValUdnZ24HA4VV0NQgiptih3/zr+lJw2ceJE6OnpVXU1CCGk2qLc/eug3E3In4UGyf8w586dw+7du6u6GgCABQsW4N69e1i+fDlOnz6Nvn37/vQ6eHl5YcmSJWjZsiUUFRVRo0YNmJmZ0cHCb+7gwYP4559/Kvz58PBw2NnZwc3NTWx1IoQQUSh3l+7s2bPgcDhQUFCo6qqQSrRx40Zcv369wp/38PCAnZ3db3+BASHk10C5u6SIiAhMmzYN+vr6kJWVhYGBAaytrREbG1sl9SGVj3I3qW5okPwP8ysl68ePH2Pw4MFYtGgRxo4di8aNG//0Ohw7dgxHjx5FmzZtsGPHDlhbW8Pb2xsdOnTAw4cPf3p9yM8hjkHyNWvW0CA5IeSnoNwtWkpKCpYsWQJ5efkqrQepfOI40V6zZg2daBNCfgrK3YJSUlLQsWNHXLt2DePHj8e+ffvQv39/7N+/H7169UJeXt5PrxOpfJS7SXUjVdUVqI4YY8jIyICsrGxVV6Va+/r1K1RUVKq0DpaWlrCzsxO4+mzSpElo0qQJ7Ozs0KtXrx8qPzU1lU7cCSHkF0C5Wzx+hdxd1Pr166GoqIgePXr80ElYUZS7CSHk10C5Wzx+hdx948YNBAcH49atWzAzM+NPV1NTw9q1a/Hhwwe0atWqwuVT7iaEiMNveSV54XOj/Pz8MHHiRKioqEBZWRlWVlZIS0vjx+Xk5GDdunUwMDAAj8eDnp4ebGxskJmZKVBe4TPB7t27hzZt2kBWVhaHDx+Gk5MTOBwOLl68iDVr1qBWrVpQVFTE8OHDkZiYiMzMTMyfPx9aWlpQUFCAlZVVibLLwsvLC8OHD4eamhpkZGTQpk0b3Lhxgz//69ev0NTURPfu3cEY40/38/ODvLw8Ro4cCQDo3r07bt++jeDgYHA4HHA4nB9+7tTJkychJSWFxYsXAwDi4uKwaNEiGBoaQkFBAUpKSujXrx8+fPjA/0zh888YYzhw4AC/LqLEx8ejXbt20NXVhbe3NwDg33//hZmZGWrWrAkejwcDAwOsW7cOubm55aq/sbFxiduz1dXV0bVrV3h6eparrMJ2PXnyBDNnzoSWlhZ0dXX58//77z907doV8vLyUFRUhJmZGT5//ixQxsePHzFx4kTUq1cPMjIy0NHRwaRJk8RyC1pycjLmz58PPT098Hg8aGlpoXfv3nBxceHHPHv2DBYWFqhTpw54PB5q166NBQsWID09nR+zfft2cDgcBAcHl1jG8uXLIS0tjfj4eP60N2/eoG/fvlBWVoacnBxMTEzw4sWLEp99/vw52rZtCxkZGRgYGODw4cMVamdkZCSsrKygq6sLHo+HGjVqYPDgwfxfn/X09PD582c8efKEv+11794dQNm2XycnJ7Rt2xYAYGVlxS+j6JXpZWlzWdaHKGFhYZg8eTJ/+9fX18dff/2FrKwsAEB2djbWrFmDBg0aQEZGBurq6ujSpQsePHgAoPzrkJCfgXJ3PsrdZefr64tdu3Zh586dkJKq2HUfhdudh4cHRo8eDVVVVXTp0oU//8yZMzA2NoasrCzU1NQwatQofPnyRaCMsuTOivpeTgPK9r3Onj0bCgoKAn2pkKWlJXR0dATiy3LMAgDXr19H8+bNISMjg+bNm+PatWsVaqevry+GDRsGHR0dyMjIQFdXF6NGjUJiYiIAgMPhIDU1FSdPnuRvexMnTgQABAcHY+bMmWjUqBFkZWWhrq4OCwsLge/on3/+gYWFBQCgR48e/DKcnJzK1eayrA9RvLy8MGLECGhqakJWVhaNGjXCihUr+PO/d1xQ3nVIyM9AuTsf5e7vS0pKAgBoa2sLTK9RowYAlOuHEMrdlLvL02bK3aRc2G9o9erVDABr1aoVGzp0KDt48CCbMmUKA8CWLFnCj5swYQIDwIYPH84OHDjAxo8fzwAwc3NzgfLq1q3L6tevz1RVVdmyZcuYvb09c3R0ZI6OjgwAa9myJevYsSPbu3cvmzt3LuNwOGzUqFFs9OjRrF+/fuzAgQNs3LhxDABbs2ZNudri7u7OlJWVWdOmTdmWLVvY/v37Wbdu3RiHw2FXr17lx126dIkBYHv27GGMMZabm8s6d+7MtLW1WUxMDGOMsfv377OWLVsyDQ0Ndvr0aXb69Gl27dq1Mtelbt26zMzMjP/vw4cPMw6Hw1asWMGf9u7dO2ZgYMCWLVvGDh8+zNauXctq1arFlJWVWVhYGGOMMX9/f3b69GkGgPXu3ZtfF8YYO3HiBAPA3r17xxhjLDo6mrVs2ZLVqVOH+fn58Zdjbm7ORowYwbZt28YOHTrELCwsGAC2aNGicn2/onTq1Ik1bNiwXJ8prHvTpk2ZiYkJ27dvH9u8eTNjjLFTp04xDofD+vbty/bt28e2bNnC9PT0mIqKCgsMDOSXsX37dta1a1e2du1aduTIETZv3jwmKyvL2rVrx/Ly8kosq+hnv2f06NFMWlqaWVtbs2PHjrEtW7awgQMHsjNnzvBj5syZw/r37882btzIDh8+zCZPnswkJSXZ8OHD+THBwcGMw+GwrVu3llhGvXr1BLaRR48eMWlpadaxY0e2Y8cOtmvXLtaiRQsmLS3N3rx5w4/7+PEjk5WVZXXq1GGbNm1i69atY9ra2qxFixasvLupTp06MWVlZWZra8uOHTvGNm7cyHr06MGePHnCGGPs2rVrTFdXlzVu3Ji/7d2/f58xVrbtNzIykq1du5YBYNOmTeOX4e/vX642l2V9CBMWFsZq1qzJ5OTk2Pz585m9vT1buXIla9KkCYuPj2eMMWZjY8M4HA6bOnUqO3r0KNuxYweztLTkb4/lWYeE/CyUuyl3l1f//v2ZqakpYyx/u5CXly93GYXbXdOmTdngwYPZwYMH2YEDBxhjjK1fv55xOBw2cuRIdvDgQbZmzRqmoaHB9PT0+PtbxsqWO4suqzy+l9MYK9v3+vTpUwaAXbx4UaD81NRUJi8vz2bNmsWfVtZjlnv37jEJCQnWvHlztnPnTrZixQqmrKzMmjVrxurWrVvmNmZmZjJ9fX1Ws2ZNtn79enbs2DG2Zs0a1rZtWxYUFMQYY+z06dOMx+Oxrl278re9ly9fMsby+5GRkRFbtWoVO3LkCLOxsWGqqqqsbt26LDU1lTGWv/3OnTuXAWA2Njb8MiIjI8vV5rKsD2E+fPjAlJSUmLq6Olu+fDk7fPgwW7JkCTM0NOTHfO+4oDzrkJCfhXI35e6y+vz5M5OQkGCdOnVir169Yl++fGG3b99murq6JbaD76HcTbm7PG2m3E3K47ceJJ80aZLA9CFDhjB1dXXGGGNubm4MAJsyZYpAzKJFixgA9vjxY/60unXrMgDs7t27ArGFybp58+YsKyuLP93S0pJxOBzWr18/gfiOHTuWa8fDGGM9e/ZkhoaGLCMjgz8tLy+PderUiTVo0EAg1tLSksnJyTEfHx+2bds2BoBdv35dIMbMzKzcdShUNFnv2bOHcTgctm7dOoGYjIwMlpubKzAtMDCQ8Xg8tnbtWoHpAErsFIom64iICNasWTNWr149/o62UFpaWon6TZ8+ncnJyQl8VxXx9OlTxuFw2MqVK8v1ucK6d+nSheXk5PCnJycnMxUVFTZ16lSB+MjISKasrCwwXVi7zp8/zwCwp0+fllhWeQbJlZWVv7sTFrb8TZs2MQ6Hw4KDg/nTOnbsyIyNjQXi3r59ywCwU6dOMcbyt9MGDRowU1NTgQH+tLQ0pq+vz3r37s2fZm5uzmRkZASW4eHhwSQlJct1UBIfH88AsG3btpUa16xZM2ZiYlJielm333fv3jEA7MSJEwKx5WlzWdaHMOPHj2cSEhL8A9riy2eMMSMjo+8OdJdlHRLyM1HuptxdHrdu3WJSUlLs8+fPjLEfHyS3tLQUmB4UFMQkJSXZhg0bBKZ/+vSJSUlJCUwva+4s74l2WXNaWb7XvLw8VqtWLTZs2DCBuIsXLwocY5TnmKVly5asRo0aLCEhgT/t/v37DEC5tldXV1cGgF26dKnUOHl5eTZhwoQS04W1/9WrVyXyWeHAlqOjo0BsWdtc1vUhTLdu3ZiioqLA9sAYEzhW+N5xQVnXISE/E+Vuyt3lcezYMaaiosIA8P8mTJjAsrOzy1UO5W7K3ZS7SWX5LR+3UmjGjBkC/+7atStiY2ORlJSEO3fuAACsra0FYhYuXAgAuH37tsB0fX19mJqaCl3O+PHjweVy+f9u3749GGOYNGmSQFz79u3x5csX5OTklKn+cXFxePz4MUaMGIHk5GTExMQgJiYGsbGxMDU1ha+vL8LCwvjx+/fvh7KyMoYPH46VK1di3LhxGDx4cJmWVR5bt27FvHnzsGXLFtja2grM4/F4kJDI36xyc3MRGxsLBQUFNGrUqEyPkSgUGhoKExMTZGdn4+nTp6hbt67A/KK3YxV+N127dkVaWhq8vLwq3LavX79i9OjR0NfXx5IlSypUxtSpUyEpKcn/94MHD5CQkABLS0v+OoyJiYGkpCTat28PR0dHoe3KyMhATEwMOnToAADl+v6EUVFRwZs3bxAeHi4ypujyU1NTERMTg06dOoExBldXV/68kSNHwtnZGf7+/vxpDg4O4PF4/G3Ozc0Nvr6+GD16NGJjY/ntTk1NRc+ePfH06VPk5eUhNzcX9+7dg7m5OerUqcMvr0mTJiL7XGn1l5aWhpOTU4UeF/Kj229Z2wyUbX0Ul5eXh+vXr2PgwIFo06ZNifmFt0+qqKjg8+fP8PX1FVlWWdYhIVWBcjfl7u/JysrCggULMGPGDDRt2rTMnytN8e3u6tWryMvLw4gRIwRyt46ODho0aCAyd5eWO8urrDmtLN8rh8OBhYUF7ty5g5SUFH68g4MDatWqxb9NvazHLBEREXBzc8OECROgrKzML693797lXieFn793757Q25G/p2j7s7OzERsbi/r160NFRaVM229Z21zRY4zo6Gg8ffoUkyZNEjjOASDw2IPvHReUdR0SUhUod1PuLotatWqhXbt22L17N65duwZra2ucPXsWy5YtK1c5hSh3U+6m3E3EripH6CtL4a99hbdhFCr8tTQoKIhNnz6dSUhICPwSXUhFRUXgNpu6deuy//3vfyXiCn/RvnDhgtDlvH79Wmi9Cm/D+p43b94I/Moq7M/FxUXgM4W/tGlrawvcTlToR3/RVlBQYADY0qVLhcbk5uaynTt3svr16/OvAi7869Gjh0AsSvlFW0FBgamoqLCIiAihy3F3d2fm5uZMSUmpxHfyvdtmRElJSWFt27ZlysrK7NOnT+X+fGHdi/8auGXLllLXoZKSEj82NjaWzZ07l2lpaZWIK3rLYEWuJHdwcGAyMjJMQkKCtW3blq1evZr/iJBCwcHBbMKECUxVVbXE8k+ePMmPCwsLYxISEvxf4/Py8lidOnUEbpVzcHD47vYbFxfHIiIiGAChV+4vWLCgXL/cM8bYrl27mISEBONyuaxr165sy5YtJbYjUVeSl3X7FXUleVnbXBj7vfVRXGRkJAMgcKulME+ePOFfpdG8eXO2aNEi9uHDB4GYsqxDQn4myt2Uu8tq8+bNTFVVlcXGxvKn/eiV5CEhIQLT//rrr1LXYYsWLfixZc2dFblluyw5razfa+EVWmfPnmWM5V+FJSsry+bPn8+PKesxS2FZf//9d4k6DxkypNzbq7W1NQPAZGVlWZ8+fdj+/fsFrnJjrPSr0VauXMl0dXUZh8MRqK+VlRU/TtTVaOU5TivL+iju9evXDAA7evRoqXFlOS4oyzok5Gei3E25u6yeP3/OJCUlS9wNa2dnxzgcDv/OsLKg3E25m3I3qSwVe8tRNVH0at6iWJGXbJT24oqiSnuRhKjllGX5pSm84nTRokUif02vX7++wL/v3bsHIP+lG6GhoWJ/i3WzZs2QkJCA06dPY/r06dDX1xeYv3HjRqxcuRKTJk3CunXroKamBgkJCcyfP5/fnrIYOnQoTp06hT179mDTpk0C8xISEmBiYgIlJSWsXbsWBgYGkJGRgYuLC5YuXVqu5RTKysrC0KFD8fHjR9y7dw/NmzcvdxmFim8rhfU5ffo0dHR0SsQXfdnYiBEj8PLlSyxevBgtW7aEgoIC8vLy0Ldv3wq1q6gRI0aga9euuHbtGu7fv49t27Zhy5YtuHr1Kvr164fc3Fz07t0bcXFxWLp0KRo3bgx5eXmEhYVh4sSJAsuvWbMmunbtiosXL8LGxgavX79GSEgItmzZUqLd27ZtQ8uWLYXWSUFBoUIv1SnN/PnzMXDgQFy/fh337t3DypUrsWnTJjx+/Pi7b0z/0e23rG0Gvr8+fkS3bt3g7++Pf//9F/fv38exY8ewa9cu2NvbY8qUKQDKtg4JqQqUuyl3lyYxMRHr16/HzJkzkZSUxH8RWEpKChhjCAoKgpycHLS0tMpcb0B47uZwOPjvv/+EbhOF+/Ly5M6K+F5OK8/32qFDB+jp6eHixYsYPXo0bt68ifT0dP6L5grbDZTtmEWcduzYgYkTJ/Lz1ty5c7Fp0ya8fv1a4CXowsyZMwcnTpzA/Pnz0bFjRygrK4PD4WDUqFHlyt1lafOPHGN8T1mOC8qyDgmpCpS7KXd/z+HDh6GtrV3ibthBgwbBzs4OL1++LPfVzJS7v7UboNxdFOVuUlG/9SB5aerWrYu8vDz4+vqiSZMm/OlRUVFISEgocZtRVahXrx4AgMvlolevXt+Nv3v3Lo4dO4YlS5bg7NmzmDBhAt68eSOwgyjrwYkoGhoauHz5Mrp06YKePXvi+fPnqFmzJn/+5cuX0aNHD/z9998Cn0tISICGhkaZlzNnzhzUr18fq1atgrKyssAtWE5OToiNjcXVq1fRrVs3/vTAwMAKtSkvLw/jx4/Ho0ePcPHiRZiYmFSoHFEMDAwAAFpaWqWux/j4eDx69Ahr1qzBqlWr+NNLe2RGedWoUQMzZ87EzJkz8fXrV7Ru3RobNmxAv3798OnTJ/j4+ODkyZMYP348/zMPHjwQWtbIkSMxc+ZMeHt7w8HBAXJychg4cCB/fmG7lZSUSm134ZuihbWz8K3q5WVgYICFCxdi4cKF8PX1RcuWLbFjxw6cOXMGgOh+UNbtV9Tny9rmQqWtD2E0NTWhpKQEd3f375atpqYGKysrWFlZISUlBd26dYOdnR1/kBz4/jok5FdDubtifqfcHR8fj5SUFGzduhVbt24tMV9fXx+DBw/G9evXy1VucQYGBmCMQV9fHw0bNhQZV97cWdG6iMpp5f1eR4wYgT179iApKQkODg7Q09PjP9atcFnA949ZCvuaOHO3oaEhDA0NYWtri5cvX6Jz586wt7fH+vXrAZSeuydMmIAdO3bwp2VkZCAhIUEg7nu5+3ttLhpf2jFGcYX7hLLk7rIcF3xvHRLyq6HcXTG/U+4G8td3bm5uienZ2dkAUOZH45SGcjflblEod5Oy+q2fSV6a/v37AwB2794tMH3nzp0AADMzs59dpRK0tLTQvXt3HD58GBERESXmR0dH8/8/ISEBU6ZMQbt27bBx40YcO3YMLi4u2Lhxo8Bn5OXlkZiY+EP10tXVxcOHD5Geno7evXsjNjaWP09SUrLEL/aXLl0SeIZbWa1cuRKLFi3C8uXLcejQIYFlAIJXBmRlZeHgwYPlXgaQf2Dg4OCAgwcPYujQoRUqozSmpqZQUlLCxo0b+QcBRRWuR2HtAkpuoxWRm5tbYr1raWmhZs2a/Cu5hS2fMYY9e/YILXPYsGGQlJTE+fPncenSJQwYMADy8vL8+cbGxjAwMMD27dsFnr9VqGi7TU1Ncf36dYSEhPDne3p68q/QKKu0tDRkZGQITDMwMICioqLAFevy8vIlEnBhXcqy/Ra2s3gZZW1zWdYHAMTExMDLy4v/nDcJCQmYm5vj5s2beP/+fYnyC+tetE8C+VdN1K9fv8RV+99bh4T8aih3V9zvkru1tLRw7dq1En89evSAjIwMrl27huXLl5e73sUNHToUkpKSWLNmTYnvhjHG//7KmzvLoyw5rbzf68iRI5GZmYmTJ0/i7t27GDFihMD8sh6z1KhRAy1btsTJkycFts0HDx7Aw8OjXO1MSkoqMThiaGgICQmJCufuffv2lRiMEZW7y9rmsh5jREREwMvLi1+WpqYmunXrhuPHjwsc5wDf1ltZjwuA769DQn41lLsr7nfJ3QDQsGFDREVFwcnJSWD6+fPnAeCHr+gFKHdT7v6GcjepqD/2SnIjIyNMmDABR44c4d/u8vbtW5w8eRLm5ubo0aNHVVcRAHDgwAF06dIFhoaGmDp1KurVq4eoqCi8evUKoaGh+PDhAwBg3rx5iI2NxcOHDyEpKYm+fftiypQpWL9+PQYPHgwjIyMA+YN4Dg4OsLa2Rtu2baGgoFChK0fr16+P+/fvo3v37jA1NcXjx4+hpKSEAQMGYO3atbCyskKnTp3w6dMnnD17lv9LXHlt27YNiYmJmDVrFhQVFTF27Fh06tQJqqqqmDBhAubOnQsOh4PTp0+X+Xa6onbv3o2DBw+iY8eOkJOTK/FL4pAhQ3540FBJSQmHDh3CuHHj0Lp1a4waNQqampoICQnB7du30blzZ+zfvx9KSkro1q0btm7diuzsbNSqVQv379+v8BXyRSUnJ0NXVxfDhw+HkZERFBQU8PDhQ7x7947/623jxo1hYGCARYsWISwsDEpKSrhy5YrIF1xoaWmhR48e2LlzJ5KTk0vcLiQhIYFjx46hX79+aNasGaysrFCrVi2EhYXB0dERSkpKuHnzJgBgzZo1uHv3Lrp27YqZM2ciJycH+/btQ7NmzfDx48cyt9PHxwc9e/bEiBEj0LRpU0hJSeHatWuIiorCqFGj+HHGxsY4dOgQ1q9fj/r160NLSwv/+9//yrz9GhgYQEVFBfb29lBUVIS8vDzat28PfX39MrW5LOsDyH8p0Jo1a+Do6Iju3bsDyL+18v79+zAxMcG0adPQpEkTRERE4NKlS3j+/DlUVFTQtGlTdO/eHcbGxlBTU8P79+9x+fJlzJ49u1zrkJBfDeVuyt1ycnIwNzcvMf369et4+/at0HkVYWBggPXr12P58uUICgqCubk5FBUVERgYiGvXrmHatGlYtGhRuXNneZQlp5X3e23dujXq16+PFStWIDMzs8R+v6zHLACwadMmmJmZoUuXLpg0aRLi4uL4uVvYD8WiPH78GLNnz4aFhQUaNmyInJwcnD59GpKSkhg2bBg/ztjYGA8fPsTOnTtRs2ZN6Ovro3379hgwYABOnz4NZWVlNG3aFK9evcLDhw+hrq4usJyWLVtCUlISW7ZsQWJiIng8Hv73v/9BS0urTG0u6zHG8uXLcfLkSQQGBkJPTw8AsHfvXnTp0gWtW7fGtGnToK+vj6CgINy+fRtubm5lPi4oyzok5FdDuZtyNwDMnj0bJ06cwMCBAzFnzhzUrVsXT548wfnz59G7d2+0b9++QvUuinI35W7K3eSHVeLzzqtM4csVoqOjBaYXf9lhdnY2W7NmDdPX12dcLpfVrl2bLV++nGVkZAh8rm7duszMzKzEcgpfIHLp0iWhyyn+UgpR9foef39/Nn78eKajo8O4XC6rVasWGzBgALt8+TJjjLF///2XAWA7duwQ+FxSUhKrW7cuMzIy4r8oJSUlhY0ePZr/Ur/yvJxB2Pfw5s0bpqioyLp168bS0tJYRkYGW7hwIatRowaTlZVlnTt3Zq9evWImJiYlXpSIUl4gUvS7y83NZZaWlkxKSopdv36dMcbYixcvWIcOHZisrCyrWbMmW7JkCbt3757QlzqUZsKECaW+8KE8L8YUtd4LOTo6MlNTU6asrMxkZGSYgYEBmzhxInv//j0/JjQ0lA0ZMoSpqKgwZWVlZmFhwcLDwxkAtnr16hLLKmv9MjMz2eLFi5mRkRFTVFRk8vLyzMjIiB08eFAgzsPDg/Xq1YspKCgwDQ0NNnXqVPbhwwcGlHxJJWOMHT16lAFgioqKLD09XeiyXV1d2dChQ5m6ujrj8Xisbt26bMSIEezRo0cCcU+ePGHGxsZMWlqa1atXj9nb25f7RSkxMTFs1qxZrHHjxkxeXp4pKyuz9u3bs4sXLwrERUZGMjMzM6aoqMgA8LfN8my///77L2vatCmTkpIq8f18r81lXR+F7S++TQcHB7Px48czTU1NxuPxWL169disWbNYZmYmY4yx9evXs3bt2jEVFRUmKyvLGjduzDZs2CD0hUllWYeE/AyUu/NR7q6YH31xp6j1e+XKFdalSxcmLy/P5OXlWePGjdmsWbOYt7c3P6asubOyclp5v9cVK1YwAKx+/foil12WY5bC76dJkyaMx+Oxpk2bsqtXr7IJEyaUaxsNCAhgkyZNYgYGBkxGRoapqamxHj16sIcPHwrEeXl5sW7dujFZWVkGgP8isPj4eGZlZcU0NDSYgoICMzU1ZV5eXqxu3bolXhZ29OhRVq9ePf5L7op+P99rc1nXR+GxZfFjNHd3d/4xnoyMDGvUqBH/peVlPS4oVJZ1SMjPQLk7H+XusvHy8mLDhw9ntWvXZlwul9WtW5ctWrSIpaamlqscyt3CUe6m3E1+HIexCvwMSAghhBBCCCGEEEIIIYT8Bv7YZ5ITQgghhBBCCCGEEEIIIX/sM8mrWmJiItLT00uN0dHR+Sl1iY6OFvqm6ULS0tJQU1P7KXURl/T09O++KEVNTQ3S0tI/tazKkJKS8t3nh2lqavJfEFJd/Up9hhDyZ/qV9kOUu0v3q+fGX2lbqkxxcXHIysoSOV9SUhKampo/sUaEkD/Nr7S/pdxdOsrdvwbK3eSPVtXPe/lTfe9Z2D9z1dStW7fUehR/pll1UPiMtdL+yvoMNXGWVRkKn5NW2l95nq3+q/qV+gwh5M/0K+2HKHeX7lfPjb/StlSZTExMSm1jeZ5/SgghFfEr7W8pd5eOcvevgXI3+ZPRM8mriIeHB8LDw0uN6dWr10+py4sXL0r9RVRVVRXGxsY/pS7iEhERgc+fP5caY2xsDFVV1Z9aVmUICAhAQEBAqTFdunSBjIzMT6pR5fiV+gwh5M/0K+2HKHeX7lfPjb/StlSZnJ2dER8fL3K+rKwsOnfu/BNrRAj50/xK+1vK3aWj3P1roNxN/mQ0SE4IIYQQQgghhBBCCCHkhxw4cADbtm1DZGQkjIyMsG/fPrRr105k/KVLl7By5UoEBQWhQYMG2LJlC/r37w8AyM7Ohq2tLe7cuYOAgAAoKyujV69e2Lx5M2rWrMkvIy4uDnPmzMHNmzchISGBYcOGYc+ePVBQUChX3enFnYQQQgghhBBCCCGEEEIqzMHBAdbW1li9ejVcXFxgZGQEU1NTfP36VWj8y5cvYWlpicmTJ8PV1RXm5uYwNzeHu7s7ACAtLQ0uLi5YuXIlXFxccPXqVXh7e2PQoEEC5YwZMwafP3/GgwcPcOvWLTx9+hTTpk0rd/3pSnJCCCGEEEIIIYQQQgghFda+fXu0bdsW+/fvBwDk5eWhdu3amDNnDpYtW1YifuTIkUhNTcWtW7f40zp06ICWLVvC3t5e6DLevXuHdu3aITg4GHXq1IGnpyeaNm2Kd+/eoU2bNgCAu3fvon///ggNDRW44vx7pMrT2OriXa0hVV2FSrVFSvQbsX8X8bkZVV2FSrU0u3q9tby8lCRFvw37d2A4U66qq1Cp5G3PiL3M7JjSny9YEVyNemIvk1Qdu7pjqroKlWq8UnRVV6HS7Uyumndz/CwjM37v4y8nHq+qq1CpzPJSqroKlar1l3/FXiblbvI9U/UsqroKlepijEtVV6HS1VPQqeoqVKomPK2qrkKlisj9vXPbh8Sgqq5CpYpL9hV7mZWRu/MUayEzM1NgGo/HA6/YsWNWVhacnZ2xfPly/jQJCQn06tULr169Elr2q1evYG1tLTDN1NQU169fF1mfxMREcDgcqKio8MtQUVHhD5AD+e8HkJCQwJs3bzBkSNnHiOlxK4QQQgghhBBCCCGEEEIEbNq0CcrKygJ/mzZtKhEXExOD3NxcaGtrC0zX1tZGZGSk0LIjIyPLFZ+RkYGlS5fC0tISSkpK/DK0tAR/EJOSkoKamprIckT5La8kJ4QQ8ovJ+72vwCSEEEJ+O5S7CSGEkOqlEnL38uXLS1ztXfwq8p8hOzsbI0aMAGMMhw4dqpRl0CA5IYQQQgghhBBCCCGEEAHCHq0ijIaGBiQlJREVFSUwPSoqCjo6wh/tpKOjU6b4wgHy4OBgPH78mH8VeWEZxV8MmpOTg7i4OJHLFYUet0IIIaTysTzx/xFCCCGk8lDuJoQQQqqXKszd0tLSMDY2xqNHj/jT8vLy8OjRI3Ts2FHoZzp27CgQDwAPHjwQiC8cIPf19cXDhw+hrq5eooyEhAQ4Ozvzpz1+/Bh5eXlo3759mesP0JXkhBBCfoY8OjEmhBBCqhXK3YQQQkj1UsW529raGhMmTECbNm3Qrl077N69G6mpqbCysgIAjB8/HrVq1eI/03zevHkwMTHBjh07YGZmhgsXLuD9+/c4cuQIgPwB8uHDh8PFxQW3bt1Cbm4u/znjampqkJaWRpMmTdC3b19MnToV9vb2yM7OxuzZszFq1CjUrFmzXPWnQXJCCCGEEEIIIYQQQgghFTZy5EhER0dj1apViIyMRMuWLXH37l3+yzlDQkIgIfHtoSadOnXCuXPnYGtrCxsbGzRo0ADXr19H8+bNAQBhYWG4ceMGAKBly5YCy3J0dET37t0BAGfPnsXs2bPRs2dPSEhIYNiwYdi7d2+560+D5IQQQiodo1usCSGEkGqFcjchhBBSvfwKuXv27NmYPXu20HlOTk4lpllYWMDCwkJovJ6eHhhj312mmpoazp07V656CkOD5IQQQiof3bJNCCGEVC+UuwkhhJDqhXL3D6EXdxJCCCGEEEIIIYQQQgj5Y9GV5IQQQirfL3DbFyGEEELKgXI3IYQQUr1Q7v4hdCU5IYQQQgghhBBCCCGEkD8WXUlOCCGk8uXlVnUNCCGEEFIelLsJIYSQ6oVy9w+hQXJCCCGVj277IoQQQqoXyt2EEEJI9UK5+4fQ41YIIYQQQgghhBBCCCGE/LHoSnJCCCGVL49+0SaEEEKqFcrdhBBCSPVCufuH0JXkhBBCKh1jeWL/I4QQQkjl+RVy94EDB6CnpwcZGRm0b98eb9++LTX+0qVLaNy4MWRkZGBoaIg7d+4IzL969Sr69OkDdXV1cDgcuLm5lShj+vTpMDAwgKysLDQ1NTF48GB4eXmVu+6EEELIz/Yr5O7qjAbJCSGEEEIIIYT8UhwcHGBtbY3Vq1fDxcUFRkZGMDU1xdevX4XGv3z5EpaWlpg8eTJcXV1hbm4Oc3NzuLu782NSU1PRpUsXbNmyReRyjY2NceLECXh6euLevXtgjKFPnz7IzaWXoRFCCCG/M3rcCiGEkMpHt30RQggh1UsV5+6dO3di6tSpsLKyAgDY29vj9u3bOH78OJYtW1Yifs+ePejbty8WL14MAFi3bh0ePHiA/fv3w97eHgAwbtw4AEBQUJDI5U6bNo3//3p6eli/fj2MjIwQFBQEAwMDcTWPEEIIET867/4hdCU5IYQQQgghhJBKl5mZiaSkJIG/zMzMEnFZWVlwdnZGr169+NMkJCTQq1cvvHr1SmjZr169EogHAFNTU5HxZZGamooTJ05AX18ftWvXrnA5hBBCCPn10SA5IYSQysfyxP9HCCGEkMpTCbl706ZNUFZWFvjbtGlTiUXHxMQgNzcX2traAtO1tbURGRkptLqRkZHlii/NwYMHoaCgAAUFBfz333948OABpKWly10OIYQQ8lPRefcPocetEEIIqXx59BxPQgghpFqphNy9fPlyWFtbC0zj8XhiX86PGjNmDHr37o2IiAhs374dI0aMwIsXLyAjI1PVVSOEEEJEo/PuH0KD5IQQQgghhBBCKh2PxyvToLiGhgYkJSURFRUlMD0qKgo6OjpCP6Ojo1Ou+NIUXuXeoEEDdOjQAaqqqrh27RosLS3LXRYhhBBCqgd63AohhJDKR7d9EUIIIdVLFeZuaWlpGBsb49GjR/xpeXl5ePToETp27Cj0Mx07dhSIB4AHDx6IjC8rxhgYY0KfnU4IIYT8Uui8+4fQleSEEEIqH71lmxBCCKleqjh3W1tbY8KECWjTpg3atWuH3bt3IzU1FVZWVgCA8ePHo1atWvxnms+bNw8mJibYsWMHzMzMcOHCBbx//x5HjhzhlxkXF4eQkBCEh4cDALy9vQHkX4Wuo6ODgIAAODg4oE+fPtDU1ERoaCg2b94MWVlZ9O/f/yd/A4QQQkg50Xn3D6FBckIIIYQQQgghv5SRI0ciOjoaq1atQmRkJFq2bIm7d+/yX84ZEhICCYlvN0Z36tQJ586dg62tLWxsbNCgQQNcv34dzZs358fcuHGDP8gOAKNGjQIArF69GnZ2dpCRkcGzZ8+we/duxMfHQ1tbG926dcPLly+hpaX1k1pOCCGEkKpAg+SEEEIq3x92mxYhhBBS7f0CuXv27NmYPXu20HlOTk4lpllYWMDCwkJkeRMnTsTEiRNFzq9Zsybu3LlT3moSQgghv4ZfIHdXZ/RMckIIIYQQQgghhBBCCCF/LLqSnBBCSOWjZ6MRQggh1QvlbkIIIaR6odz9Q/74QXKtCf2g85c5uJoqSPMIQsjKY0h18xUZrzqgE2ottgRPVwsZgREI3XgKiY9dvs3v1wGa40wh38IAUqqKcO+zAOmfgwTK4PC4qL3KCuqDu4AjLYVEJzcE2xxGTkxipbSx7/j+GDRtCFQ0VRHsGYi/Vx+B3wfRbezYvzNGLRwDTV0tRASF48zmk3B1dBaIGWk9Gr0s+0BOSR7e7z1xZMUhRAZF8OfX0K+J8TZWaNSmCaS4Ugj2CsKFHWfx+dUnsbdv8ISBGDHDAmqaavD3DMC+lQfg7eYtMr6bWVdYLZ4IHV1thAaF4ejGY3j7+J1AzMRF49Hfsh8UlBXg/u4z9tjsRVhgOH++rn4tTLOdiuZtm0GKK4UAz0D8s/0k3F5+EHv7alv1gd7MgZDWUkaKRwg8bU4gydVfZLz2wPaov3QEZGprIi0wEr7rziHmkRt/vlb/ttCd0BtKLfQhraaIV/9biuTPwQJlSPC4aGg3FjrmnSDB4yLW8QM8lx1HVrT4t1HtiX1Rs0gfDLQ9hlQ3P5HxagM6ovaSb30wZMNpJAj0wfbQHm8KeUMDcNUU8bG3NdKE9MG6qydCfVAXSPCkkODkhqDlR5BdCX1QyrgXuB3NwFFQRl5UCLLunUJeeIDIeMkm7SBtMhwcFQ2wuChkPbqAXP9v25VkozbgGveEhI4eOHKKSD9qg7yoEMFltuoBqead8mN4skjdNg3ITBN728qDsdwqXT75vbQd3xudp5lBQVMZkZ4h+G/1SYR9EN2vmvZvh/8ttICKrgZig6LwcPN5+Dp+61dN+rZBmzG9UMNQD3KqirDvZ4NID8H9ohSPiz62Y9B8YAdISXPh9/QjbtueQGpMUqW0UWnUQChPtICkhhqyvAMQu+kAMt1F5zb5Pl2hOnsipGpqIyckDLG7jiH92bfcJtezM5RGDACvaQNIqighdPgMZHkLfmeKw/tDoX8P8JrUh4SCPII6DUFecmqltK/buD7oOX0glDRVEOYZjEurTyD4g+jc1qp/B5gtHAF1XU1EB0bi+uaz8HBy4883Mm2HLmN6oY5hPcirKmJT/yUIE7IOh64YB+OBnSAlzYXn0w9wWPk3kith31/Dqi90Zw6CtKYKUjyC4b/ib6S4is5tGgM7ou6SUZCprYn0wAgErj+D+Eeu/Pnq/dujxvg+UGhRD1w1Rbj0XITUYrlNZ2wvaA7tCgVDfUgpyuFlw/HITaqcfX+b8b3RsaAPRnmG4O7qkwgvpQ826d8O3Qv6YFxQFB5tPg+/In2wcd82aF2kDx7pZ4OoYutPksdFb9sxaFbQB/2ffsR/ldQHNSb0h/Z0c3A1VZHuGYQvq44grZTzAxWzTqi5aAykdbWQGRSOsI2nkFTk2FmlbwdojOsLOUMDSKkqwdN0PtI9AgXKUB/dB2rm3SDX3ACSinL40Gw0cpMqp/+VFeVuIk7dx5nCdPogKGuq4ItnMM6vPo6gD6L3i8b9O2DwwlHQ0NVEVGAkrmw+A3enb/vFVqbtYDKmD+oa1oOCqiLW9l+MLx5BAmV0teyF9oO7oE4zfcgqymFuiwlIr6T9IgBMmTYWc+dNhba2Jtw/eWLxojVwcf4oMt58SD+sWLkAderowt8/CKtXbsWD+04CMTa28zFh4kgoKyvhzWtnLJi/CgH+Qfz5RkbNsGbdErRq3QJ5ubm4ceMebJZtQGqq+Ns5wmooJswcDXVNNfh4+GHLil347OopMr7XwB6YuWQqatbWQUhgKPauP4Tnj17x5/+vvwmGjzdHkxaNoKKmjJE9J8Lns+C+VponDWu72TAd3AvSPC5eOb7FxmXbERcTL/b29R7fDwOmmUNZUwUhnkE4ufoY/EsZN2nfvxMsFlpCQ1cLkUERuLD5FNwcv52Xtu3bAT3HmELf0ACKqopY3m8Bgotto/+z7I1Og7tBr3k9yCnKYYrhGKRV0jZqPmEQRvLHTfyxd+UBeJUybmJi1g2TFk+Ajq4OQoPCcGTjMbx5/JY/v2u/Lhg4dgAatmgAZVUlTOkzA/4egsdyXB4XM1fOQI/B3SEtzcW7J++x22Yv4mMSxN6+yVPHYM68KdDS1sTnT15Yunhtqf1vsHlfLF85H3Xq6CLAPwh2q7bh4f0nAjHLV8zDuIkj+P1v0YLVCPD/dnzSwqgp7NYuQavWhsjNy8XNf+/BdvmmSul/ZUW5+8dU6eNWQkNDERMTw//3s2fPMGbMGHTt2hVjx47Fq1evSvn0j1Mb1Bm1V1shfKcDPvddiDSPIDQ8uwpS6spC4xXaNILBAWvEnH+Ez6YLkXDvDer/vQyyjerwYyTkeEh564kvG06JXG4du0lQ6d0GftO3wWuYLaR11FD/2FKxtw8AOg3oggm2k3FpzwUsGbAAQZ5BsD29Bkoi2tjIuDHm71uERxcfYLHZfLy7/wZLjtigdsNvbTSfMRT9Jw7AEZtDsBm8GJlpmVh5eg24PC4/ZvnxlZCQksAaS1ssGbAAwZ6BWH58JVQ0VcTavu4DTTBj1XSc2nUGM/rNhL9HALac2QgVdeHLaWrcFLYHbPDfhbuY3vcvvLj7EmuP2UGvkR4/ZtTMERhiZY7dy/di9sC5yEjLwOYzmwTat+HkOkhKSWLRyCX4q/8sBHgEYP0/66CqqSrW9mkP7ohGa8bBf8dlvO69HMmfg2F8YTmkNZSExiu3aQhD+7kIO+eI172W4et/79Hyn0VQaKzLj5GUk0HCGy/4rj8ncrmN1o6HZh9jfJy6G+/M14Cnowqj49ZibRsAqA/qjLqrrRC68yI+mS5CqkcQmpwrvQ82OGiNr+cf4WOfhYi7+xYNjy8V6IOScjJIfuuJkI2nRS5Xz84Kqr3bwHf6NngMXQlpbTU0/Fv8fVCyaXtI9x6D7GfXkH7MFnlRIZCxXArICV9/EroNwBsyCzluT5B+1BY53s7gjVgAjua39ceR5iH3izeyHjuIXjBXGrn+H5H94oa4m0RIlefuZgM6wNR2DJz2XMXhAbaI8gzB2NPLIK8uvF/VNm6A4ftmw+WiE+zNVsDr/nuMOmINrYbf+hVXVgYh77zxcPMFkcs1XTkWjXq2wqWZe3FixDooaqti5OEFYm8fAMibmkB98XTE259B2IiZyPIJgM7hjZBQUxEazzNqCq0tNki+ehdhFn8h9fFL6OyxA7e+Hj9GQlYGGa7uiNt1TORyOTI8pL14j/hjor8HcWg9oCOG2I7Hf3uuYIvZMoR5BGPWKRsoiFiH+q0bYuLeuXjl4IjN/Zfhw/13mHZkMWo0rM2PkZbjwf+9N65vFp3bhq0cj+Y9jfH3zF3YPdIOytqqmGK/UOzt0xjcCfXsJiBkxyW49lmC1M9BaH7eFlwRuVuxTSM0PjQfkecfwaX3YsT+9w5NTyyBXONv7ZOU4yHprScC158RuVwJWR7iH7viy56rYm9TUU0HdEBv2zF4uucqjhb0wdGnl0FOxPrTNW6Aoftmw+2iE46arYD3/fcYccQamsX64Jd33nhUSh/ss3IsGvZshSsz9+JkQR+0qIQ+qDqwC3RXTkLEbgd49bdGukcg6p+2E3lsIm/cGPr7FyHmwkN49VuAhHtvUO/YcsgInB/IIOWtJ8I2ij4/kJDlIcnJFZH7L4u9TYRUde5uM6ATRthOwM09l7DObClCPYIx/9QKKIrYbxi0boipe+fjucNjrO2/BG7332LWkSWoWWS/z5OTgd97L1zZLHq/KC0rDfcnbrhz8JrY21Tc0GFm2LjJBls27UW3LoPg7u6Fa9f/gYamutD4du1b4+8Tu3H65CV07TwQt289wLkLh9CkaUN+zPwF0zB9xgQsmLcSPbsPRWpqGq5dPwEeTxoAoKOjhX9vnkJAQDB69hiKYUOs0LhxAxw6vFXs7eszuCcW2s3B4R3HMbrPJPh89sPB8zuhqqEiNN6oTXNsOmSH6+dvwbK3FZz+e4adJzbBoLE+P0ZWTgZubz9i7/pDIpe7aO1cdOvdGUum2mLKkNnQ1NHAjuMbxd08dBjQGWNtrXB1jwNWDFiIEM8gLDu9SuS4SQPjRpi9zxpOFx/BxmwhnO+/gfWRZdAtMm7Ck+XB+50nzm8Wve+XluXhwxNX/HvgitjbVFSPgSb4a9V0nNx1BtP6/QV/jwBsPbNJ5LhJM+OmWHnABncu3MXUvn/h+d0XWFds3ERGTgbu79xxZKPoY8tZq/9Cx94dsGb6OswfvhDq2upYe9ROvI0DMGRof6zfZIOtm/ejRxdzuLt74vK149DQUBMa3659Kxw9sQtnT11G9y6DcefWQ5w5fxBNmjTgx8xdMA3TZozHwvmr0LvHcKSlpePyNcH+d+3GSQQEBKP3/4bDYshkNG7SAAfst4i9feTnqdJB8mHDhuH169cAgH///Rfdu3dHSkoKOnfujLS0NJiYmODWrVuVtnztqYMQfe4BYi4+RoZvKIKX2SMvPRMao3oKj588AIlOroi0v44Mv1CEbTuPNPcAaFn158fEXnmC8N0XkfRM+BXFkopy0BjVE1/WnEDyi09I+xSAwAX7oNi2CeRbNxT6mR8xcMpgPLxwH46XHiHU9wuO2BxEZnom/jeil9D4/lYD4fbEBTcOX0OYXygu7DiLQPcA9Jtgxo8xmzwIV/ZfxLsHbxDsFYR91rugqqWGdn06AAAUVRVRs14tXD94BcFeQYgMisCZzacgIyeD2g3rirV9w6cNw53z/+HexfsI9g3B7mV7kJmRib6jTIXGD51sjndO73DR/hJC/L7gn+0n4evuB/OJg4rEDMGZvefw8v4rBHgGYsv8rdDQVkcX084AACVVJejW08WFAw4I8AxEWGA4jm76G7JyMtAvkjTEQW+GGULPPEb4hSdI9QmDx+JjyE3PQk3L7kLj607rh1jHDwg6eAupvuHw33IRSZ8CUXvSt+8j4vIzBOy8itin7kLLkFKURa3RPeCz+jTinn9G8sdAuM+zh2q7RlA2ri/W9tWYNhBfzz1AtMNjpPuGInDpYeSlZ0LL8n/C46cMQIKjKyIO/YsMvzCEbjuP1E+B0LHqx4+JufIEYbsuIemp6D6oadkTwXb/IOmFO1I/BcDfej8U2zaGgpj7ILd9P+S4OiLnw1OwmHBk3TkBlp0JbksT4fFtTfMHt1/fBosNR/aTy8iLCAK3TW9+TM6nF8h+dh25gcLXHwDkvL2H7Jc3kRsm+uqcn47lif+PVImqzt0dp/SDywVHuF16imjfMNyyOY7s9Ey0GiG8X7W36gu/Jx/x8vBtxPiFw3HHZUS4B6HdhD78mI/XnuPJ3msIeC68X/EUZdF6ZHfcW38WgS89EOEehH8XHUadNg2h20q8+0UAUB4/DElX/kPK9fvIDghBzNo9YOmZUBwiPLcpjzVH2ot3SPznErIDvyB+/0lkevhB2fJbbku59QgJ9meR/tpVaBkAkHTmGhL/dkDmB9FXhYnD/6aY4eWFR3h9yQmRfmG4sOIYstKz0HFED6Hx3Sf1g+cTNzw6chNR/mG4vfMivnwOhMmEb9/Hu2vPcHfvFXi/EH7HmoyiLDqO+B+urj8Fn1ef8cU9EGcWH4JBm0bQa9VA6Gcqqtb0gYg8+xBRFxyR5hMKvyVHkJeeCe1RwnNbran9EefohrCDN5DuG4bgrReQ8ikQNYvktq+XnyJk52UkPBN9RVT40dsI3X8dyS6ir3oThw5T+sH1giM+XHqKGN8w3C7ogy1F9MF2BX3wVUEfdCrog22L9MFP157j2d5rCCylD7Ya2R0P1p9F0EsPRLoH4caiw6jdpiFqibkPak0djJjz9xF38REyfL8gZPkh5GVkQn2k8GNnrckDkeTkgq+HryHDLxQR288h3T0AmkWOneOuOiFyjwOSn4u+4zD675uIOngFqS6ir+r76Sh3/zaqOnf3njIAzy48wstLTojwC8WZFUeQlZ6FziOE7xd7TjLD5yduuH/kBiL9w/DvTgeEfA7A/yb05ce8vvYUt/ZehqeI/T4APDp+B3cPXUeAq4/Y21TcrNmTcPIfB5w9cwXeXn6YP9cWaenpGDduuND4v2ZOxMMHT7F3z1H4ePtjw7pd+OD2GdOmj/sWM8sK27cewJ3bD/H5szdmTFsEnRraGDAwf//Zt9//kJ2Tg4ULVsPPNxAuLp+wYL4tBpv3Q7164j3vHjt9JK6evYkbF+4gwCcIG5ZsQ0Z6JsxHDRAabzl1BF46vsGpg+cQ6BuMg1uPwvOTD0ZZffs+bl++hyM7T+D1s3dCy1BQlIe55QDstNuHdy9c4PnRG6vnb0DLdi1g2LqZWNvXf8ogOF54gCeXHiPMNxR/29gjMz0TJiOEjw31tRqAD09ccevwdYT7heLSjvMIdA9AnwnfxoaeX3uCa3svwr2Uff/d47dw89BV+LlW7r7fYtow3D7/H+5evIdg3xDsXLYHGRmZ6Cdi3GTY5CF46/QODvaXEOIXghMF4yZDJg7mxzy48hCndp+B8zMXoWXIK8qh/6i+OLjWHq4v3eDzyRdbrLejedtmaNK6iVjbN3P2JJz6xwHnzlyBt7cfrOetQlp6OsaMF97/pv81AY8ePsO+Pcfg4+2Pjet34+MHD0wp0v9mzJyAHdsO4r/bj+Dx2Rt/TVsMnRpaMBuQf25u2q8HsnNysNjaDn6+gXB1+QTreaswyLwv9OvVEbrcn4Jy9w+p0kHyz58/o1mz/J3bpk2bsHHjRvz777/YvHkzrl69ip07d2LVqlWVsmwOVwryLQwEB7MZQ9Lzj1AwbiT0M/LGjUoMfic6uUHBuOwDa3ItDCAhzRUoJ8M/DJmhX0Uut6KkuFKoZ1gfH5+78acxxvDp+Qc0at1Y6Gcatm6Mj8V24m5PXdCwIF6rtjZUtdQEYtKS0+Dr5oOGrfPrnxyfjDC/UJgM6wGeLA8SkhLoM8YUCdEJCPgkvkE7Ka4UGho2gMuzbyf8jDG4PHNFUxE73abGTeH8THCA4P2T92hqnB9fo44O1LXV4VJkR5+anAZPNy9+TFJ8EkL8vqD38F6QkZWBhKQEBow1Q3x0PHw+ie/ElMOVhGILfcQ+K3Lgxxjinn6CShvh25yycQPEPhU8UIx1/CAyXhglo3qQkJYSKCfNLxzpX6KhXI5yvqewDyYWPeFnDInPRPdBBeOGgvEAEp+4lqvvyLeoBwlpLhKL9kG/MGSGRperL3+XhCQkaugjN/BzkYkMuUGfIVFL+Am9hG79EoPfuQEfIaEr/kE4QiqqKnO3JFcSNQ31BQazGWMIeO4O3dbCBzprt65fYvDb7+lH6LYue7+qaagPSWkpgXJi/COQEBpTrnLKREoKvKYNBAezGUP6a1fIGAnPbTJGTUsMfqe/fA+eiPiqJMmVRO3m9QQGsxlj8H7xCfoi1qF+q4bweiG4Dj2ffoBeOX7YrNO8HqSkpQSWG+UfjrjQaJHLrQgOVwqKLeoh4algbkt49glKbYTnKkXjhoLxAOKd3KAoxpwrLhJcSdQw1BcczGYMgaX0Qd3W9UsMfgeUsw/WENIHYyuhD3K4UpAzNBAczGYMyc8+QF7U+UHrRkgqduyc9MRVZDwhVaFqc7cU6javB88X3/ZzjDF4vvgIAxH78XqtGsLjheB+8fPTD6hXCReViQOXy0XLVs3h5PiSP40xBifHl2jbrpXQz7Rt1wpOji8Epj169Iwfr6dXGzo6WgIxSUkpeP/ejR8jzZNGVlY2GGP8mIz0TABAh45txNM45J93N2nRCG+efhvMZozhzbP3aNGmudDPtDBuhjdP3wtMe+X0Bi3alH1wu0mLRuBKc/G6SDlBfiGICI0UudyKkORKQd/QQGAwmzEG9+cf0aC18H15g9aNSgx+f3zqhga/4DaaP27SUGAwO3/cxAXNWjcV+pn8cRPBwe93T96jmXHZjy0bGjYEV5orUM4X/y+IDI1CMzEOknO5XBi1aoYnToL974lT6f3vSZH+CgCPHz5D23YtAQB1+f3vW0xyUgqc33/41v+kpZFdvP9lZAAQb/8jP1eVDpJLSUkhOTkZABAYGIh+/foJzO/Xrx+8vSvnFzUpNUVwpCRLPIM4OzoBXBGPBOFqqiA7OkEwPiYB3HI8YoOrqYK8zOwSz4jMjk4UudyKUlRVgqSUJBKLPe8pISZB5GNPVDRVkFAsPjEmASoFbVTVUuWXISoGANaMWQn9ZvVw2sMB532uYMCUwdgwwQ6pYny2orJafvviowWfRxYfEw81LeG31ahpqiK+2PPL4qMToKaZH69a8N/iz8iKj44XeJTKYsulqN+sPm56X8dd/9sYPnUYlo21QUpiyo82i09aTQkSUpIlngOeGZ0InpaK0M/wtFRKxGdFJ0JaS/htYkKXq5W/jeYU20azYhLBE+M2yu+DQvqUdGl9sNi6yY5OBFfE9yG0DC1VEX0wAdJa4ntcDkdOERwJSbBUwfXBUhLBURC+PjgKKmCpgs9WZalJkJBXEVu9qkxenvj/SJWoytwtp6oICSlJpBTL3akxSVDQFPGYJk0VIfGJUCjH/kxBUwU5mdnIKLbfKG85ZSGpqgSOlCRyYwVzVW5sPCTVhec2SQ1VIfEJkBRxi2lVUig4Nin+HPCk6EQoifgulTRVkFxs358cnQgljbLnNiVNFWRnZpd4Fm1SjOjlVgS3ILeVzMUJInOVtJaQ48voREiXI7f9LBXtg6nF4lNiEiFfgT6YWcl9UEotv//lFFsfOaUc70tpqiCn+LFJOc8PflmUu38bVZm7FVQVISkliaRy7PeVNVWE5IkEKIt4tEdVU1dXhZSUFL5+jRGYHv01BtramkI/o62tga/RsSLjtQr+W1qZT5+8gra2BubOmwoulwsVFSXYrV0MANDREb7cilBVU4GUlBTiouMEpsdGx0FdxHm3hpa6iHjhj58RRl1LHVmZWUhJEjzHLm25FaFYsI0mFtvmEr8zblJ8nKX4mMivQllNuZRxE+H1zR83SRCMj47nj5eUhZqWKrIys0qMAZU2XlMRhf0vukRfiYW2lvB+oKWtUaJvff0aw+932toaBWWU7H9aBfOePXkFLW0NzJk3BVwuF8oqSli9Jr//aYux/5Ub5e4fUqWD5CYmJjh//jwAoFWrVnBychKY7+joiFq1apVaRmZmJpKSkgT+suhB9VVu6roZSIxNxEqL5Vg2eCHe3n+DZX/bQkWMg5BVae762UiITcD8odaYNWAOXtx7ifX/rBXrzp6Q3wrd9vXbqKzcnUO5mxBCfi2Uu38blZW7cyl3VykvT1/MmLYYs+dORmS0O3z8XyM4KBRRUdHI+8MGtgj52by8/DBz+lLMnDMJYV8/wsvvFYKDC/sf+34BlYVy9w+RqsqFb968GV27dkV4eDi6dOmCFStW4N27d2jSpAm8vb3h4OAAe3v7UsvYtGkT1qxZIzBtikIjTFMq/faNnLhksJxccItdhSTsavFCwq4y52qoIDu67G9Wzo5OgASPC0klOYErWbmayiKXW1HJ8UnIzckt8Yu7ioYKEkQsKyE6ASrF4pU1VJBQ0Mb4r/HfyvgaLxAT5BEAADDs3AKte7bBxBajkZ6SDgA4ZmsPoy4t0X3Y/3D9kHheSpEYl9++4i/LVNVQRdzXOKGfiYuOh6pGsXhNFf6v3PEF/1XVUBEoQ1VTFf6f89/U3KpzS3To1R7mzYYhLSV/Hfqu2Afjbq3Rx6I3Lhwo5YWK5ZAVl4S8nFxIF7syi6epjMyvCUI/k/k1oUS8tKYysr4mCo0Xutyv+duolJKcwNXk0hrKyBTjNsrvg0L6VFZpfbDY9snVVEa2iO9DaBlf40X0QRVkfS17X/4elpYMlpcLjrzg+uAoKIOlCF8fLCUBHHklwXh5JeSlJoitXoT8qMrK3SZKzdFdpUWpn0uLT0ZeTi4UiuVueQ0lpEQL71cp0QlC4pWRUo79WUp0AqR4XMgoyQlcTV7ecsoiNz4JLCcXkuqCuUpSXRW5scJzW25MvJB4FeTGCI+vSikFxyaKxdaJkqYykkR8l0nRCVAstu9X1FQucVViaZKiE8DlcSGrJCdwNbmShujlVkR2QW4rmYtVROaqrK9Cji81lZFVjtz2s1S0D8oXi1fQUEZqBfogT0lO4GpycffBnLj8/idVbH1IlXK8nxOdAKnixyblPD8gpLJVVu5updwExiqlPz4jJT4ZuTm5Je7+KW2/nxidICRPlLxy91cRGxuPnJwcaGlpCEzX1NJAVFS00M9ERcVAq9hLPYvGfy34r1axMjS1NPDp47d3h1y+dBOXL92EppY60lLTwRjDrDmTEBT0RSxtA4D4uATk5OTw774upK6phlgR590xX2NFxMcKjRcm9msspHnSUFBSELiavLTlVkRywTaqXGybU/7OuEnxcZai4ya/ksS4xFLGTYTXN3/cREUwXlOVP15SFnFf4yHNk4a8krzA1eSljddURGH/0yzR/9QR9VV4//saFVOiv2ppafD7XVRUTEEZJfufe5H+d+XSTVy5dBOamupIS8vvfzNnWyE4MEQsbSM/X5VeSd6kSRO8efMGWVlZ2Lp1K1JTU3H27FnY2dnBz88PFy5cwMSJE0stY/ny5UhMTBT4m6j4/edAsewcpH70h1KXIifkHA6UuhgixVn4rWapzt6C8QCUuxkhxbnsLwJJ++iPvKxsgXJkDGqCp6slcrkVlZOdg4BPfjDsbMSfxuFwYNi5BbxdvIR+xsfFC4adBdto1LUlfAriv36JQvzXOIEyZRVk0aBlQ/gUvGhIWoYHAGDFfj3Ly8uDhIT4Nrmc7Bz4fPJFqy4t+dM4HA5adWkJDxfhLx3zcPZA6y6Cz6Uy7toaHs758REhkYiNihWIkVOQQ5OWjfkxMrIy/PYUxfLyIMHh/HC7+OVl5yL5YyDUuxZ53hqHA7WuzZHwXvg2l+jsKxgPQN2khch4YZI+BCAvKwdqRcqRM6gB2dqaSCxHOd9T2AeVS/TBFiL7QoqzD5S7GgpMy++DZe87qR8DkJeVLbDc/D6oWa6+/F15uciLCISkftETBw4k9ZohT8QLNfNC/SCpJ3iiIanfHHmhv9ALOCsqL1f8f6RKVFbu7qL8/WdU5mbnIvxTIPQ7f4vlcDio17k5QkW8rPCLi59APAAYdG2OUJey96vwT4HIzcoRKEe9Xg2o6GqUq5wyyclBpocvZNu3/DaNw4Fsh5bIEPFCzYwPHpBtL5jbZDu2rvQXcFZEbnYuvrgHoFGnb/tyDoeDhp2aI1DEOgx09UGjToK5rXEXQwS5lH2fHeIegJysHIFytOrVgJqupsjlVgTLzkHyxwCoFM1VHA5Uuhgi6b3wXJXs7CMYD0C1mxGSxZhzxSUvOxcRnwKhV7RPcTjQL6UPhgrpg/rl7IMRP6kPsuwcpH3yh2JnwWMTxS4tkCrq/MDFG0rFjp0Vu7YUGV+tUO7+bVRW7m6pLPw9V0XlZucg2D0ATYrt95t0MoS/iP14gKuPQDwANOnSAgHl2O//TNnZ2XBzdYdJ9078aRwOBybdO+LdW+EvzH731lUgHgB69OjCjw8K+oLIyK8CMYqKCmjTpqXQMqO/xiI1NQ1Dh5khIyMTjo+fi6NpAPLPuz0/eqN912/PWeZwOGjXxRgf3wt/4fJH589o19VYYFqHbm3x8f1nofHCeH70RnZWtsBy6xrUQQ1dHZHLrYjc7BwEfvJHsyL7cg6Hg2adDeEr4mXKvi7eaF5s32/Y1Qi+v+A2mj9u4iMwxsHhcNC6Syt8dvEQ+hlR4yafnct+bOnzyQfZWdkwLlJO7Xq60NHVxmcR4zUVkZ2djQ+un9HNpCN/GofDgYlJp1L7X7fuHQWmdf9fZ7x76wYACOb3v28xiooKMG5jJLz/Ref3vyGF/a/Y+wZ+KsrdP6RKryQHAAMDA5w/fx6MMXz9+hV5eXnQ0NAAl8st0+d5PB54PJ7ANGmOZJk+G3X0BvR3zUXqR3+kuvpCe+oASMjKIMbhEQBAf89cZEfEIXTzmfz4v2+h0eX10J4+CIkPnaE2uAvkWhggaMkhfpmSKgqQrqUBae38X01lDfJvW8v+moCc6ATkJqch5sIj1F5thZyEFOQmp6Hu+qlIee+F1ErYod489i9m75gP/49+8PvgA7NJg8CTk4Hjpfw2ztk5H7GRcTi39RQA4M6Jm1jjsBEDp5rD+fE7dBnYDfUM68N+2QF+mbf/voFhc0YgIjAcX79EYdTCMYj/Goe39/PfmO7j4oXUxFTM3jkfl/ZcQFZGFnpZ9oFWbW04Pxb+5uqKunzkCpbuWgyfD77wcvPCsClDISMrg3sO9wAAS3cvRkxkLP7efBwAcPXv69h1eTsspg3D60dv0WNwdzRs0RA7l+7hl3n172sYM3c0QgPDEPklElaLJiImKhbP7+Xv6D47eyAlMQVLdy/G6V1nkZWRif5j+kOntg5eP3or1vYF2d9G871/IcktAImufqgzrT8k5XgIv/AEANB830xkRMbBb8MFAEDwkf/Q9voq1J1hhuiHrqhh3glKRvXgsegIv0wpFXnI1tIATyf/l2S5+jUB5F+FnhWdiJzkdISdc0SjNeOQnZCCnOR0NNlohYR3Pkh0Fu9gUMSRmzDYPQcpH/yQ4uqLGlMHQlKOh+gLjwEABnvmIisyFl82nc2PP3YLTa+sQ43pgxD/yBkag7tAvoUBAhZ/u/JFUkUBPBF9MLugD0aff4S6dt/6oN6GKUh+74UUMffB7Df/gTdoOvIiApEb5g9u+77gcHnI/pC//qQHTQdLjke248X8+Hf3IDNuBaTa90OunxukmnWERM16yLxz/FuhMvKQUFYHRyF//XHUa0AC+c86L3z+OUdeGRwFZUioagMAJLRqA1npyEuMBTLE916AcvnDbtP63VVG7pYqY+5+dew/DNkxHeEfAxH2wR8dJvUFV44H10v5/WrIzhlIiozHo635d/W8OXEXEx1s0XFqf/g+dkXzgR1R07Aebi77m1+mrLI8lGtpQFFbBUD+4BuQf/VqSnQiMpPT4eLgBFPbsUhPSEVmchr6r52AL84+CHUV/49YiaeuQHPDYmR+9kXmJy8ojxsKjqwMUq7n5zbNDYuR8zUW8Xvy9w2JZ66j5ontUB4/DGnP3kKhb3fwmjVE9JpvuU1CSRFSNTQhWfAsUK5ebQD5V6EXPs9cUl0Vkhqq4NbJzwvSDfSRl5qGnIho5CUli619j4/dxrgdMxHyyR9Bbv7oMbk/eHI8vL7kBAAYt2MWEqPicGNr/qMBnI7/h/kOq/G/KQPw2dEFxgM7oY6hAc4vP8ovU05ZHqq1NKBc8Fg37Xr5bUiKTkBydCIyktPx6uJjDLUdj9TEVGQkp8FijRUCnL0R5Cq+QXIACDt8E432zEbyB38ku/qh1lQzSMjxEHXBEQDQcN8cZEXEImjjufz4o3fQ4toa1JoxEHEPnaFp3gUKRvXgWyS3SRXmtoLcLVuQu7MKchuQf0eUtJYKZPR0AADyTeoiNyUdmWExyEkQ3ztTXh/7D4N3TEfEx0CEf/BHu4I++KGgDw7eOQPJkfF4XNAH3564i/EOtuhQ0AebFfTB20X6oEwpfTC1oA+6Ojihd5E+2LegD4aJuQ9+Pfov6u6ch7SPfkhz84Xm5IGQkJVB7MWHAIC6u+YjOzIW4VtO58f/fRMNL22A1rTBSHz0HmqDukKuhQFCihw7S6ooQLqmJrgFxyYyhccm0fH8559LaaqAq6kKnl5+22Ua10VeSjqywqORK8b1Vy6Uu38rlZG7JcuYux8cu4VJO2Yh6JM/At380GuyGaTleHhxKX+/OGnHbMRHxeHa1vz94qPjt7HIYQ16TxmAT44uaDuwM/QMDXB6+WF+mXLKClAXst9PjE7gX6GupKkCZU0VaNXN3y/qNqqDjNQMxIbFIE2M75ICgAP7j+PQ4W1wdfkEZ+cPmDnLCvJycjhz5jIAwP7IdkSER2KN3XYAwKGD/+DO3XOYPWcy7t1zxLDhA9CqdXPMm7uCX+ahAyeweMks+PsHITj4C1bYWiMyIgq3bt7nx0ydPg5vX7sgJTUVPf7XBevWL4Pd6m1ITBRf3gaAM4cdsHbPCnh88IK7qwdGTx0BWTkZ/HvhNgBg3T5bfI2Iwb6N+bnr/NGLOHrtAMbNGIVnD1/C1LwXmho1xrrFW/hlKqkoQqeWDrR08q/o1atfB0D+FeSx0XFISU7F9fO3sHDNHCQmJCE1ORVLNyzAh3ef8Mml7IPtZXHn2A3M2DEXAR/94f/BF/0mDYCMnAyeFIyb/LVzLuIi4+CwNX9s6O6JW1jpsB79pw6C22NndBzYBfUMDXBs2bexIXllBWjU0oBqwb6/Rr38fX9CdAISC7ZRZU0VqGiqQLtg31+7UV1kpKYjJiwGqWLcRi8duYJlu5bA54MPPN28MXzKEMjIyuBuwbjJ8t1LEB0Zg2MF4yZX/r6G3Zd3wGLacLx+9Ab/G9wdjVo0xI6lu/llKqooQqumFjR08o8t6xjoAgDiouMQHx2P1OQ03LlwF3+tmoGkhGSkJadhzrpZcH//GZ5iHCQHgIP7j+PA4a1wc3WHi/NHzJg5EXJysjh3Ov8pBgcPb0VERBTW2e0AABw+dBI3/zuLWXMm4f49JwwdZoaWrZpjwRxbfpn2B09i4eKZ+f0vKBQ2K+cjMuIrbt96wI+ZMm0s3r5xQWpqGrr36Iw165di7ertSBJz/ysXyt0/pMoHyQtxOBxoa2sLTPvy5QtWr16N48ePi/jUj4m78QJSakqotWgUuJqqSPscCJ+xa5FTcPuudE1NoMjV0CnvvREwexdqLRkN3aVjkREYAb/Jm5Hu/e1WCpU+bVFv11z+vw0OLQIAhO24gPCd+ScLIXbHUTuPof6RJeDwuEhyckOQzbeEL04vbz2HkroyRlmPhoqmKoI8ArBhvB3/VjWNmpoCz0vydvbCnrk7MGrRGIxePA4RQeHYOm0jvvh8a+N1+6vgyclg+qZZkFeSh9d7D6wfb4fszGwA+bcrbRhvB8vFY2F3fj0kpaTwxTcEW6duQLBnkFjb53TzCZTVlTFx0fj8R6J4BGDZuBX8l0xo1dISuKLdw9kDG2ZvwqQlEzFpqRXCAsOxaoodgry/1evCwYuQkZOB9Zb5UFBSwKd37lg+1obfvqT4JCwba4NJS6yw4+JWSEpJItgnGKsm2yHAM0Cs7Yv69xWk1ZVgsMQCPC0VJH8OhovlZv4LwWRqaQi0L/G9Dz79tQ/1l41EA5tRSAuMhNvE7UjxCuXHaJm2QfO9f/H/bXRkHgDAf9tl+G/PP4jzXnUKLC8PLf+2hgRPCjGOH+G59NvJrLjE3ngBKXUl1F5sCa6mCtI+B8JrzDr+C3V5tTQEXhSR8t4bfrN2ofbS0ai9bAwyAiPgM2mLQB9U69MWBrvn8P/dwH4hACB0hwNCd+T3wSC7E6jLGBoeXQwOj4tEJzcELv/2Q4K45Hq8QZacErgmwyAtr4y8qGBknN8KFLycU0JZA3lF3oadF+qLzOsHId3dAtI9RoDFRSLz4i6w6G/rT6pha/AGTef/W2Zofluznl5F9tOr+THGPSHdbSg/RnbCSgBA5o3DyPn4TOztJH+uqsjdn2+9hry6InpYD4eCpjIiPYJxZvwWpMbk9yvlmuoC+8Uvzr64MvcA/rfIAj0Xj0BcUCQuTNuJrz7f+lWj3sYw3/GtX1kcyO9XTruuwGl3fr+6t+4MGGMYaT8PktJS8H/6CbdtT1RKG1PvPYGkmjJUZ42HlIYqMr0CEDljBXJjEwAAUjW0gCL7jswPHvi6bBNUZ0+E2jwrZAeHI3KeHbL9gvgxcj06QGv9Yv6/tbfnn4THHzyN+EP5g31KIwZAdeY4fkzNkzsBAF9ttyHl328nBD/K5dYrKKgpwWzBCChqqiDMMwgHJmziv6RNrZY6WJED/EAXH/wzbx8GLByJgYtHITooEkembUOEz7dbyQ17t8G47TP5/560fz4A4M7uS7izOz+3XVl3CiyPYcoha0hJS8Hz6Uc4rDwmtnYVivn3JbjqSqi7ZBSkNVWQ8jkIny03iMxtye+94T1zD+ouHQW95aORHhgBD6utSPP61j410zZotGc2/99NDlsDAIK3X0TI9vwfWmtM6IO6i0bwY4z+XQcA8J63H18dnMTWPo9bryGnrgiTgj4Y5RGMc0X6oFKxPhjq7Itrcw+gxyIL9Cjogxen7UR0kT7YsLcxBhfpg8MK+uCTXVfwtKAP3i/ogxYFfTDg6SfcqYQ+GH/zOaTUlFBj4WhwNVWR7hEIv3Frvp0f1NIQOAFNdfZC4JwdqLl4LGouGYfMoHAETNmEjCLHJsq920Fv5zz+v/UP5vfFiJ3nEbEr/0IHzbF9UcPakh/T6MomAECQ9R7EXXos9naSP1dV5O73t15CUU0JgxeMhJKmCr54BmHPhA1F9vsaYEXymr+LD47N2wPzhZYYsng0vgZF4MC0rQgvst9v2bsNrLbP4v97+v4FAIAbuy/i5u5LAACTMb0xaP63/eKSS/n7xROLDuDlZSextvHqldtQ11CDje18aGvnPxJl6BArRBc8XkS3dg2BO5HfvnHBlEkLYLvSGqvsFsLfPxijR/0FT49vF+3s3nUEcvJy2LNvA5SVlfD61XsMHWKFzMwsfoyxsRFsbOZBXkEOPj4BmD/XFg4Xrou1bQBw/99HUFVXwV9LpkBdUw3en30xy3Ih4mLyf2jXqaUtMK7w4b07bGbaYdbSaZi9fDpCAkNhbbUc/l6B/BgT065Yu+fbjwJbDq8FANhv/xuHt+dvi9tX7UVeXh62H9sAaR4XLx3fYtOy7WJv3+tbL6CkroTh1qOgoqmKYI9AbB6/lv9oN/Vi4ya+zt44MHcXLBaNxsjFYxEZFIGd0zYjtMi4iXHvtpix49vY0NwD+WNDV3ZdwJXd+eelvcaYYtiCUfyY1Zc35n8HC/fi6WVHsbXP8eYTKKurYOKiCVDTVIW/hz+WjrMRGDcp2r7Pzh5YXzBuMmWpFcICw7Cy2LhJp94dsWzXt2PLVYfyB5j/2XkKJ3fmH1seWHMILI9hzZFV4Epz8e6JM3bb7BVbuwpdu3oH6hpqWL5iHrS0NeH+0RMWQycjOrqw/9UUOO9++8YV0yZZw2bVAtiuXogA/yCMtZwJT89vF07s3XUE8nKy2LV3Pb//WQydJND/Whu3wLIVcyEvLw9fH39Yz1uJixf+FXv7yM/DYUWz0S/mw4cPaN26NXJzy3d5/7taQyqpRr+GLVK//+0O8bkZVV2FSrU0+/d+waeSZNb3g6oxw5lyVV2FSiVve0bsZWa8Fs+z+ouS6TBS7GWSH1fR3G1Xd0wl1ejXMF5J+DMRfyc7k3+Pl3OLMjLj9z7+cip2hejvxiyviq7G/klafxH/STnl7j9HRXP3VD2LSqrRr+FijEtVV6HS1VPQqeoqVKomPK2qrkKlisj9vXPbh8Sgqq5CpYpLFu/djADl7h9VpVeS37hxo9T5AQHivSqXEEIIIT+GcjchhBBSvVDuJoQQQr6vSgfJzc3NweFwUNrF7BwxvgiREEJIFaFno/02KHcTQsgfgnL3b4NyNyGE/CEod/8QiapceI0aNXD16lXk5eUJ/XNx+f1vbyKEkD9CXp74/0iVoNxNCCF/CMrdvw3K3YQQ8oeg3P1DqnSQ3NjYGM7OziLnf+/XbkIIIYT8XJS7CSGEkOqFcjchhBDyfVX6uJXFixcjNTVV5Pz69evD0VF8b/QlhBBSRf6wX6B/Z5S7CSHkD0G5+7dBuZsQQv4QlLt/SJUOknft2rXU+fLy8jAxMflJtSGEEFJZGMut6ioQMaHcTQghfwbK3b8Pyt2EEPJnoNz9Y6r0cSuEEEIIIYQQQgghhBBCSFWq0ivJCSGE/CHoti9CCCGkeqHcTQghhFQvlLt/CF1JTgghhBBCCCGEEEIIIeSPRVeSE0IIqXyMftEmhBBCqhXK3YQQQkj1Qrn7h9AgOSGEkMpHt30RQggh1QvlbkIIIaR6odz9Q+hxK4QQQgghhBBCCCGEEEL+WHQlOSGEkMpHt30RQggh1QvlbkIIIaR6odz9Q2iQnBBCSOWj274IIYSQ6oVyNyGEEFK9UO7+IfS4FUIIIYQQQgghhBBCCCF/LLqSnBBCSOWj274IIYSQ6oVyNyGEEFK9UO7+IXQlOSGEEEIIIYQQQgghhJA/Fl1JTgghpPLRs9EIIYSQ6oVyNyGEEFK9UO7+ITRITgghpPJRsiaEEEKqF8rdhBBCSPVCufuH0ONWCCGEEEIIIYQQQgghhPyx6EpyQgghlY9eIEIIIYRUL5S7CSGEkOqFcvcPoSvJCSGEVL68PPH/ldOBAwegp6cHGRkZtG/fHm/fvi01/tKlS2jcuDFkZGRgaGiIO3fuCMy/evUq+vTpA3V1dXA4HLi5uQnMj4uLw5w5c9CoUSPIysqiTp06mDt3LhITE8tdd0IIIeSn+wVyNyGEEELKgXL3D6FBckIIIb89BwcHWFtbY/Xq1XBxcYGRkRFMTU3x9etXofEvX76EpaUlJk+eDFdXV5ibm8Pc3Bzu7u78mNTUVHTp0gVbtmwRWkZ4eDjCw8Oxfft2uLu7459//sHdu3cxefLkSmkjIYQQQgghhBBCKoYet0IIIaTyVfFtXzt37sTUqVNhZWUFALC3t8ft27dx/PhxLFu2rET8nj170LdvXyxevBgAsG7dOjx48AD79++Hvb09AGDcuHEAgKCgIKHLbN68Oa5cucL/t4GBATZs2ICxY8ciJycHUlKUggkhhPzC6JZtQgghpHqh3P1D6EpyQgghv7WsrCw4OzujV69e/GkSEhLo1asXXr16JfQzr169EogHAFNTU5HxZZWYmAglJSUaICeEEEIIIYQQQn4hdJZOCCGk8lXCs8wyMzORmZkpMI3H44HH4wlMi4mJQW5uLrS1tQWma2trw8vLS2jZkZGRQuMjIyMrXN+YmBisW7cO06ZNq3AZhBBCyE/zhz2HlBBCCKn2KHf/ELqSnBBCSOVjeWL/27RpE5SVlQX+Nm3aVNUtFSopKQlmZmZo2rQp7Ozsqro6hBBCyPdVQu4mhBBCSCX6BXL3gQMHoKenBxkZGbRv3x5v374tNf7SpUto3LgxZGRkYGhoiDt37gjMv3r1Kvr06QN1dXVwOBy4ubmVKCMyMhLjxo2Djo4O5OXl0bp1a4FHn5YVDZITQgiplpYvX47ExESBv+XLl5eI09DQgKSkJKKiogSmR0VFQUdHR2jZOjo65YovTXJyMvr27QtFRUVcu3YNXC633GUQQgghhBBCCCG/MgcHB1hbW2P16tVwcXGBkZERTE1N8fXrV6HxL1++hKWlJSZPngxXV1eYm5vD3Nwc7u7u/JjU1FR06dIFW7ZsEbnc8ePHw9vbGzdu3MCnT58wdOhQjBgxAq6uruWqPw2SE0IIqXx5eWL/4/F4UFJSEvgr/qgVAJCWloaxsTEePXpUpDp5ePToETp27Ci0uh07dhSIB4AHDx6IjBclKSkJffr0gbS0NG7cuAEZGZlyfZ4QQgipMpWQuwkhhBBSiao4d+/cuRNTp06FlZUVmjZtCnt7e8jJyeH48eNC4/fs2YO+ffti8eLFaNKkCdatW4fWrVtj//79/Jhx48Zh1apVJd4ZVtTLly8xZ84ctGvXDvXq1YOtrS1UVFTg7Oxcrvr/ls8k166RVNVVqFSmkTWqugqV7pOUbFVXoVLF50pWdRUqlRY3p6qrUKnyYhKrugqknKytrTFhwgS0adMG7dq1w+7du5GamgorKysA+b8816pVi/+4lnnz5sHExAQ7duyAmZkZLly4gPfv3+PIkSP8MuPi4hASEoLw8HAAgLe3N4D8q9B1dHT4A+RpaWk4c+YMkpKSkJSUn580NTUhKfl77wfKa36XiKquQqUa9uS3POQSoCyZXtVVqFShEopVXYVKdTfn9+6DuVK/9/Fz66quAPkj1WHSVV2FSjVZo21VV6HSvcqO+n5QNeaTFVPVVahUERlxVV2FSsWTpDtwq5OsrCw4OzsL3N0tISGBXr164dWrV0I/8+rVK1hbWwtMMzU1xfXr18u17E6dOsHBwQFmZmZQUVHBxYsXkZGRge7du5ernN//jI0QQkjVq+Krx0aOHIno6GisWrUKkZGRaNmyJe7evct/OWdISAgkJL7dXNWpUyecO3cOtra2sLGxQYMGDXD9+nU0b96cH3Pjxg3+IDsAjBo1CgCwevVq2NnZwcXFBW/evAEA1K9fX6A+gYGB0NPTq6zmEkIIIT+OrvwmhBBCqpdKyN2ZmZnIzMwUmMbj8UrcxR0TE4Pc3Fz+OXYhbW1teHl5CS07MjJSaHxkZGS56njx4kWMHDkS6urqkJKSgpycHK5du1biPPx7aJCcEEJI5WOsqmuA2bNnY/bs2ULnOTk5lZhmYWEBCwsLkeVNnDgREydOFDm/e/fuYL9AuwkhhJAKoRxGCCGEVC+VkLs3bdqENWvWCEwrvDDsV7Fy5UokJCTg4cOH0NDQwPXr1zFixAg8e/YMhoaGZS6HBskJIYQQQgghhBBCCCGECFi+fHmJR6IIexeYhoYGJCUlERUl+BinqKgo6OjoCC1bR0enXPHC+Pv7Y//+/XB3d0ezZs0AAEZGRnj27BkOHDgAe3v7MpdFL+4khBBS+ejlX4QQQkj1QrmbEEIIqV4qIXfzeDwoKSkJ/AkbJJeWloaxsTEePXpUpDp5ePToETp27Ci0uh07dhSIB4AHDx6IjBcmLS0NAAQenwoAkpKSyCvnsQddSU4IIaTy0YkxIYQQUr1Q7iaEEEKqlyrO3dbW1pgwYQLatGmDdu3aYffu3UhNTeW/y2v8+PGoVasWNm3aBACYN28eTExMsGPHDpiZmeHChQt4//49jhw5wi8zLi4OISEhCA8PBwB4e3sDyL8KXUdHB40bN0b9+vUxffp0bN++Herq6rh+/ToePHiAW7dulav+NEhOCCGEEEIIIYQQQgghpMJGjhyJ6OhorFq1CpGRkWjZsiXu3r3LfzlnSEiIwBXfnTp1wrlz52BrawsbGxs0aNAA169fR/PmzfkxN27c4A+yA8CoUaMAfHsuOpfLxZ07d7Bs2TIMHDgQKSkpqF+/Pk6ePIn+/fuXq/40SE4IIaTyMboajRBCCKlWKHcTQggh1csvkLtnz56N2bNnC53n5ORUYpqFhQUsLCxEljdx4kRMnDix1GU2aNAAV65cKU81haJnkhNCCCGEEEIIIYQQQgj5Y9GV5IQQQiofPdeUEEIIqV4odxNCCCHVC+XuH0KD5IQQQiofY1VdA0IIIYSUB+VuQgghpHqh3P1D6HErhBBCCCGEEEIIIYQQQv5YdCU5IYSQyke3fRFCCCHVC+VuQgghpHqh3P1DaJCcEEJI5aNkTQghhFQvlLsJIYSQ6oVy9w+hx60QQgghhBBCCCGEEEII+WPRleSEEEIqH6NftAkhhJBqhXI3IYQQUr1Q7v4hdCU5IYQQQgghhBBCCCGEkD8WXUlOCCGk0rE8VtVVIIQQQkg5UO4mhBBCqhfK3T+GBskJIYRUPnqBCCGEEFK9UO4mhBBCqhfK3T+EHrdCCCGEEEIIIYQQQggh5I9FV5ITQgipfPQCEUIIIaR6odxNCCGEVC+Uu38IDZITQgipfPRsNEIIIaR6odxNCCGEVC+Uu38IPW6FEEIIIYQQQgghhBBCyB+LriQnhBBS+egFIoQQQkj1QrmbEEIIqV4od/8QupKcEEIIIYQQQgghhBBCyB+LriQnhBBS+egXbUIIIaR6odxNCCGEVC+Uu38IDZITQgipfIxeIEIIIYRUK5S7CSGEkOqFcvcPocetEEIIIYQQQgghhBBCCPlj/fFXkitYDIbSuBGQVFdDlq8/4rftQ9Znb5Hxsj27QeUvK0jV0EH2l1Ak7DuKjBdvv83v0QUKwwZCunFDSKooIWL0NGT7+AsWIs2F6vy/INenBzjSXGS8foe4zXuRFxdfKW1sOqEXWswwg6ymMuI8Q/By5SlEuwWIjNc3a4c2i4dDQVcDSUFReLvxAr48/iAQY7xoGBpb9oC0shyi3vnguc0JJAVG8eerN9dDO5uR0DSqB5aXh8A77/B6zVnkpGWKvX1dx/XB/6YPhJKmCsI8g3F59QmEfPAXGd+yfweYLRwBNV1NRAdG4sbms/BwchOI6b/AAh0te0JWSR6B771x0fYYooMi+fN1m+lj0LLRqGNkAJabB7f/3uDa+lPIqoT21Z/YG41nmkFGUxkJHiFwWXEScaWsP90B7WC41ALyuhpIDozCx/XnEVFk/dXq3wb1x/eCqqEeeGqKuNfLBgmfgwXKkOBx0XL1GNQZ3AESPC4inT7CedkJZMYkib19GuP7Q2vaEEhpqiLdMxBhq48g7YOvyHjl/p1RY+EYSOtqITMoHOGbTyLZ0fnb/L4doT6mL+QMDSClqgTvfvOQ7hEoUAaHx0VN20lQHdgVHGkukp+6ItTWHjkxCWJvH7dLf0j/byg4iqrICw9ExpXDyAsR3T4po86Q7j8WEmpayIsOR+bNf5Dr+a19Ui06gtupHyRrG4Ajr4TUbXORFybYPm5HU0gZm0BS1wAcGTkkLx8FpKeKvW3lQrd9ETGS7j0YMmYjwVFWQ26IP9JP7kNugJfIeG47E8hYWEFCQwd5UaFIP38UOR/efJvfpiukew2EpF4DSCgqI9lmKnKDv+URjrwiZIZNhJRhG0hoaIElJSDb+QXSL52otL41eMJAjJhhATVNNfh7BmDfygPwdhN9fNLNrCusFk+Ejq42QoPCcHTjMbx9/E4gZuKi8ehv2Q8Kygpwf/cZe2z2IiwwnD+/QfP6mGozBY2MGiIvLw9P7zzHoTX2yEjLEHv7+o7vD/NpQ6CiqYogz0AcW30EfqXs+zv27wzLhWOgpauFiKBwnN58Ei5F9v0AMMp6NHpb9oGckjy83nviyIpDiAiK4M+v17wexi2biPot6iMvLw+v/nuFf9b9XSntazCxNxr/lX/sFe8RAmfb0nN37QHt0GLJt9zttkEwd+v2y8/dagW5+7/ewnN3q9VjUHfQt9z9fvkJZFRC7h46YTBG/zUSappq8PPwx66V++DpJroP9hhggqmLraCjq4PQwFAc2ngUrx6/EYiZsmgiBo42g6KSAj6+d8f25bsRGhjGn9+weQPMXDEVjY0aIy8vF063n2HfmoNIr4T113Z8b3SeZgYFTWVEeobgv9UnEfZB9Ppr2r8d/rfQAiq6GogNisLDzefh6/ht/TXp2wZtxvRCDUM9yKkqwr6fDSI9BNefFI+LPrZj0HxgB0hJc+H39CNu255AaiWsvzKj3E3EqM343uhY0K+iPENwd/VJhJfSr5r0b4fuBf0qLigKjzafh1+RftW4bxu0LtKvjvSzQVSRfiWjLA8T62Ew6GoIpVoaSItNgvd9ZzjtuITM5PRKaWPncX3QY/pAKGoqI9wzBNe+c15q1L89+hacl8YERuLW5nPwLHJeamjaFp3G9IauoT7kVRWxvf9ShBdpo5yyPEwXWKBR1xZQraWBlNgkuN9/h/92XkRGJbRx2ARzjCmy79+5ci88Stn3/2+ACaYtnsTf9x/YeERg32/SryuGjBuIxi0aQllVGeP7TIHvZ8HvS5rHxdxVM9FrcA9wpaXxxukdttnsRnyM+MdOLCYOwbiZllDXVIOvhz+2rdiNz26eIuN7DuiOv5ZOQQ1dHXwJDMW+9fZ48fg1f36P/t0wbPxgNDZsBBU1ZYzuZQWfz37F2ieN+atnoc/gnpDmcfHa6S02L9uJuEpo34QplvhrjhU0tTTg4e6NlUs3ws3lk8j4AYP7YLHNHOjWqYXAgGBstNuJxw+eCcQsWj4bo8cPh5KyIt6/ccXyhWsRGBDCn9+8RROssLOGUevmyMvNw+0bD7DGdivSUtPE3r6JUywxc+4kfvtWLNnwnfaZYumKgvb5B2O93U48fvBUIGaxzWyMGW8BJWVFvHvjimXWaxEY8K0PGho1wQq7hWjZujlyc/Nw58Z9rF5ROe0rM8rdP6TKrySPjY2Fo6Mj4uLiAAAxMTHYsmUL1q5dC09P0TskcZDr3R2qC2Yg8egpRIydgWwff2jt2wIJVRWh8dItmkJjgy1S/v0PEWOmI93pBTS3rwXXQI8fw5GVQaabOxL2HRW5XFXrmZDt1gExy9YgatoCSGpoQHObnXgbV6DewPbosGoMXHZdw7V+toj1CEG/M0sho64kNF7LuAH+d2AWvC88wbW+tgi664zexxZAtZEuP8Zo5gA0s+qD58uP49+Bq5Gdlol+Z5ZCkscFAMhpq6D/hWVICorCvwPt8N/YbVBtqAuTXdPF3r5WAzpiiO143N1zBdvMliHMIxgzT9lAQUT79Fs3xIS9c/HKwRFb+y/Dx/vvMOXIYtRoWJsf02vGIHSz6oeLK45hp/kKZKVn4K9TNpAqaJ+SlipmnbVFTHAkdpqvwKEJm1CjYW2M3T5T7O2rPagDWtqNwecdV3Hf1BYJHiEwOb8MPBHtU2/TAB0PzUbAOSfc67MCYXffo/MJaygXWX9ScjKIfuONjxsuiFxuqzVjUbNPK7yctheOQ9dBVlsVXf5eIPb2qQzogpq2kxG55wK8ByxAumcQ6p1eAyl1ZaHxcsaNobdvEWIvPoC32Xwk3n8D/SM2kGlYhx8jIctD6jsPhG8+KXK5tVZOgXLPdgiauRV+I2zA1VaD3uHlYm+fVKsu4JlPQebd80jbPh+5YYGQm7EWHAXh7ZPQawyZ8YuR/fo+0rbPQ86n15CdvAISOt/aB2kZ5AZ6IPOm6PZBmodcTxdkPbgk5hb9gDwm/j9SZaoyd3M7dIfsmL+QcfUUkm2nIzfEH/LLtoCjpCI0XrJBM8jNtkWW039IXjEN2e9fQN56LSR09b4Fycggx/sTMi4Iz90cVXVwVNWRfs4eyUsnI+3wVki1aAu5aYvE30AA3QeaYMaq6Ti16wxm9JsJf48AbDmzESrqKkLjmxo3he0BG/x34S6m9/0LL+6+xNpjdtBrpMePGTVzBIZYmWP38r2YPXAuMtIysPnMJnALcpu6thq2XtiMsKAwzBo4F8vG2kCvYV0s3bVY7O3rPKALrGwn4+KeC1g0YAGCPIOw6vQaKIvY9zcybgzrfYvw6OIDLDSbj7f332DpERvUKbLvHzJjKMwmDoC9zSEsG7wYmWmZWHl6Db99qlpqWH12HSKCIrDUfDHWjbdDnYZ1MGfHPLG3r86gDmi1egzcd17F3YLc3eOc6Nyt0aYBOh2cDf/zTrjbZwVC775H1+NCcvdbb7htFJ27W9uNRa3erfBi+l48qsTc3XNQd8xZ/ReO7zyFSX2n5w+UnN0icvts3qYZ7A7Y4tb5/2BlOg3P7r3Apr/XQr/I9jlm5igMnzQU25btwtSBs5CRloGdZ7dAumD9aWirY8+FbQgNCse0gbNgPWYZ9BvpYcXupWJvX7MBHWBqOwZOe67i8ABbRHmGYOzpZZAXsf5qGzfA8H2z4XLRCfZmK+B1/z1GHbGGVsNv648rK4OQd954uFn0+jNdORaNerbCpZl7cWLEOihqq2LkYfGvv3Kh3P1bqcrc3XRAB/S2HYOne67iaEG/Gn16GeRE9Ctd4wYYum823C464ajZCnjff48RR6yhWaxffXnnjUci+pWitioUtVXxYMM5HO69FDcWHYaBSQsM3DqtUtrYckBHDLYdh3t7LmOn2XKEewRj2qnlIs9L9Vo3xNi9c/HWwRE7+i/Dp/vvYXVkEXSKtFFaTgaB771wa/M5oWUoaatCWVsVNzaewdY+i3F+0SE0MmmJkVtmiL19PQf1wNzVf+HvnScxse80+Hr4Y9fZrVAVse83bNMMaw6sxM3zdzDBdCqe3nuOLX+vQ70i+35ZORl8fOuOAxuOiFzuPLtZ6Ny7I1ZMX4OZw+ZDQ0cdm4+tFXPrgN6D/ocFdrNxdMc/GGs6BT4efth3fofI9rVo0xwbDq3Gv+duY0yfyXC6+wzbT2yEQSN9foysnCzc3nzCvg32IpdrvWYOuvXpjGXTVmHa0DnQ0NbAtr83iLt5GDSkL1avX4KdWw6ib3cLeLh74+yVw1DXUBMa36ZdSxw4tg3nz1yFqclw3Lv9GH+f2YdGTerzY2bOm4xJ08dgmfUaDOxtibS0dJy9cgQ8njQAQFtHExeu/42gwBAM7GWJMcOno1GT+th9oHLaZ7dhKXZsOQhTk+HwcPfC+atHSm3fob+34dzpq+jTbRju3nmEE2cF2zdr3mRMnj4WS63XwKzXKKSlpeP8VcH2OVw/jqCAEJj1HIXRw6ahYeP62HNQ/O0rF8rdP6RKB8nfvn0LAwMD9OzZE/Xr14ezszPatWuHv//+G6dOnYKxsTFcXFwqbfmKY4Yj5fodpN68h5zAYMRt2o28jEwoDOorPH7UUGS8eofk0xeRExSCRPt/kOXlC4UR5vyYtDsPkXTsNDLeOgstgyMvD4XB/RC/yx6Z792Q7eWL2DVbwTNqDunmTcTeRsNp/eB13hE+F58iwTccz5edQE5GJhqNMhEa33yyKUKdPuKj/W0k+IXDeftlxLgHodnE3kVi+sJ1778Ivu+COM8vcJpvDzltFdQ1NQYA1OnVCnnZuXix4iQSAyIQ8yEAz5cfRz2zdlDS0xZr+3pMMcPLC4/w5pITIv3CcHHFMWSlZ6HDiB5C400m9YPnEzc8PnITUf5huLPzIkI/B6LrBNMiMf1xf99VfHrwHuFeIThtfQDK2qpo0adtfvt7tkZudg4urTyOrwERCPnoD4cVR9Gyfwdo1BVv+xpN74eAs44IdHiKJJ8wvF9yHDnpmdC3FL7+Gk7pi0jHj/A+dBvJvuFw33oZCZ+CUH9SH35M8OXn8Nh1DZFP3YWWwVWUhb5ld7itPouvLzwQ/zEIbxcchka7hlBvXV/oZypKc8pgxF64j7hLj5Dp+wWhNgeRl54JtRG9hMdbDUTSExdEH76GTL9QRO44i3T3AGhMMOPHxF9zQtReB6Q8/yC0DAlFOaiN7IWw9X8j5eVHpLv7I2TRHii0aQK5Vo3E2j7p7ubIfnUPOW8fIS/qCzIvHQTLygS3fW/h8SaDkOvlgmzHa8iLCkXWf2eRF+oPbtcB/Jic947IuncBOT5uIpeb/eQGsh5dRm6w6Cs7CKmoqs7dvH4WyHK8g6ynd5EXFoz047uAzExIm/QTHt93KHI+vkXmbQfkhYcg4/IJ5Ab5gtfHnB+T/fwBMq+dRo678NydFxqEtD12yHF9hbyv4cjxcEXGxePgtuoISIj/UGr4tGG4c/4/3Lt4H8G+Idi9bA8yMzLRd5Sp0Pihk83xzukdLtpfQojfF/yz/SR83f1gPnFQkZghOLP3HF7ef4UAz0Bsmb8VGtrq6GLaGQDQoVcH5GbnYu+K/QgNCIX3Bx/sXr4H3cy6oqZeTbG2b+CUwXhw4T4eX3qEUN8vOGxzEJnpmfifiH3/AKuBcH3ign8PX0OYXyjO7ziLQPcA9Cuy7x8weRAu77+Idw/eINgrCHutd0FNSw3t+nQAALTp2Ra52bk4utIe4QFh8PvoB3ubg+jYvzN06tYQa/saTesH/3MFuds3DO+W5ufueqXk7gjHj/A6dBtJfuH4tO0y4j8FoYHVt9wddOU5Pu+6hqhScnc9y+5wtTuLqBceiP8UhNfWh6HZVvy5e+RUC9w8dwd3Lt5FkG8wti3bhcz0TAwYJbwPjpg8FG+c3uKcvQOC/UJwdNsJ+Lj7YriV+beYKcNwcs8ZPL//Ev6eAVg3bzM0tDXQ1bQLAKBTrw7IycnBDps9CPH/Aq8P3ti2bBd6mJmglpi3z45T+sHlgiPcLj1FtG8YbtkcR3Z6JlqNEL7+2lv1hd+Tj3h5+DZi/MLhuOMyItyD0G7Ct/X38dpzPNl7DQHPha8/nqIsWo/sjnvrzyLwpQci3IPw76LDqNOmIXRbiXf9kT9TVefuDlP6wfWCIz5ceooY3zDcLuhXLUX0q3YF/epVQb9yKuhXbYv0q0/XnuPZ3msIFNGvon1CcXnGHvg+ckV8yFcEvfSA47aLaNCzFTiS4s/dJlPM8PrCY7y79ARRfmG4vOIYstOz0G5Ed6HxXSf1g9eTD3A8cgtf/cNxd+dFhH0ORJci56XO157h/t6r8HkhvI2RPqH4569d8HjkgtiQKPi9+oz/tl9As56tISHmNlpOtcCNc7dxu2Dfv3XZTmSmZ5Sy7x+GN05vcbZg339k2wl4u/tiuNUQfszdKw9wfPcpvHsm/PhLXlEeA0f1x941B+H8whXen3ywYcEWtGjbHM1ai3fsZMz0kbh+9iZuOtxBoE8QNi3Zjoz0DAyyNBMaP2rKcLxyfIvTh84jyDcY9lv/htcnH4yYNJQfc+fyPRzb9Q/ePn0vsn2DLc2wa/V+vH/hAq+PPlizYBOM2hmieeumYm3f1JkTcO7UZVw8dx2+3v5YZr0G6WkZGDV2qND4ydPHwunRc9jvOwE/nwBs27gP7h88YDV1ND9myoxx2LP9MO7/5wjPzz6Y99dyaOtowdSsJwCgl2l35GRnw2bRevj7BeGDqzuWWa+B2eA+0NOvI3S5FTV91kScPXkJDmevwcfbH0sW5LfPUkT7pswYB8eHz3Fo33H4+gRg64Z9+PTBA5OmjuHHTP1rPHZvO4x7dx7D87MP5s5YBm0dLfQtaF/vgvYtX7SO376l1mswYLCp2NtHfp4qHSRfsWIFLCwskJiYCBsbG5ibm6Nnz57w8fGBn58fRo0ahXXr1lXOwqWkIN24ITLeFDkYYAwZb10g3UL4DonXommJwe+MV+/BMyz7Dky6SQNwuFxkvPlWTk7wF+RERIEnYrkVJcGVhIahPsKeff42kTGEPfsMLREnTNrG9RH2TDAJhz75CC3j/HjFOpqQ01YRiMlOTke0mz+0jRsAACSlpZCXnSPwwoDcjOz88ts2FEvbAECSK4nazevB+8W3W2gYY/B+8Qn6rRsI/Yxeq4YlDjI8n36Afuv8eqnX1oKylqpAmRnJ6Qh284NeQZlS0lzkZueAFWlfdkYWAKBe28biaRzy159qC31EFV0fjCHqmTs0jIW3T71NfcF4ABFOH6FhXPYTLNUW+pCUlhIoJ9kvAqmhMVBvI74TNQ5XCnKG9ZHy3O3bRMaQ8vwD5FsL/x7lWzcuMfid/NRFZLwwcob1ISHNFSgn0z8MWaFfId9ajIPkklKQ0K2PXJ8i9WUMuT5ukNATvhxJvcYlBr9zvFwhqSe+7arKsDzx/5EqUaW5W1IKkvoNBQezGUOOuzOkGgjPoVL1myLHXfDEP+fjO0jVb/ZDVeHIyYOlp4n9lkYprhQaGjaAyzNX/jTGGFyeuaKpiBPCpsZN4VwkHgDeP3mPpsb58TXq6EBdWx0uz759D6nJafB08+LHcKW5yC6W2zILcpth2x/7roqS4krBwLA+PhbZ9zPG8PH5BzQSsS9v2LoxPhbb97s+deHHa9fWhqqWGj4UiUlLToOvmw8aFezXuTwp5GRnC7Qvq6B9TdqK70RbgisJtRb6iCxH7tYwFpK7n5Qvd6sV5O5IIbm7POV8jxRXCo1aNBQY0GCM4f1zZzQ3Ft4Hmxk3xftngn3wjdM7NDPO365q1qkBDW11vH/+rczU5FR4uHryy5SWlhayfeY/4s6onaF4Gof8Y8uahvoCg9mMMQQ8d4euiGPL2q3rlxj89nv6Ebrl+HGipmH++itaTox/BBJCY8pVjtj9Arn7wIED0NPTg4yMDNq3b4+3b9+WGn/p0iU0btwYMjIyMDQ0xJ07dwTmX716FX369IG6ujo4HA7c3NwE5sfFxWHOnDlo1KgRZGVlUadOHcydOxeJiYnlrvuvpCpztwRXEjUM9QUHsxlDYCn9Srd1/RKD3wHl7FfC8JTkkJmSDpYr3twtyZWEbnN9+BQ7L/V58Ql6rYWf/+q1agDfF4KPgvB6+kFkfFnJKMohIyUdeWJso6h9/7vnLmhuLPwYoblx0xKD32+c3omMF6Zxi4bgSnMFygn2/4KI0EgYlqOc75HiSqFxi4Z4U6x9b5+9RwsRy2nRpjnePhMc/H7l9BaGxs3LvNwmLRqBK83FmyLlBPuFICI0Ei3alL2c7+FyuWjRsimeOb3iT2OM4fmT1zBuayT0M8btWuKZ02uBaU6PX8C4bUsAQJ26utDW0cTzIjHJSSlwdf7IL1NamovsYsdeGen5ubtdh9ZiaRtQpH1PvtWFMYZnT17BuF1LoZ9p07Ylnj15JTDN6fELGLfLr3th+4rGFLavTUGZ0jxpZGWJaF9H8bWv3H6B3F2dVekgubOzM6ytraGoqIh58+YhPDwcU6dO5c+fPXs23r17V0oJFSepogyOlCRyiz0HPC8uHpLqwm/JkFRXKxGfW0q8qDJYVhZYiuAzTMtbTlnIqClCQkoS6dGCB3XpMYmQ0xJ+S7OspgrSiz37MD06CbKaKvz5+WUIi8kvM/yFB+Q0ldFihhkkuJKQVpZD2+UjAQByWio/2Kpv5FWVICklieQYwfYlRydCUVP4cpQ0VZBU7LnTydGJUNRQ5s8vnFY8pnCez0t3KGmq4H/TBkKSKwlZJXkMWpr/i6qyluqPNaoI6YL1l1GsLhnRSZARsf5kNFVKxGdGJ0KmHN+7jJYKcjOzkZ0k+BytjOhEyIj4XitCUlUJHClJZBdbH9kxCZASsRwpTRUR8WX/3qU0VZCXmY3cJME+WN5yvocjrwSOpCTykgX3GSw5ARJKwpfDUVQBS04oES/qMRKEVIWqzN0cReX8fpVYLHcnxYOjLDyHclTUSsYnxoOjUvH+zlFQgsyQcch6fKvCZYiirJaf2+KjBescHxMPNS3hbVTTVC3xbM746ASoaebHqxb8N77Y/jM+Oh6qBfs91xduUNNUxYgZFpDiSkFBWQFTl0/OL19L/YfbVUixIHcnFKtLQkwCVETs+1U0VUrEJ8YkQKWg7ioFuTdRSJmF7fv04iNUNFUxePoQSHGlIK8kj3HLxgPIfxSLuPBE5e6YJMholpK7Y4rn+kTIiit3i/HYS0VNGVJSkiWelRoXHc/f3opT11RDXLHtOS4mHuoF66ZwuxYaUzDP+YUr1DXVMHrGSEhxpaCorIC/bPL3O+piXH9yqvnrL6XY+kiNSYKCiPWnoKkiJD4RCuU4ZlLQVEFOZjYyiq2/8pbzu3FwcIC1tTVWr14NFxcXGBkZwdTUFF+/fhUa//LlS1haWmLy5MlwdXWFubk5zM3N4e7+bbA1NTUVXbp0wZYtW4SWER4ejvDwcGzfvh3u7u74559/cPfuXUyePLlS2vizVGXurmi/Si0WnxKTCPkf6A+yqgroOmcIXM8/rnAZolTkvFRRU+X/7N13eBRVF8Dh36YX0hNCk96kN0G6SgkdFOlIrwpI71WQotJFAREUFekgRUE+OohAGgECJIEUWnolvez3R8ImG3aRJBuXxPM+Tx7I7Nk792R25+zM3rmjOd5R89/k1fphRYeJH3Dl19P5bkOTl+37HfK5738VDk72pCSn8CzXcVvUS2pOfmTmZ0RkWKTa8siwKBy0fAbKzC93fGSeapJDyef5PXuxHR3mZ+9gi5GREeFhEWrLw8IicCrpqPE5TiUdCcsVHx4WgVPW36Oks2NWG+HqMaERlMxq8/LFqziVdGTcxOEYGxtjY2PN3EWZ04iVLKV5vfnxPL+wUPW+hOXoS25Ozo6Eheb6e4SGq+JV+Wlo8/nf7NKFq5R0dmT8xBGq/OYtzszP2dmp4IkJvdDrSfKUlBTMzc2BzG9/LCwscHTMfhE7OjoSERGh7ekAJCcnExsbq/aTLBPV61WUz2POTdlC3TGdGe67ncHum4h7GEZCaLTa6PKiKtj3ET9P+4b3Rnfjqzs/8fn1LUQ8DCU2LBqlvPaE0EzmRis2Cq1263hUV6Ext8ByxgrSHweQdPAl9wYoYgJ9Alk15Uv6jOnN775H2ee+m6cPg4kMjURZDEaQPPR9yMZp6+gxqhe/3t3HdtedhDwMISo0Smp3EeDvE8CyySvpP7YPp/3+4IjHfp4GBRMRGkmG1IPCo+favWbNGkaPHs3w4cOpVasWmzdvxsLCgu3bt2uMX79+PZ06dWLGjBm8+eabLF26lEaNGvH111+rYj766CMWLlxI+/aap3eqU6cOBw4coHv37lSpUoX33nuPzz//nKNHj5KWlpan/r9OCqt2pynTC7XfumJSwpwBO2YQ7veY82sP6rs7hcK0hDmjdswixO8xJ9ft13d3hMDn7n0mfzyPsZ8Mw++JKx73zhMU9IjQkPBiUbt97vrx6fi5jJswjAdP3bjhc4GgwMdZ+enxs6UcdxeIkT5X/sYbb/DgwQMqVqwIwO7duyldOnteyKdPn6oVb01WrFjBkiVL1JZNLl2RKWUqv/R56dExKNPSMbRX/ybTwN6O9IhIzc+JiHwh3vAl8draUJiYoChhqTaaPK/tvIqkyDgy0tJVI7yfM3e0ISFU8yWDiWHRmDuq31zE3MmaxLBo1eOZbViTGBqtFhNxO/suxvcPX+H+4SuYO1qTmpAMSqg7ujOxgZpHfuRHfFQs6WnpL3zbbuVkQ1xYtMbnxIZFY+1o+2J81rf4sVnPs3KyUf3/+e+PvANUv7sduYzbkctYOdqQnJAESnh3VDfCg3SXX0rW9ss98szMyZokLdsvKSz6hXhTJxuScmyrf5IUGo2hqTHG1hZqI9LMnGxI0vJ3zY/0qFiUaekY59oexo62pGlZT1pYtJb4KI3x2towMDXG0NpSbTR5Xtv5J8r4WJTp6RhY2ZGzRCqsbMmI1bweZVw0CitbtWUKK1uUsdE665e+yEmo4qOwavesOhWZXa+SlmdkUsbFZL6vbOzIeVhuYG2HMkZzDVVGR2Jgk6vW29ihjM7H+93MnBIzV6FMSiB+7UJI1/3JgZjIzNpml2uklZ2jHZGhmnOMDIvCzjFXvJOtaoRTVNa/do62am3YOdlx//Z91e9nDp/lzOGz2DnakphV2z4c/QFPAp/qJDeAuKzabZtrX27raEu0ln1/dFj0C/E2jrZEZ+2zo0OjVMuiQrO3q62jLf7eD1S/X/ztAhd/u4CNoy3JCUkolUq6j+pJcFBIwRPLkqytdjtavzC6/LmksGjMHHPXehu1z1n/5KW1Ow/t/JPoyBjS0tKxz/V6s3eye2FE3XMRYZHY53o92zvaEZG1/Z6/Ju2d7IjI8fq0d7TD97af6vdTh89w6vAZ7BztSEpIRKmEfmM+5EmQ7l6fCVGZ269Eru1h6WjNMy3b71lYtIZ4G57l4TPTs7BojEyNMbO2UBtNntd2dK0wandycjLJyclqy0xNTTE1NVVblpKSgpubG3PmZN9Y3cDAgPbt23Plivol8s9duXKFqVOnqi1zcXHh8OHDBepzTEwM1tbWGBnp9dC5QAqrdr9jXYf3bOu99Hn5fV9Z5oov4WhDfD7eDyaWZgzcOZPk+CT2jllLRprua3d+jkvjwqI1x4dr/pu8jKmlGWN+nEPys0R2jF2t8xxftu+PyOe+/1VEhEViYmpCCWtLtdHkdi+pOfmRmV/aC6PTM+uS5i+PMvPLHW+vVsf+SUTo8/xKqI0mt3ey1/p3zY/IiGjS0tJwdFIfFe/k5PDCSOnnwkLDccoV7+jkoBp9HRoSntWGo+r/AI4lHbh9M/u+WIf3H+fw/uM4OjmQkJCIUqlkzMdDCQp4qJPcIDu/3KPinUo6EKotv5Bw1aj47HhHVbwqv5Lq+Tnlyu/Q/uMcypXf2E+GEhjwSCe55YccdxeMXkeS9+/fX+1yua5du6q+4QY4cuQITZs2fWkbc+bMISYmRu3n41IV/3nlaWmk3PXBrGnD7GUKBWZvNSTFy1vjU5K9vDF7S31uIbNmjUm+qTlek5Q7vihTUzFrmt2OUYVyGJV2JlnLevMrIzWd8Jv+lG2VYx4thYIyrWoT6u6n8Tkhbn6UaaU+71a51nUIdcuMjwsKIyEkWq1N4xLmODWoQoib7wvtJYbHkpaQTOUezUhPTnlhvvOCSE9N5+GtB1RvkT0XpUKhoEaLOvi7v9gXgAAPH6q3UJ/fq2aruvi7+wAQ8TCUmNAotTbNSphToUFVAjS0GRceQ0pCMo26NSc1OYV7l7x0kRqQuf2ivPxxzrX9nFvVIVzD3xogwtWPkrm2X6k2dQh307y9NYny8ic9JQ3n1tntWFUpjWU5RyJcX72df6JMTSPhph8lWuaYB02hoETLesS7a77hZLz7XUq0VP8gbtW6gdZ4TRJu+pGRkqrWjmnlspiUK0m8+728JfEy6WlkPPLDsFqO/ioUGFavT0aA5vWkB9zFqJr6vHBGNRqQHiA34BSvj8Kq3VNqV/jnlaenke7vg1HtHLVYocCoTiPSfDXX0DQ/b/V4wKhOE9L8bmuM18rcghKzv4C0VOJXz4fU1Lw9/xWlpabhc9OXhq0aqJYpFAoatmqAt/sdjc/xdvOmUauGassat26Et1tm/NOgYCJCItRiLEpY8GaDmqqYnKLCo0lKSOKdHm1JSU7FLdd80gWRlprG/Zt+1Mux71coFNRrWY97WvblPu53qZtr31+/dQNVfOaI8Ei1Ns1LmFOtQXXuadivx2Tl17J7a1KTU7mR894YBZSRmk6klz+l8lC7w9381Gou5L12Rz6v3a1erN15aeefpKWmcc/Lhyatst9TCoWCxq0acctN83vwtps3jVupvwffatOE226Z78EnQU8JD4lQi7EoYUGthm9qbDMqPIrEhCTa9XiHlOQUrmu5IVp+pKem8+SmP5VaZv8dFQoFlVvW4ZGWz5YP3f3U4gGqtK7DIy2ftTV5cjNz++Vsx6FyaWzLOeapnaJgxYoV2NjYqP2sWLHihbjw8HDS09NxdnZWW+7s7ExwcLDGtoODg/MU/yrCw8NZunQpY8aMyXcbr4PCqt1tbP55XuiM1HSe3vSnYkv1/WKll7yvHml4X1XK4/sKMkeQD/p5NukpaewZuZr05MKp3emp6Ty65U+1HMeZCoWCai3qEJB1nJlbgIevWjxA9Vb1tMZrY1rCnLE/zSU9NY3vR31JWiHkqG3f36RVI265af48dcvNWy0eoGmbxlrjNbnr5UNqSipNWjVWLStf5Q1KlyvFzTy080/SUtO46+VD0xzrUSgUvNWqMV5a1uPleou3csQDNGvThJtur36+447XPVJTUmnaOrudCln5ebnq7rxJamoqXp7etGr7tmqZQqGgVZtmuF2/ofE5btc81eIB2rzbHLfrngAEBT4iJDiMVm2bqR4vYWVJw8b1NLYZHhZBQnwCPd7vRHJSMhfOav6yMz+05/c2btc8NT7H9bqG/N5pjtu1zL5n55cd8zw/Vw1tPs+v5wedM/M791fBExN6odevwxctWvTSx+fNm4ehoeFLYzSNPIg2eLVz/3G/7Mdh8SxSvH1Ivn0Xq4G9MTA349nRkwA4LJlFWmg4MZu+z4zffRDnrWuxGtSHxEt/Y+nyLia1qhO5fI2qTQNrKwxLlcQw61s34wpvAJkjyDMiolDGx/Pstz+wmzKejJg4MuLjsZ8xkeQbt0m5pfngtyBubv2DtmvHEnbDnzDP+9QZ1Qljc1N89pwH4J11Y4kPjuL6yr0A3Pr+JN33z6PumM4EnfakSs/mONarzMVZ2Zc13vr+BA0n9SLGP4S4h6E0mf4hCSHRBJ7MvtFFrWEdCHH1JS0+ibJt6tBs/gCurdhDSq65Fgvq7LbjDF79MQ9v3ifQ8z7vjOyCiYUpV/edA2Dw6k+ICYnk6Be/AnB++x9M2rOId0d14/ZZdxp3b8Ebdauwe853qjbPb/8dl4nvExbwlIiHoXSd1o+YkCi8/syep6/1EBf83XxITkiiZqu69Jw7mCOrdpGo4/zubfmDZuvHEnnDnwjP+9QY3QkjC1P8d2duv2YbxpEQHMXN5XsA8Nl2gvcOzqfG2C48Oe1B+Z7NsatfGdcZ36vaNLG1xKKsI+bOtkDmQTRkjkJLCoshNS4R/1/P0WDxYFKi4kl9lkCjZUMJv+5DhI4P1MK2/Ub51ZNJ8PIj4YYPTiN6YGBhRuS+zHn0yq+ZTGpwJE+/2JkZv+Mo1fYsx2l0L2LPXMeuexvM61bl4exNqjYNbUpgUtYJI+fMb/ZNK5cFIDUsirSwaDLiEojc8z/Kzh9JevQz0uMSKPfZGOLd7pDgocOT5EDKucOYDZxC+kM/MoJ8MG7bE4WJGalX/weA2aApZMREkHIsM7+U80ewmLgC43d6ke7tilGj1hi8UZWkPdmXCWNRAgM7JxTWmfkZlMzMTxkbpZrPXGFli8LaDgPHMpl/k9IVUCYnkhEVBgnqc979a/5jl2kVZ4VVuzMMX612J/+xD4uxs0nzv0f6/buYduoNpmaknD8BgMW42WREhZO0Z1tm/ImDlJi/FtMufUj1+BuT5u9hWLk6Cd+vVrWpsLTCwLEkCtvMESgGpTNrd0Z0JMqYKNUJcoWJKfHfrEBhbgHmFgAoY2N0fkOb/VsPMGvtDHxu+HLX8y69R32AmbkZJ/dkfj6ZtW4G4cERfL8yszYf/P4wa/d/RZ8xvfn79DXe7fkO1etVZ82s9ao2D35/iEGTBvLI/zHBD4MZPn0Y4SERXDp5WRXTc1gPvF29SYxPpHGbRoyZP5ptK7YTn2su0II6uu03Jq6ejJ+XH743fOg+ogemFmacydr3T1ozmYjgSH7J2vcf23GUpXuW02N0L9zOXKdV9zZUqVuVzTn2/ce+P8KHE/vy1P8JIQ9DGDBtEJGhkVz7M/smTp2HduWe2x0S45Oo37oBQ+cO56eVP5Kg4/zubf2Dt9dl1W6PF2v32+vHkRgcxY0V2bW73YH51BzbhcenPajQszn29Spz/SW121pD7X7w6zkaLR5MSnQ8qXEJNP58KGGuuq/de77bx7y1s7nrdQ9vj7v0Hd0bM3Mzju/JfA/OXz+b8KfhbF6Z+R7c+/1BNu1fS/+xffjrf3/Tvud71KxXnVUzs9+De7cdYOikwTx68JgnD58yesZwwkPCuXjykiqm97Be3HS9TWJCIm+1bswnC8by7fLvXpirtqCubPuD91eP5YmXP49v3OftEZ0wtjDFY1/m9nt/zThig6M4/UXm9ru64wTD9syn+egu+J7xoE735pSpW5mjs7O3n7mNJTZlHbHK2n4OlTO337OwaJ6FxZAcl4j7nnO4zB9MYnQ8yXEJdPlsKA/dfHjkoceT5IVQu+fMmfPCaO/c9eB1ERsbS9euXalVqxaLFy/Wd3cKpLBqt5Hi5c957u9tf9Bz9Vieevnz5MZ9mma9r25kva96rhlHXHAUZ7LeV9d2nGDInvm8nfW+qp31vjqe431l9pL3VXxYTOYJ8p9mY2xuwuFPv8HUyhxTq8wvBhIiYlHq+PV9fttxBqwez8ObDwjy9KNt1nHptawcB6z+mNiQSI5/sRuAi9v/4JM9C2k7qit3znrQsHsL3qhbmX1ztqratLCxxLaso+q+VyUrZ362jwuLJi4sBtMS5oz7aS7GZib8MnkTZlbmmGXl+EzHOf763T4WrJ3NXS8fbnvcof/oDzEzN+NY1r5/4fo5hD0N41vVvv8A3+xfxwC1fX8NVubY91vbWuFctiSOWfM/l69SHsgcYR0ZFkV8XDxHd//OpEXjiY2OJT4ugWnLJnLT9Ra3tQwcyK9ftuxh8fq5eN+4y23POwwc3QdzC3OO7s68+e+SDfMIDQ5n0/ItAOzetp+tBzcyaGw/Lp2+gkvPdtSqX5PlM75Uy69UWWecsvKrkCO/iLBI4uPi+e3X40xZPIGYqFjin8UzY9lkbly/yS133Q6g/O6bH1n7zXK8PG7j4X6T0eM/wtzSnD2/HAJg/bfLefo0lJWfrQPg+y0/s//YD4z9ZCj/+/MCPT/oTL0GdZg5ebGqzW2bf2LS9LE8eBDEw8BHzJg7kZDgUE4ez54Tf9jogbhe9SAhPoHW77ZgwZJpLF+yltjYOJ3mt2XTD6z/dgU3PG7h6XaT0eOHYGFpzu6s/DZsXkHwk1CWf7ZW1feDx39k7IRhnD55np69u1C/YR1mTM7eV3737U4mTx+L//1AggIfMWveJEKCQzmRI7/howfies2D+GcJtHm3BQs/m87nS9YSG6Pb/PJEjrsL5LW+ZiwiIoJFixZpnXeuoBJOncPAzgabccMwdLAjxec+oRNnk5F1c07DUiXVCkuKlzfh8z7H9uMR2H4ygtSHjwmbvpDU+wGqGPM2LXBYPFP1u+OKBQDEbP2RmK2ZB3tRa76BDCWOXyxCYWJM0hVXIldlH8jq0oOjVzFzsKbx9N5YONkQ4R3IHx99obrxpmVZR7UcQ918OTPhG5rM7MNbs/oS4x/MqVFribqXfbnIjW+OYWRhSutVIzCxtiDkug8nBn+h9s18yQaVaTztA4wtzIi+/4SLs7fjdyD7QFxXPI5doYS9NV2m9MXayZZHdwL4dugK1WVqdmUd1OZS9Xf34cdPN9J1Wj+6z+hPaEAw28Z8yVOf7Mt9/rf5CCbmpvRfMQZzawseXL/Ht0NXqH0rX6F+VbpM6YOphRkhD56wZ+53XD90Uef5PTzyN6YOVtSZ+SFmTjZE3w7k/MBVJGdtP4uyDmrbL8LVlysfb6LurD7UndOXZ/7BXB6+hpgc269Mx8Y0Wz9W9XuLLRMBuPXVAW6vzpyjz2PRzygzlLTY9imGpkYEn7uJ2+wdOs8v+tgljBxsKD11IEZOdiR6P+DBkMWkZd18zaSMk9pOPsHtLgGTVlN6+iBKz/iI5IAn+I9ZTpJP9lQ/Nh2aUn71ZNXvFTdlvh+D1/5K8LrML0seL92GUplBxc2zUZgYE3fBg0fzv9V5fmkel0i2tMG08yAU1nZkPH5AwpZFKJ9l5qewc8Igxzz9GQF3Sdr5FaZdB6PoNoSMsCckfv85GcHZ+RnVaYb5wOz8zIfOAiD5xC5STmTmZ9yyM6adBqpiLCZl3pwqcdc60q7p9kY+QuRW2LU79e9zJFrZYv7hcBQ2dqQH3id+1SyUWdMYGTiUVDtpne57m4RNn2PWZwRmfUeSEfyY+DULyXgUoIoxbtwCi7GzVL9bTlwIQNKBH0k6+CNGFathVLUWANZrf1brT+ynA8gI1910HQDnjp7HxsGGYdOHZE6J4v2A2R/NU914s2RZ9c8n3m7efD5hBSNmDmPErOE89n/CwlGLCbiXnePub/ZiZmHG1FWTKWFdgpvXbzFn8FxSc9S2mg1qMGzaEMwszHh4/yFrZ6/nfwd0v8+4fOwS1g42DJg6EFsnO/y9H7B0yGLVjTcdyzipzVV5z+0uayetZuD0QQya8RFPA56wasxygnLs+w9tPoiphRnjVnyCpbUld1y9WTpksVp+1epXo/+UAZhZmPP4/iM2z9nE+UPndJ5fUFbtrjsjs3ZH3Q7k3KBVJGmp3eGuvvz1ySbqzepDvdl9ifMP5uII9dpdtmNj3l6XXbtbbs6s3TdXH+BWVu12X/wzSqWSVt9l1u6n527iOkf3tfv0kXPY2tsyavpw7J3s8L19n2mDZ6luHutcpqTapb63XG+zeMLnjJk5grGzRvLI/zFzRi7EP8fr85dvdmNuYcbML6ZSwroEXtdvMm3wbFJybL83G9Zk5PShmFuYE3j/IV/MWsvJA6d0nt/tY39j6WDFu1M/pISTDcHegfw8ZBXxWdvPpoz69nvo5suBSZt4b3of2s3oS2RAMLvHrCHUJ3v71ejQmF6rs7dfn02Z2+/c2gOcW5e5/U4uzdx+/TZ/iqGJEfcv3OT4fN1vP33TdKJVE0dHRwwNDQkJUd+/hoSEUKpUKY3PKVWqVJ7iXyYuLo5OnTphZWXFoUOHMDY2znMbRUlh127vY39j4WBF26z3VYh3ILtyvK+sc72vHrn5cmjSJt6d3od3s95Xe8esISzH+6p6h8b0zPG+6p31vjq/9gAX1h2kdJ2KlGtUFYAJF9eq9WdDy0+JeaR5Gob88sw6Lu00pQ/WTrY8vhPI1qErVTcstSvriDLH5/4Adx9+/nQjnaf1o+uM/oQFBLNjzFcE58ixdocmDPhqvOr3IV9/CsDJdfs5uW4/5epUokLDagDMu6B+PmFpq4lEPQrTWX6nj5zFzt6GUdOH4eBkj+/t+0zJte/POQ/zTdfbLJqwjDEzRzBu1ige+j9m1sgFPMix72/VsQUL1s5W/b7s28zPX9tW/8D3azLv+7J+8SaUGUpWbF2CsakxV89d58u563SW13OnjpzBzsGWcTNH4uBkj89tPyYOnK66WWmpss5qn028XG8x7+MlfDxrNJ/MGcND/0dMHz6X+/f8VTFtOrZi8fq5qt9XbMmcrmjrV9vZujpz/75m0UYyMjL4YtsyTEyNuXLuGqtmZw/C1JUjh05g72jP9LkTcCrpyO2bdxn84VjVzTzLlCutlp/rNU8mjJ7JzHmTmLVgMv4PAhk5eCL37mR/cfvN+u+xsDDni7WLsbax4vrf7gz+cCzJySmqmIaN6jB99idYWFpw39efWVOXcGDP0ULJz8HRnplzJ6ryG9g7O7+y5UqrvT5dr3ny8aiZzJo/iTkLJuN/P5Dhg9Tz27T+eywszfly3RKsbay49rc7A3uPUc+vcV2mz5mApaUFfr4PmDllMfsLIT/x71Eola/vnRRv3LhBo0aNSM/jnJ9BTdoVUo9eDyeDS/9zUBF306hwLoV7XbRMfq2/nyqwGiZ6/Ob0X1Dl/dd2t6kTVut0X9jjlw3WeZuW83/+5yDxr8tv7Y4e9F4h9ej10Pt88d7vA9gYmum7C4WqT6qVvrtQqL5W6G5u79dRB6Pi/fl5ceAvOm9T37W7WbNmNG3alI0bNwKQkZFB+fLlmTBhArNnz34hvl+/fiQkJHD0aPbnmBYtWlCvXj02b96sFhsQEEClSpXw8PCgQYMGao/Fxsbi4uKCqakpv//+OxYWFnnIsGjKb+1eWmFQIfXo9RClKBo3Ji2IK6m6/aL/dZOaUXRvuPsqnibp9r52r5uM1/d0pU48jdbtFQOg/9pd1On1iO3IkSMvffzBgwcvfVwIIUQRIZd9FRtSu4UQ4j9Cz7V76tSpDB06lCZNmtC0aVPWrVtHfHw8w4cPB2DIkCGULVtWNaf5p59+Stu2bVm9ejVdu3Zl9+7duLq6snVr9vQVkZGRBAUF8eTJEwDu3cucaq9UqVKUKlWK2NhYOnbsSEJCAj///DOxsbHExmaOdnZycvrHKUleV1K7hRDiP0KOuwtEryfJe/XqhUKh4GWD2RUKxb/YIyGEEEK8jNRuIYQQ/4Z+/foRFhbGwoULCQ4OpkGDBpw4cUJ1c86goCAMctyLqkWLFuzatYv58+czd+5cqlWrxuHDh6lTJ/vmiEeOHFGdZIfMG1pC5pzdixcvxt3dnatXrwJQtWpVtf74+/tTsWLFwkq3UEntFkIIIf7Zq90lq5CULl2agwcPkpGRofHH3d1dn90TQgihKxkZuv8ReiG1Wwgh/iNeg9o9YcIEAgMDSU5O5urVqzRr1kz12Llz5/jhhx/U4vv06cO9e/dITk7m1q1bdOnSRe3xYcOGoVQqX/h5fmPOd955R+PjSqWyyJ4gB6ndQgjxn/Ea1O6iTK8nyRs3boybm5vWx//p224hhBBFRIZS9z9CL6R2CyHEf4TU7mJDarcQQvxHSO0uEL1OtzJjxgzi4+O1Pl61alXOnj37L/ZICCGEEC8jtVsIIYQoWqR2CyGEEP9MryfJW7du/dLHLS0tadu27b/UGyGEEIVG+d+6TKs4k9othBD/EVK7iw2p3UII8R8htbtA9DrdihBCCCGEEEIIIYQQQgihT3odSS6EEOI/4j82l5kQQghR5EntFkIIIYoWqd0FIifJhRBCFDrlf+yu2EIIIURRJ7VbCCGEKFqkdheMTLcihBBCCCGEEEIIIYQQ4j9LRpILIYQofHLZlxBCCFG0SO0WQgghihap3QUiJ8mFEEIUPinWQgghRNEitVsIIYQoWqR2F4hMtyKEEEIIIYQQQgghhBDiP0tGkgshhCh8SrmBiBBCCFGkSO0WQgghihap3QUiI8mFEEIIIYQQQgghhBBC/GfJSHIhhBCFT+ZGE0IIIYoWqd1CCCFE0SK1u0DkJLkQQohCp5RiLYQQQhQpUruFEEKIokVqd8HIdCtCCCGEEEIIIYQQQggh/rNkJLkQQojCJ99oCyGEEEWL1G4hhBCiaJHaXSByklwIIUThy5C7bAshhBBFitRuIYQQomiR2l0gMt2KEEIIIYQQQgghhBBCiP8sGUkuhBCi8MllX0IIIUTRIrVbCCGEKFqkdheIjCQXQgghhBBCCCGEEEII8Z8lI8mFEEIUPvlGWwghhChapHYLIYQQRYvU7gJ55ZPkR44ceeVGe/Toka/OCCGEKJ6USinW+iC1WwghRH5J7dYPqd1CCCHyS2p3wbzySfJevXqp/a5QKNT++AqFQvX/9PT0gvdMCCGEEAUitVsIIYQoWqR2CyGEEPrxynOSZ2RkqH7+/PNPGjRowB9//EF0dDTR0dH8/vvvNGrUiBMnThRmf4UQQhRFGUrd/+TRpk2bqFixImZmZjRr1oxr1669NH7fvn3UrFkTMzMz6taty++//672+MGDB+nYsSMODg4oFAo8PT1faGPr1q288847WFtbo1AoiI6OznO/C0JqtxBCiHx7DWr3f5HUbiGEEPkmtbtA8jUn+eTJk9m8eTOtWrVSLXNxccHCwoIxY8Zw584dnXVQCCFEMaDn4rpnzx6mTp3K5s2badasGevWrcPFxYV79+5RsmTJF+L/+usvBgwYwIoVK+jWrRu7du2iV69euLu7U6dOHQDi4+Np1aoVffv2ZfTo0RrXm5CQQKdOnejUqRNz5swp1Bz/idRuIYQQefIfOzB+HUntFkIIkSdSuwvklUeS53T//n1sbW1fWG5jY0NAQEABuySEEELo1po1axg9ejTDhw+nVq1abN68GQsLC7Zv364xfv369XTq1IkZM2bw5ptvsnTpUho1asTXX3+tivnoo49YuHAh7du317reyZMnM3v2bN5++22d55RXUruFEEKIokVqtxBCiKJGH1dwA1y5coX33nsPS0tLrK2tadOmDYmJiXnqe75Okr/11ltMnTqVkJAQ1bKQkBBmzJhB06ZN89OkEEKIYkyZodT5T3JyMrGxsWo/ycnJL6w7JSUFNzc3tZPZBgYGtG/fnitXrmjs75UrV144+e3i4qI1viiQ2i2EECIvCqN2i7yR2i2EECIv9F27n1/BvWjRItzd3alfvz4uLi6EhoZqjH9+BffIkSPx8PCgV69e9OrVi1u3bqlinl/BvWrVKq3rvXLlCp06daJjx45cu3aN69evM2HCBAwM8nbaO1/TrWzfvp3333+f8uXL88YbbwDw8OFDqlWrxuHDh/PTpE7NC7PRdxcK1TODGH13odD1TC3e2/CYSYK+u1CoTiiM9d2FQrXmcYS+uyCAFStWsGTJErVlixYtYvHixWrLwsPDSU9Px9nZWW25s7Mzd+/e1dh2cHCwxvjg4OCCd1xPXvfa7fk/B313oVCVMSv+N1e7lRzyz0FF2EUzM313oVA14cWpp4qTgeZSu0XR87rX7hhFhr67UKjeyMjX6ZIiZUqZfI2bLDK6PkzTdxcKlZ2Jlb67UKg8bu/SdxdEHuW8ghtg8+bNHD9+nO3btzN79uwX4nNewQ2wdOlSTp06xddff83mzZuBzCu4gZdeQTVlyhQmTZqkto4aNWrkuf/52utXrVoVLy8vTp06pTrB8Oabb9K+fXu1u20LIYQQQKHMjTZnzhymTp2qtszU1FTn6ykupHYLIYTIExn5rXdSu4UQQuSJHmv38yu4c96L61Wu4M59TO/i4pKnL4JDQ0O5evUqgwYNokWLFty/f5+aNWvy+eefq93T41Xk+6tRhUJBx44d6dixY36bEEII8V9RCAONTE1NX+mkuKOjI4aGhmqXKkPm5cqlSpXS+JxSpUrlKb6okNothBDilRXvQcJFhtRuIYQQr6wQandycvIL05pqOhbX1xXcDx48AGDx4sV89dVXNGjQgJ07d9KuXTtu3bpFtWrVXrmtVz5JvmHDhldudNKkSa8cK4QQQhQmExMTGjduzOnTp+nVqxcAGRkZnD59mgkTJmh8TvPmzTl9+jSTJ09WLTt16hTNmzf/F3qsO1K7hRBCiKJFarcQQojXyatOc6ovGRmZ3wyMHTtWNc1Lw4YNOX36NNu3b2fFihWv3NYrnyRfu3btK8UpFAop1kIIIdTo+2ZdU6dOZejQoTRp0oSmTZuybt064uPjVUV0yJAhlC1bVlVAP/30U9q2bcvq1avp2rUru3fvxtXVla1bt6rajIyMJCgoiCdPngBw7949IHMU+vMR58HBwQQHB+Pn5wfAzZs3sbKyonz58tjb2xd63lK7hRBC5Je+a/d/ldRuIYQQ+VUYtftVpznV1xXcpUuXBqBWrVpqy998802CgoJeuR3Iw0lyf3//PDUshBBCvC769etHWFgYCxcuJDg4mAYNGnDixAnVpV1BQUFqd75u0aIFu3btYv78+cydO1d1g6w6deqoYo4cOaI6yQ7Qv39/QP1b9c2bN6t9696mTRsAduzYwbBhwworXRWp3UIIIUTRIrVbCCHE6+RVpznV1xXcFStWpEyZMqpBa8/5+PjQuXPnV24HCjAn+XNKZea3FHLjECGEEFq9BqPRJkyYoLU4nzt37oVlffr0oU+fPlrbGzZs2D+e6F68ePFrcxlaTlK7hRBC/KPXoHaLbFK7hRBC/KP/4BXcCoWCGTNmsGjRIurXr0+DBg348ccfuXv3Lvv3789T/w3+OUSznTt3UrduXczNzTE3N6devXr89NNP+W1OCCFEcZZRCD8iz6R2CyGEeGVSu18LUruFEEK8Mj3X7n79+vHVV1+xcOFCGjRogKen5wtXcD99+lQV//wK7q1bt1K/fn3279+v8Qruhg0b0rVrVyDzCu6GDRuyefNmVczkyZOZM2cOU6ZMoX79+pw+fZpTp05RpUqVPPU/XyPJ16xZw4IFC5gwYQItW7YE4NKlS4wbN47w8HCmTJmSn2aFEEIIUUikdgshhBBFi9RuIYQQRY0+ruAGmD17NrNnz37VbmqUr5PkGzdu5Ntvv2XIkCGqZT169KB27dosXrxYirUQQgg1cvMv/ZPaLYQQIi+kduuf1G4hhBB5IbW7YPJ1kvzp06e0aNHiheUtWrRQGzYvhBBCAHKJ9WtAarcQQog8kdqtd1K7hRBC5InU7gLJ15zkVatWZe/evS8s37NnD9WqVStwp4QQQgihW1K7hRBCiKJFarcQQgjx78nXSPIlS5bQr18/Lly4oJob7fLly5w+fVpjERdCCPHfJpd96Z/UbiGEEHkhtVv/pHYLIYTIC6ndBZOvkeS9e/fm6tWrODo6cvjwYQ4fPoyjoyPXrl3j/fff13UfhRBCCFFAUruFEEKIokVqtxBCCPHvyddIcoDGjRvz888/67IvQgghiiuZG+21ILVbCCHEK5Pa/VqQ2i2EEOKVSe0ukHyfJM/IyMDPz4/Q0FAyMtS3Qps2bQrcMSGEEMWHUor1a0FqtxBCiFcltfv1ILVbCCHEq5LaXTD5Okn+999/M3DgQAIDA1Eq1ee7USgUpKen66RzQgghhNANqd1CCCFE0SK1WwghhPj35Osk+bhx42jSpAnHjx+ndOnSKBQKXfdLCCFEcSLfaOud1G4hhBB5IrVb76R2CyGEyBOp3QWSr5Pkvr6+7N+/n6pVq+q6P0IIIYohuexL/6R2CyGEyAup3fontVsIIUReSO0uGIP8PKlZs2b4+fnpui9CCCGEKCRSu4UQQoiiRWq3EEII8e955ZHkXl5eqv9PnDiRadOmERwcTN26dTE2NlaLrVevnu56KIQQouiTb7T1Qmq3EEKIfJParRdSu4UQQuSb1O4CeeWT5A0aNEChUKjdMGTEiBGq/z9/TG4gIoQQQrwepHYLIYQQRYvUbiGEEEI/Xvkkub+/f2H2QwghRDEmc6Pph9RuIYQQ+SW1Wz+kdgshhMgvqd0F88onyStUqFCY/RBCCFGMSbHWD6ndQggh8ktqt35I7RZCCJFfUrsLJl837vzxxx85fvy46veZM2dia2tLixYtCAwM1FnnhBBCCKEbUruFEEKIokVqtxBCCPHvyddJ8uXLl2Nubg7AlStX+Prrr/niiy9wdHRkypQpOu2gEEKIok+ZofsfkTdSu4UQQuSF1G79k9othBAiL6R2F8wrT7eS08OHD6latSoAhw8f5sMPP2TMmDG0bNmSd955R5f9E0IIURwoFfruwX+e1G4hhBB5IrVb76R2CyGEyBOp3QWSr5HkJUqUICIiAoA///yTDh06AGBmZkZiYqLueieEEEIInZDaLYQQQhQtUruFEEKIf0++RpJ36NCBUaNG0bBhQ3x8fOjSpQsAt2/fpmLFirrsX6FrP6QTXcb0wsbJlod3Ati5aBsPbvhpjW/apTm9pw3AsVxJQgKesmflT9w4664W88HU/rw7oAMW1hb4uN7lh3lbCQl4qnq8Qp3K9J/9EZXqVSUjIwPXP67wy9IfSE5IKpQcOw/pQq+xH2DrZEfAHX+2LdyC7w1frfEturZkwLTBlCxXkqcBT9i54gfcz7qpxQyYOoj2AztiaW3JXdc7bJn7DU9z5FimUhmGzhtOzSa1MDI2IvBuALu++plbV27qPL+aQ9tTZ3xXzJ1siPQO4uqCnYR7PtAaX6FbUxrN+JAS5RyJ9Q/BdfluHp+5oRbTYHpvqg98FxNrC0JdfbgyZwdx/iGqx+3rVKTJvH441q9MRkYGgcevc33JL6QlJOs8v+L+Gn3vo050HtsTGydbgu4E8Mui7/F/SX5NujTng2kDcCznRIj/U/at/Bmvc+r59ZrSn7YD2mNhbYGv6z1+mp8rv9qV6DP7IyrVr0pGegauf/zN7mWFk5+pSy9Me/THwNae9EA/ErZvIN3vrtZ447fbYt5/JAZOpcgIfkTCz1tI87ia/XjT1ph27IFh5eoYWNkQO2MU6QHqfy+T9t0wadUeo0rVUFhYEj20G8qEZzrPLS/+a5dpvY6KU+0uM9yF8h/3wKSkLc+8A/Gdu504D+37Dafub1NpVn/M3nAiwT+YB0t/JvK0h+pxxy5NKTO0I1b1KmNsb4XrezN4djtArY3SH7XH+f1WlKhXCSMrCy5VG0pabEJhpVjs9/19h3/A0I8H4uBkj4+3H6vmreW2xx2t8e27v8vHM0dT5o1SBPk/YsOyb7l0+opazPiZo3h/UHesrK24cd2L5bO+Isj/kerxmnWr8+n8j6ndoCbp6RmcPn6O1Ys2kpig+xNNbT5yocPY7lg72fLoTiB7F20n8MZ9rfENu7xN92n9cCjnRKh/MIdX/sLtc9mv0QYuTWk9qANv1K1MCTsrlneZwSNv9fmIjUyN6T1vCI27t8DIxJg7F26we8E24sJjdJ5fq4868t7Y7lg72fD4ThAHFu0g6CX5NejSjC7T+mJfzokw/2COrtyF9zlP1eP1XN6i5aAOvFG3EpZ2VnzRZRaPNeTXa95gGmXld/fCDfYt2F4o+dkM7I79iA8xdLQj+e4Dwj7/hqSbPlrjS7i0xnHSEIzKOpMa+Jjw1duJv3A9+/EOLbHp1wWz2tUwtLUm8P2PSb6r/lnVpk9nrLq9i2mtKhiWsMSvaW8y4uJ1nlteSO3Wv+JUu1t81IF3xnbHysmGp3eCOLToBx6+ZL9Rr0szOk3rg105J8L9gzm+8lfu5thv1HF5i+aD2lMua7+xpstsnuTYb5jbWOIypQ/VW9fFrqwjzyJiufWnKyfX7CUprnC+YKg/pD2Nx3bF0smGsDtBnF24k5Ab2o9Lq3VtSotpH2JdzpHogBAurthNwNns49KqnZpQb3A7StatiLmdFT93mkuYd5DqcVMbS5pP7U2FNnWxLutAQkQs9/9046+v9pNSCDmW6NMTq8F9MXSwJ8X3PtFfbiTF+57WePN2bbAZNxyj0qVIffiImI3fkfTXtezH321FiQ+6Y1yzOoa21gQPGkOqj/prwmnzaswaN1Bb9uzAUaJWrtNlagD0G96bYR8PwjHrs8mKeWu45eGtNb5D9/eYMHOM6rPJ2mWb1D6btOvSlj5D3qdWvZrY2tvQp90Q7t1WPw9jYmrC9MWT6NSzPSamxvx19irLZn9JZHiUzvPrP7w3wz8ejGNJe+55+7F87uqX5tex+3tMmDWGsm+UJtD/IWuXbuJijvzad3mHvkOz8+v93kca85uxeBKde3XAxNSYy1n5RYRF6jy/Xw8cZceu/YRHRlGjamXmThlP3Vo1tMafPHORr7/byePgECqUK8uU8cNp06IpAKlpaWzc+iMXr7jy6MlTSlha8vZbDZkybjglnRxUbcTExrF8zTecu3wVAwMD2r/TkjmfjsPCwlzn+b0qqd0Fk6+R5Js2baJ58+aEhYVx4MABHBwyXyRubm4MGDAgT22lpKSwd+9epkyZwoABAxgwYABTpkxh3759pKSk5Kd7r6xZt5YMnD+cQ+v3sqDbdILuBDDzp4VYO9hojK/WuAYfb5zK+b2nWdB1Gm5/XmPy1lmUq15eFdN13Pt0HNaVHXM3s7jnbJITkpn50wKMTY0BsC1px+xfFhES8JTFvWbx5ZCllK1enjGrJxZKji27t2L4glHsWfcr07pOJuCOPwt//gwbLTnWaFyTqRtncHrPn0zr8ilXT/7N7O/mUT5Hju+P703X4d3YMucbZvWYTnJCEgt//kyVI8C8HQsxMDRkYf95TO86mQBvf+btWIitk61O86vYoxlvLRqE55pDHOk0n0jvIDr8MgszB2uN8U5NqtF20yf4/HqeIy7zCTrpxnvfT8G2RjlVTJ2Pu1FrREeuzN7O8e6LSEtIpuMvszDMys/c2RaX3bOJDQjhWPfFnBr0JbY1ytFq3Vid5gbF/zXatFsL+s8fxm/r97K46wweegcybecCrLRsv6qNajBuwxQu7DnNoi7Tcf/zGhO3zqRs9TdUMV3G9aLD8C7snLeFpb3mkJKYxNSdCzDKkd/0XxYREhjM0l6zWTN0KWWrv8HIryboPD/jFu9iPvRjkvb9QOys0aQH3qfEvC9RWNtqjDesXhvLyQtJPnOc2JmjSLl2iRIzl2HwRiVVjMLMjLS7N0n8eavW9SpMzEj1vEbioV90nZIowopL7Xbq2YKqS4YSsHofrh1m8ex2IPV2z8PYUfN+w7pJdWptnszTXWdwbT+T8D+uUeeHmVjWzN5vGFqYEXP1Lg+W/ax1vYbmJkSe9SRo/SGd55Rbcd/3d+zZjmmLJ7Jl9XYGdhyBz20/vvl1DXaOthrj6zepw4pvF3P412MM6DCcc39cZM2OFVSpmb1vHDZhEANGfsjymV8ypMtoEhOS2LR7DSamJgA4OTuyee96HgY84qMuY/hk4FSq1KjEZxvm6Ty/xt2a03v+EI6v38+KrpkneyfunEcJLbWtcqPqjNjwKX/tOcOKLrO48ed1xm6dQekctc3EwhQ/17scXql9v/7hgqHUbdeYbR+vYW2/Rdg42zFm8zSd59ewW3Pen/8RJ9fv58uuc3jiHcj4nXO05lexUXWGbJjE33vO8mWX2dz805WRW6dTunr2Zy8TCzMeuN7lyMpdWtf7/oIh1GnXmB0fr2NDvyVYO9sxYvNUnedXonMbnGaNJmLTzwT1nkDyvQeU/e5zDO01v//MGrxJ6a9mE3PgJEEffMKz01cos3EhJtUqqGIU5mYkut8mbPV2retVmJsSf9GVyC17dJ6TKLqKS+2u3+1tesz/iFPrD7Cu61yeeAcyeudsrfuNCo2qMWjDRK7tOcfaLnO49acrw7ZOo5TafsOUANd7HF/5q8Y2bJztsHa25djyX/iq4wz2TN9Mzbb16btK98dsANW7N6PNgkH8ve4Qv3SdT/idID74eRbmWnIs3bgaXTZ+wq095/mly3z8TrrR47spOOTI0djClMfX73Fpheb9QglnO0o423Lx813s7DCbP6dtpWLbenT8crTO8zPv8A62k8cRu20nwR+NI9X3Pk4bV2FgZ6sx3qReLRyWzSf+tz8IHjyWxPOXcfzqM4yrVFTFKMzMSL5xi5ivv3vpup8dOsbjTh+qfqI3aj8Oyi+Xnu2YsXgSm1d/T7+Ow7h325fNv67F3tFOY3z9JnVZ9e0SDv16lL4dhnLmjwus37GKqjUrq2LMLczxuObFumWbtK535mef0rZDS6aPnsfw9z/GqZQja7ev1Hl+nXq2Z+aST/l29Tb6dBjKvdu+bNm9Tmt+DZrU5YvNn3Fo11H6tM/Mb8MPX+TKzwz3qzdY+5L8Zn02mXc6tmLq6LkM6zUep1KOrCuE/P7433m+2LiV8SMGsW/7RmpUrcTYqfOJiIrWGO9x05uZi1fyfjcX9u34mvdaN2fSnKX4PggAICkpGe979xk7bAB7t3/NuuXzCQh6xIRZS9TzW/IFfv5BfLduOZu+WIyb5y0Wf7FB5/mJf0++TpLb2try9ddf89tvv9GpUyfV8iVLljBv3qsfbPj5+fHmm28ydOhQPDw8yMjIICMjAw8PD4YMGULt2rXx89M+aqqgOo/qzrndp7i47wxPfB+xY+4WkhOTadP3PY3xHYd3w+u8B79v+Y0nfo85sPpXAm75035oZ1VMp5HdOPL1ftxPXefh3UC2TN2AbUl7GnfM/EaqYbsmpKem8+OC7wh+8AR/Lz92zN1M0y7NKVmhlM5z7DGqF6d+PcmZfad55PuQzXO+ITkxmXb9OmiM7zaiBx7n3Tm85RCP/B7x6+pfeHDrPl2GdcuOGdmDfRv3cu3UVQLvBrB+ylrsS9rTrOPbAFjZWVOmclkOfrufwLsBPA14ys6VP2JmYUb5GhU0rje/ao/ujM+us/jtvUCM7xOuzN5BWmIy1fq31Rhfa6QLj895cXvzcWL8nuDx5X4ibwXw5vDsv0etUZ24sf43Hv7pTtSdh1z8dDMWzraUd2kMwBvtG5KRls7fc38k9v5TIm484Mrs7VTs2hSris46za+4v0Y7jurOhd3/49K+szzxe8TOeVtISUymdd92GuM7jOjKzfMenNj6G0/vP+bQmt0E3vanXY78OozoxtGN+/E4dZ1HdwP5bupG7JztaJSVX/2s/H5W5XefnfO28FYh5GfWrQ/Jp4+Tcu4EGY8CSdi6BlKSMHmvi+b4rr1J9bxG8pE9ZDwOImnPdtIf+GLW6X1VTMqFUyTt30naTTeNbQAk/76f5MO7SPfRPjLg36bMUOj8R+RNcandb4zrxtOfTxO8+xwJPo/wmbGVjMQUSg/QvF8sN6YrkWc9efjNERJ8HxOwag/Pbj6g7Ijsv0HI/gsErtlP1AXtVzs92vo7QRsPE+umfTSprhT3ff/gsf04+MtRjuz+nQc+AXw+80uSEpPp1b+bxvgBo/vy19mr7PxmF/6+gXzzxXfcuelD/+EfqmIGju7Ld+t+5NzJS/jeuc+CiUtxcnbk3U6tAWjdoQVpaWmsmL2awPtBeHve5fOZX9K+27u8UbGsTvN7b1Q3Lu8+zd/7zhHs95hf531HSmIKLfq+qzH+3RFd8D7vyf+2HiX4/mOOrdnDw9sPeGdo9mv02qGL/LHhAHcva36NmlmZ06LvexxY9iM+V27z8JY/P834hipNalKxYTWd5vfOqK78tfsMV/edJ8TvMXvnbSMlMYW3+76jMb7tiM7cPX+DM1uPEXL/Cb+v2cuj2/60HuqiinE9dJGTGw7ic/mW1vze7vsuh5b9hO+V2zy65c+uGZup3KQGFRpW1Wl+dkM/IHbfCWIPnSLlfhChizeiTErG+gMXzfFDehF/yZWo7ftJefCQiA07Sbrjh+3AHqqYuCOnifxmFwl/eWhsAyB652Gitu0l6Yb2q83+bVK79a+41O62o7pydfcZrmftNw7M+57UxBTe0rLfaD2iM/fO3+Dc1mOE3n/CyTX7eHzbn5Y59hvuhy5xasNBfLXsF4N9HrFz/Dq8T7sTERSK35Xb/PHVHmq1a4SBYb5Og7xUo1GdufXrWbz3XSDS9wn/m5N5XFqnn+bj0oYjXAg474XbluNE+j3hyur9hN4KoMGw7OPSOwcvc3X9YYIuad43Rvg84ti4DTz4nwcxgaE8/Muby1/uo1K7hih0nKPVwA95dvh34o+eJM0/kKgV68hISsayRyfN8f0/IOnKdeJ+3ktaQBCxm38g5a4vJfr0UsUk/PE/Yrf9RNI17cc1AMqkZDIiolQ/ynjdX8k3ZOwADvxyhN92H+eBTwBLZ35B4ks+mwwa3ZfLZ6/ywze/4O8byKYvtnLn5j21zybH9p9gy5rt/H3xusY2SlhZ8v6A7ny1eAPXLrtxx+seCyZ/TsOm9ajXqLZu8xs3gP0//8bhrPw+m7GKpMQk3h+gOb/BY/px+ezf7PjmFx74BvD1qq1437zHwBHZ+R3df4LNa7Zz5YL2/D4Y2J0vFq3n2iU3vL3useDTZZn5NdZtfjv3HOLD7p15v2tHqlSqwMIZEzEzNeXQsT81xv+89zdaNmvCiEEfUqVieSaOGUKt6lXYtf8oAFYlLNm2fjmd2rWhUoVy1K/zJnOnjsf7ni9Pg0MBuB8QxKW/XVky+1Pq1a5Jo/p1mDtlPH/87zyhYRE6zS8vpHYXTL73nBcvXmTw4MG0aNGCx48fA/DTTz9x6dKlV25j/Pjx1K1bl5CQEM6dO8eePXvYs2cP586dIyQkhNq1a/PJJ5/kt4svZWhsRMW6Vbh9yUu1TKlUcvuSF1Ubab4ko2qj6mrxADcveFAtK97pDWdsS9px61L2JVKJcQk88PRVtWlkakxaahpKpVIVk5KU+c19jbfe1E1yWYyMjahStyo3cvRHqVTidcmTGlpyrNGoJjcueaot87zgQfVGNQFwLu+MfUl7tZiEuAR8PX2o0TgzJi4qlkd+j3i393uYmptiYGiAy6BORIdFcf+m7j58GRgb4lCvEk8v3s5eqFTy9NJtnBprPmByalyVpxfVP2Q8Puelii9R3gkLZ1ue5vggkhqXSJjHfZwaZx5kGpgYkZGaBjm2YXpSKgDOTavrJDco/q9RQ2MjKtapwu3L6vl5X/aiaiPNf8cqDavjfVk9v1sXPKmSK7+cbSbGJXA/Z34mRqRrya+aLt+DRkYYVq5BmleOD31KJalebhhVr6X5KdVrq8cDqTeuYaglviiRu2y/Hop67VYYG2FVrzJRF3PsB5RKoi54Yd1E837DunF1oi6o7zciz97QGq9vxX3fb2RsxJv1anA1xwGVUqnk6kVX6jWpo/E59RrX5uoFV7VlV85dpV6TzAOssuXL4OTsqBbzLC6eWx7eqjZNTE1ITUlVyy85KXOKtAbN6usmOcDQ2JDydSpzL8dJG6VSyd3LN6mkpbZValj9hZPf3hduUKnRq5/cLl+nMkYmRmrthNx/QsSjMCprWW9+GBob8kadSvjkys/n8k0qas2vmtrfA+DuhRta4zV5Iyu/nOsNvf+EyEdhWv+u+WJshFntasRfyXEyW6kk/ooH5g00vw/M6r9JwhX1k98Jl9y0xhclUrtfD0W9dhsaG1K2TiW1L8GUSiW+l29RQct+rkLDavjm+tLs3gUvrfGvyszKgqRniWSk6/bFaGBsiHPdSgRdUj8uDbp0m9KNNB+Xlm5U9YWT34EXvLTGvypTKwtSniWi1GWORkaY1KxO8rUc07gplSRfc8e0rubjFJO6tUi6rn5ck/S3KyZa4l/GolM7ypw6SKnd27D5ZCQKU9M8t/Eyzz+b/P3CZ5Pr1Nfy2aR+4zpqn2UA/jp3VWu8JrXq1cTYxFhtvQF+gTx59JR6TermMQvtjIyNqFWvhtrJeqVSyd8XrlNfy3rqN67zwsnvv87+rTVek1r1X8zP3y+QJw+f5qmdf5Kamor3PV/efquBapmBgQFvN2nAjVuap/K7cfsOzZs0UFvWolljbtzWPvXfs2cJKBQKrKwsM9u4dQdrqxLUeTP7c8jbTRpiYKDAy1t/X3hL7S6YfJ0kP3DgAC4uLpibm+Pu7k5ycuZBRkxMDMuXL3/ldi5fvsyyZcuwtn7xEiRra2uWLl3KxYsX89PFf2RlZ4WhkSEx4dFqy2PDo7VOCWLrZPtCfEx4DDZZ8bYlbVXL1GOisXHKvIzF+/JNbJxs6TK2J4bGRlhYW9Jv9kdZz9d8qUt+WdlbZ+WoPp9VdHg0tk6a12XrZEt0WLR6fFg0ds9zzHpe7r9D7jYXD5xPpdqV2XVnL3t9D9JjdE8+G7KY+Bjdza1oam+FgZEhibn+3olhMZg7ab4k1tzJlsSwWPX48FjMs/Izz9qGGmNKZrYZfNkbcycbao/rioGxISY2FjSe20/t+bpQ3F+jz/OLzd3fsBisteRn42RLbO6+h0Vjk3WJ/vM8Y3O9hmPDsv8Gd/66hbWTLZ3GZOf34azBQPbfRxcUVjYoDA3JiFGfb00ZE4WBrb3m59javxgfrT1eiLwoDrXb2N4KhZEhKWHq+4GUsBhMtLx/TUraaoiP1hqvb8V9329nb4uRkRGRueaijAiLxKGk5n2dY0kHLfEOWY9nPu9lMdcuueFQ0oEhHw/EyNgIKxsrJs0fD4BTSQd0pYSdtcbaFhcWrbW2WTvZvjCvdlxYDNZapp/R1kZqciqJuebJjwvXXlPzwzIrP039tdKyHiut+Wn+rKaJtZMtaVry07be/DC0tUZhZEh6RLTa8vSIaAy1XJJu5GhHeq7tnfaSeCHyojjU7uf7jWea9gN52G88C4vBKg/7xdws7KzoMPF9/v71dL7b0MY867g0IVefE8JjsNByXGrpZEtCrmPO+LBYLAqwTzOzK0GzSb24uetsvtvQxMDWJnPfGKl+XiE9MgoDB82129DBnowI9fiMyCgMtcRrk3DyDJELVxA2bhqxP/yKRecO2C+dk7cE/sHzzya558mOCIvEUctnBMeSDnmK19ZGSnIKcbHq946KCItSfbbRBe35ReUpv/CXxGtrQ2N+4ZE4Ounus1dUdCzp6Rk42KvXXQd7O8IjNc/tHh4R9UK8o70d4RGa45OTU1j77Xa6tG9LCUtLVRv2turvbyMjQ2ysrLSuV7z+8nWSfNmyZWzevJnvvvsOY+PseahbtmyJu7v7S56pztbWloCAAK2PBwQEYGtr+9I2kpOTiY2NVftJV6a/ch/+bY99H7J12kY6j+rB93d/5WvX7YQ9DCE6NIqMDOU/N1BEjFk2jpjwGOZ9OJuZPaZx9eRV5m5fgJ2OvwjQh2ifx1ycvIU6Yzsz2G87/Tw28SwojMTQaJTFYBsW99foE9+HfD9tI51Gd2fLnV2su/494Q9DiQmLKhbb73WlVCp0/iPy5nWv3Smvce3+Lyju+/4H9/xZOGkZH43rzxX/0/zP6wiPg54SHhpBxn9tiIwQr0hqt/697rU7rYjUbtMS5ozaMZMQv8f8ue6AvrtTKExKmNPrh+lE+D7m77UH9d0dnYk/dJykv11Jve9PwonTRC5eicW7rTEsW1rfXRP/EalpaUxbsBylUsmCGbq/j5muSe0uGKP8POnevXu0adPmheU2NjZER0e/cjujRo1iyJAhLFiwgHbt2uHsnDmfc0hICKdPn2bZsmVMnPjyG0atWLGCJUvUJ8+va12T+rYvv8QxLiqO9LR01QjU56wdXxxJ/Vx0jhGrz9k42hCTFR8dGp29LDQqR4wtgd7+qt+v/HaRK79dxNrRhuSEZFAq6TyqO2FBwS/tc17FRcZm5ah+YtrW0ZboMM3fbEWHvThSzdbJlqjnOWY9z8bRlqgcOdo62uLvnXnn7rot69G43Vt8VHcAic8y76q9df631G/dgHc/bMfBb/brIj2SI+PISEvHPNdIJHMnGxJzjRp8LjEsGnMn9REU5o7WJGbll5i1Dc2drFX/fx4TeTv7TuL+h6/gf/gKZo7WpCUkgxJqjelMXFBowRPLUtxfo8/zyz1SzsbJ5oWR4M/FhEW/MPLMJscIyud5WjvZqv6f+bsND70DVL//feQSfx+5pMpPqVTiMqoboUEhBcwqmzIuBmV6OgY29uQ8fFDY2JERrflu3sroSAxs1EcNKGy1xxclcg5K/1732j3U4k2GlXj5/ISpkXEo09IxyTUqy8TJhpQc++ycUkKjNcTbao3Xt+K+74+KjCYtLQ17J/V9nYOTPRGhmvd14aERWuIjsh7PfJ69kz3hoRFqMfdu+ap+P3HoFCcOncLe0Y7EhCSUKBk8th+PAp/oJDeAZ1GxGmublZOt1toWGxaNVa7aZuVk88Jo9JeJDYvG2NQYc2sLtdHWVo7aa2p+xGflp6m/cVrWE6c1P82f1TSJDYvGSEt+2tabH+nRsSjT0jF0sFVbbuhgS3q45s/OaeFRGOba3kYviS9KpHbr3+teu5vb1KaF7cunTXi+3yihaT+Qh/1GCScb4vKwX3zO1NKM0T/OJulZIj+MXUNGmu5P7CdmHZda5OqzhaMNCVqOS+PDorHIdVxq6WRNQj72acaWZry/cwap8UkcHbNO5zlmRMdk7htzjbw1tLcjI0Jz7U6PiMTAQT3ewN6OdC3xryrlVuY0FsZvlCX98dMCtfXc888mDho+a+T8XJFTeGhEnuK1tWFiaoKVdQm10dYOTnaqzza6oD0/uzzl5/iSeG1taMzP0Z5wHc7ZbWdrjaGhARG5Rm9HREbhaK95kKajg90L8eGRUTjmes0+P0H+JCSU7RtWqkaRP28jMlr9/Z2Wlk5MXJzW9f4bpHYXTL5GkpcqVUrjjT0uXbpE5cqVNTxDs88++4xZs2bx5Zdf0qBBA8qUKUOZMmVo0KABX375JbNmzWLx4sUvbWPOnDnExMSo/dSx+ee5CdNT0wi4eZ9aLeuplikUCmq3rIef+z2Nz/Fz96F2S/UPAXVa18c3K/75iKvaOdo0K2FO5QbVNLYZGx5DckISzbq3JDU5VW2uUF1IS03j/k0/6uXKsW7L+tzTkuM997vUa6k+N2f9Vg3wcc8sRiFBIUSGRqrFmJcwp1qD6txzy4wxNc+cIyz3qFxlRgYKhe6+hcpITSfCy5/SrXKcVFEoKN2qNmFumuc+D3PzU48HyrSpo4p/FhRGQki0WoxxCXOcGlYhzM2X3JLCY0lLSKZij2akJ6fw9ILmm6rkR3F/jaanphFw6z61WmT3V6FQ8GaLevi5a74x3n0PH2q1qKe2rHaretzPlV/ONs1KmFPln/LrlpnfbV2+B9PSSH9wD6O6jbKXKRQY121MmpYbaqb53FaPB4zrNXmtbsApiq7XvXYPtKz5j+tWpqYR5/UA29Y59nMKBXat6xLrqnm/Eevmox4P2LWtpzVe34r7vj8tNY07Xvdo1rqJaplCoaBpq8Z4uWquoV5ut2naurHasrfbvIWXa+bcr4+DnhAWEk6zHDGWJSyo07CWxjYjw6NITEjEpWc7UpJT+Pu85htO5Ud6ajpBtx5Qo0X2nKQKhYIaLergr6W2+Xv4ULOF+vZ7s1U9/N1f/NyhTdCtB6SlpFEjRzslK5fGoZwTD7SsNz/SU9N5eMuf6rnyq96iDgFa8/NViweo0aqe1nhNHmbll7OdkpVLY1/OSevfNV9S00i67YvF2w2ylykUWLzdgERPzfOUJt24ox4PWLRopDVeiLx43Wt3U5t/nl86PTWdx7f8qZZrv1G1RW0CteznAj18qdZC/Zitequ6WuO1MS1hzuif5pCemsaOUV+Rlpyap+e/qozUdEJu+vNGS/Xj0jda1uapu+bj0qfufpRvqZ5j+VZ1tMZrY1LCnA9+nkV6ajq/jVhDemHkmJZGyl0fTN9qmL1MocD0rYYk39R8nJJy0xuzt9SPa8yaNSZFS/yrMq5eBYD0cN2dRNb22aRZqybc0PLZ5IbbLbV4gLfbNNUar4m3111SU1LV2qlYpTxlypXGy1X7zeTzKi01DW+vezRr/ZZqmUKhoFnrt7ihZT033G7xdo54gOZtm2qN18T7xvP8stupWKU8Zd4onad2/omxsTG1alTjqqunallGRgZX3TypX0fz4Nn6td/kbzdPtWVXrntQv3Z2/PMT5EEPn7Bt3XJsbdS/1Kpf501i455x+272fumqmycZGUrq1frn4xrxesrXSPLRo0fz6aefsn37dhQKBU+ePOHKlStMnz6dBQsW5KmtWbNmMWvWLPz9/QkOzhypVKpUKSpVqvRKzzc1NcU0140bDBWGr/TcP7YdZczqifh7+fHghi8uI7pjamHKhX1nABi7ZhJRwRHs/eIXAP7ccYy5e5bSeXQPPM+48Xb3VlSqW4Xtszer2jzx/TF6TvyQYP+nhD0M4cNpA4gOjcTtz2uqmPZDO+Prdo/k+ETqtK5P/7lD2bvyJxJidX+X5iPbDjNp9RTu3/TD19OHbiN7YmZhxum9/wNg0topRAZH8POqnQAc236EZXtX0GN0L9zOuNKqR2uq1KvKt7O/VrV57Psj9JnUj6cBTwgJCmHg9MFEhkZy9c+/Abjndo/4mHgmrZnC3vW/kpKUQocBLpR8wxm3M7o7EAW4/d0ftF47lnAvf8I97lNrdCeMzE3x3XMegFbrx5LwNAr3lXsB8P7+JJ33z6P22M48+p8nlXo2x6FeZf6auV3Vpve2E9Sb1IvYByHEPQyl0YwPSQiJJuhk9o1Hag7rQKirL2kJSZRpXYcmCwbgtnwPKTrehsX9NfrntqOMWj2RgJv3eeDpS8eR3TC1MOVSVn6jVk8kOiSS/Vn5ndp+nFl7PsNlVHdunHWnWfeWVKxbhR/mZOd3avsxuk/8kJCAp4Q/DOX9aQOIConCPUd+7YZ0xs/tLkkJSdRuVZ++c4ewf9XPL8x1WlBJx/Zh+ckc0u/fI83vDmZdPwRTM1LO/gGAxYQ5ZESGk7Tru8z44wewWrIe0259SXX/G5OW72FYpQbxW1ar2lSUsMLA0RmFXeY8bgZl3gAgIzoSZdaIc4WtPQa29hiUKguAYflKKJMSyQgPQfksTqc5vqr/2l2xX0eve+02ecXa/XDzMd7c8AlxnveJ8/Cj3JiuGFiY8nR35vybNTdOIDk4Ev/PdwHwaOtxGhxeQrlx3Yj8nzsle7XEqn4VfKZvUbVpZFsCs7KOmJTKHPVhXrUMkDkKPSVrRJeJky0mJW0xr1QKAMs3y5P+LImkx+GkRavPtVhQxX3f//OWPXy2fh7eN+5yy8ObgaP7Ym5hxm+7jwOwdON8Qp+Gs3F5Zv9//W4v3x3axEfj+nPxf3/h0qs9terXZOmMVao2d323l1GThxL04BGPg57w8azRhIWEc/ZE9hy7/Ub05sb1myTEJ/J227eYvOATNn7+Lc9idbv9zmw7xpDVnxB48wGBnn68O7ILphamXNl3DoChqz8hOiSS3774FYCz239nyp7FtBvVjVtn3WnSvSXl61bhlzlbVW1a2FhiX9YRm6w5Sp0rZ75GY8OiiQ2LISkukb/2nqH3/CEkxDwjMS6BfktG8MDtHgEeeTup9E/ObTvOoNXjCbr5gCBPP9qO7IKJhSlX92V+9hq0+mNiQiI59sVuAM5v/4NJexby7qiu3D7rQaPuLXijbmX25MrPrqwjNlnT8pXMkV9cVn5/7z1Lr/kfER/zjKS4RD5cMhx/Nx8CPXR3U3iAqB8PUmrFdJJv+ZJ08x62Q97HwNyM2EN/AlBq5XTSQiIIX7sjM37nYd7Y+SV2wz7g2flrWHd5B7Pa1QhZtF7VpoFNCYxLl8Qoay5X40rlgMxR6M9HnBs62mHkaIdxhczcTatXJCM+kdSnoWTE6PY1+qqkduvf6167jV6xdp/fdpz+q8fzKGu/0XpkZ0wsTLmetd/ov3o8MSFR/JG137i4/Q8+3rOQtqO64n3Wg4bdm1OubmX2z/lO1aZ51n7DOmu/4VQ5c/qNuKz9hmkJc8b8NAdjM1N+nLwaMytzzKzMAXgWEavzaRbdt/2By+qxhN70J9jzPg1HdsLYwpTbezNzdFk7lmfBUVxelXlc6rH9JH32zqPR6M74n/GkRo/mONerzP9mZx+XmtpYYl3WAUvnzBztqmTmGB8WQ0JYjOoEuZG5CScmf4uJlTkmWTkm6jjHuF37cVg0i5Q7PqTcvovVgN4YmJsRf/QkAPaLZ5EeFk7Mpu8z43cfpOSWtVgN6kPipb+x6PguJm9WJ2r5GlWbBtZWGJYqiaFj5r7RqELmcU16RCQZEVEYli2NZad2JF6+SkZMLMbVKmM35WOS3G+Q6vdAZ7kB7NzyK8vWL8D7xl1uetxm8Oj+mFuYcXj3MQA+37iQkKdhbFj+LQC/fLeX7Ye+Yci4AVz431907tWe2vVr8tmMlao2rW2tKV3WGadSjgBUrFoeyBxhHREWybO4eA79epTpSyYREx3Ls7h45nw+Dc/rN/Fyv40u7dz8K59vWMBtzzvc8vBm8Jh+WfllfvZavnEhocFhrPs8M7+ft+5hx+FvGTpuIBf+d5nOvTpQu/6bLJ7+Yn4ls/KrVLXCC/kd3HWUmUsmERMdQ3xcPHOXT8PzuhdebrrNb0i/95n3+Wpq16xGnVo1+HnvYRKTkunVtQMAc5Z+RUlHB6aMHw7A4L49Gf7JTH749QBtWjTlj/+d5/ZdXxbPmgRkniCfOu9zvH382PTFEjIyMgjPugrCxtoKY2NjqlQsT6u3m7B41XoWzphIaloay9d+S+f2bSmpwznX80pqd8Hk6yT57NmzycjIoF27diQkJNCmTRtMTU2ZPn36P16mpU2lSpVeKNAPHz5k0aJFbN++XcuzCubqsctYOVjTe+oAbJxsCfL258shS1WXfzqUcUSZkX2tgq/bPb6dtJYPpw+kz4xBhAQ8Zd2YVTzyyZ6G4/jmQ5hamDJixTgsrC3xcb3Dl0OWkprjG90q9avxwZT+mFmY8fT+Y3bM2czlQ+cLJcfLRy9hbW9D/6mDsHOyw9/7AZ99tEg1PYVTGSe14nnP7S5rJ33FwOmDGTxzCE8DnrBy9OcE5cjx0LcHMDM3Y/yKCVhaW3LH1ZulHy1S5RgXFctnQxYxaMZHfLb7cwyNjHjoE8TKUZ8TcCdAp/kFHLmKmb01Daf3xtzJhsjbgZwa/AVJ4Zk3QSlRxhFy5Bfm6sv5Cd/QaGYfGs3qS6x/MGdGriX63iNVzK1vjmFkYUqLL0ZgYm1ByHUfTg3+Qu1beceGlWkw/QOMLcyIuf+Ev2Zt58GByzrNDYr/a/Tasb+wsreh15T+mfnd8WfN0GXZ+ZV1RKnM3n5+7vfY8uk6Ppg2gN5Z+W0c8wWPfR6qYn7ffBgTczOGPc/v+l3WDF2qNnKkUv2q9JrSD1MLM54+eMyPc7dwpRDyS/3rLInWtpj1G46BrT3pAX48+3wmypjMA2IDR2fIkV+6z23i1y/FfMBIzAeOIuPpY559MZ+Mh9nTIRg3aYnlJ7NVv5eYsgiAxL0/kLTvBwBMO/TAvO8wVYzV0o0AxG9aScq5EzrPUxQNxaV2h/32FyYO1lSa2Q+TkrY8ux2A14DPSc26nNmsrPp+P9bVhzvj11Np9gAqzx1Iov9Tbg37gvi72fsNR5cm1Nzwier32lunABDw5V4CvtoHQJmhHag4o68qpuGRpQDcnbSJ4D3ndJpjcd/3//nbaewcbBk/c1TmlCi3fflkwDQis04WlirrrDYP+g3XW8z9eDGfzBrDhDljCfJ/xNThc7h/N3vf+MPXv2BuYc78r2ZiZV0Cz2tefDJgGinJKaqYOg3fZNz0kVhYmhPgF8jnM7/g+P6TOs/P7dgVSthb021KX6ydbHl0J4Cvhy5X3YTOrqwjGTn2/Q/cfdj+6QZ6TOtPjxkDCAt4ypYxX/I0R22r16EJQ77Kfo2O/DrzNXp83T6Or8t8je5f+iPKDCWjv52GkYkRdy7cYPeCbTrPzyMrvy5T+mTlF8jmoSvV8stZuwPcfdj56Ua6TOtHtxn9CQsI5vsxX/HUJ/uzV50OTRj01XjV78O+/hSAP9bt58S6zGn6Di3diTIjgxHfTsXIxIi7F7zYt+B7nef37I8LhNvZ4DDpIwwd7Ui+84DHY+arbuZpVLqk2mfnJM87PJ2xCsdPh+IwZRipgU94MvEzUnwDVTEl3m1OqRXTVL+XWTMXgIivfyZi088A2PbrisOEwaqYN37O/II8eM5qYg+f0nmeomgoLrX7xrG/KWFvjcuUD7FysuXJnUC2DV2pupln7v1GoLsvv3z6NZ2m9aXzjH6EBwTzw5jVBOfYb9Tu0Jj+OfYbH2XtN/5ct58/1x2gXJ2KVGhYDYA5F7K/tAL4vNVEoh6F6zRHn6NXMbe3pvnU3lg42RDmHcihj74gIeu41KqMo9q+46mbL39M+oYW0/vQcmZfogOCOTJ6LRE5cqzSoREua8aqfu+6KXObX1l7kL/XHqRknYqUblQVgBEXs08+A3zfYjKxOswx8dQ5om1tsBk7DEMHO1J87hM2aTYZWVNWGJYqqXZck+LlTcT8z7EZPwKbj0eQ9vAx4dMXkno/QBVj1qYFDotmqn53XJ75xU/M1h+J/W4npKVh2rQRJfpnnpBPCwkl4cxFYrf/rLO8njv522nsHOz4eOYoHJ0cuHfbl/EDpuT6bJL92euG601mf7yIibPGMGnOOIL8H/Lp8Fn43c0+ef+OSyuWrc/+MuvLLcsA+ParbXz7VWb9+mLhejIylKzZtgITU2Mun73K57O/1Hl+J377H3YOtkyYORrHkg7cve3LuAFTVDfnLF22lNpnL0/Xm8wav5CJs8fy6dxxBPo/ZNKwmWr5vevSms83ZOf31dbM/L75chvffJX5+WPVwnVkZGSw7vsVGJua8NfZqyyd9YXO8+vcvi1R0TF8ve1nwiMjqVmtCptXL1VNe/I0JBSDHLMaNKxbi1WLZ7Fx64+s3/IDFcqVZcOKBVSrXBGA0LAIzl7KHAT64bBP1Na1feMqmjbKvDpz1aKZfL7mG0ZOmoOBgYL277Rk7uTxiKJLocxZjV5Beno6ly9fpl69elhYWODn58ezZ8+oVasWJUqU0Gnnbty4QaNGjUhPz9ucWh9V+ECn/XjdPFMWzmVir5Oe6ZrvAl5cnDbS/VUDrxMjHU6r8zpa85bu5lB7HdlljXbUpaAm7XTeZnnX0zpvs7gqCrX7nHMfnfbjdfO9WdG4uVlB3ErW3X0dXkfNzcrquwuFyjh/szAWGZ+YR+u7C4Wq+h3dfwkutVu/ikLtnl5xgE778bopm/FqI+WLsg+ddTOv9+uq68PifdydkbfTeUWOx+1d+u5CoTJ2fPVps16V1O6CyfNIckNDQzp27MidO3ewtbWlVq1/nodMmyNHjrz08QcPdHsJjRBCCP2Qy770S2q3EEKIvJLarV9Su4UQQuSV1O6Cydd0K3Xq1OHBgwevPH+ZNr169UKhUPCywey6vNGjEEII8V8ltVsIIYQoWqR2CyGEEP+efF1XuWzZMqZPn86xY8d4+vQpsbGxaj+vqnTp0hw8eJCMjAyNP+7u7vnpnhBCiNeMMkOh8x+RN1K7hRBC5IXUbv2T2i2EECIvpHYXTL5Gknfp0gWAHj16qH3jrFQqUSgUrzyXWePGjXFzc6Nnz54aH/+nb7uFEEII8WqkdgshhBBFi9RuIYQQ4t+Tr5PkZ8+e1cnKZ8yYQXx8vNbHq1atqrN1CSGE0B857tI/qd1CCCHyQmq3/kntFkIIkRdSuwsmXyfJ27Ztq5OVt27d+qWPW1pa6mxdQggh9Oe/dpnW60hqtxBCiLyQ2q1/UruFEELkhdTugsnXSXKA6Ohorl27RmhoKBkZGWqPDRkypMAdE0IIIYRuSe0WQghRlGzatIkvv/yS4OBg6tevz8aNG2natKnW+H379rFgwQICAgKoVq0aq1atUk1ZAnDw4EE2b96Mm5sbkZGReHh40KBBA7U2tm7dyq5du3B3dycuLo6oqChsbW0LKcN/JrVbCCGE+Hfk6yT50aNHGTRoEM+ePcPa2lptfjSFQiHFWgghhBqlUr7R1jep3UIIIfJC37V7z549TJ06lc2bN9OsWTPWrVuHi4sL9+7do2TJki/E//XXXwwYMIAVK1bQrVs3du3aRa9evXB3d6dOnToAxMfH06pVK/r27cvo0aM1rjchIYFOnTrRqVMn5syZU6g5/hOp3UIIIfJC37W7qMvXSfJp06YxYsQIli9fjoWFha77JIQQophRZvxzjChcUruFEELkhb5r95o1axg9ejTDhw8HYPPmzRw/fpzt27cze/bsF+LXr19Pp06dmDFjBgBLly7l1KlTfP3112zevBmAjz76CICAgACt6508eTIA586d010y+SS1WwghRF7ou3YXdQb5edLjx4+ZNGmSFGohhBCiiJDaLYQQoqhISUnBzc2N9u3bq5YZGBjQvn17rly5ovE5V65cUYsHcHFx0RpfFEjtFkIIIf49+RpJ7uLigqurK5UrV9Z1f4QQQhRDGXLZl95J7RZCCJEXhVG7k5OTSU5OVltmamqKqamp2rLw8HDS09NxdnZWW+7s7Mzdu3c1th0cHKwxPjg4WAc91w+p3UIIIfJCjrsL5pVPkh85ckT1/65duzJjxgy8vb2pW7cuxsbGarE9evTQXQ+FEEIIkS9Su4UQQrxOVqxYwZIlS9SWLVq0iMWLF+unQ68hqd1CCCGEfrzySfJevXq9sOyzzz57YZlCoSA9Pb1AnRJCCFG8yA1E9ENqtxBCiPwqjNo9Z84cpk6dqrYs9yhyAEdHRwwNDQkJCVFbHhISQqlSpTS2XapUqTzFv66kdgshhMgvOe4umFeekzwjI+OVfqRQCyGEyE2ZodD5j/hnUruFEELkV2HUblNTU6ytrdV+NJ0kNzExoXHjxpw+fVq1LCMjg9OnT9O8eXON/W3evLlaPMCpU6e0xr+upHYLIYTILznuLpg83bjzvffeIzo6upC6IoQQQghdk9othBCiKJo6dSrfffcdP/74I3fu3GH8+PHEx8czfPhwAIYMGcKcOXNU8Z9++iknTpxg9erV3L17l8WLF+Pq6sqECRNUMZGRkXh6euLt7Q3AvXv38PT0VJu3PDg4GE9PT/z8/AC4efMmnp6eREZG/htpA1K7hRBCCH3I0407z507R0pKSmH1RQghRDGlVOq7B/9dUruFEELkh75rd79+/QgLC2PhwoUEBwfToEEDTpw4obo5Z1BQEAYG2WO+WrRowa5du5g/fz5z586lWrVqHD58mDp16qhijhw5ojrJDtC/f39AfV70zZs3q82b3qZNGwB27NjBsGHDCitdNVK7hRBC5Ie+a3dRl6eT5EIIIUR+/Ncu0xJCCCGKutehdk+YMEFtJHhO586de2FZnz596NOnj9b2hg0b9o8nuhcvXiw3EhVCCFEkvQ61uyjL80lyb29vtcvRNKlXr16+OySEEEII3ZLaLYQQQhQtUruFEEKIf1eeT5K3a9cOpYbx+wqFAqVSKXfZFkII8YIMucu2XkntFkIIkVdSu/VLarcQQoi8ktpdMHk+SX716lWcnJwKoy9CCCGEKARSu4UQQoiiRWq3EEII8e/K80ny8uXLU7JkycLoixBCiGJKKd9o65XUbiGEEHkltVu/pHYLIYTIK6ndBSM37hRCCFHo5C7bQgghRNEitVsIIYQoWqR2F4xBXoLbtm2LiYlJYfVFCCGEEDomtVsIIYQoWqR2CyGEEP++PI0kP3v2bGH1QwghRDEmNxDRH6ndQggh8kNqt/5I7RZCCJEfUrsLJl/TrdjZ2aFQvPiHVygUmJmZUbVqVYYNG8bw4cML3EEhhBBFn8yNpn9Su4UQQuSF1G79k9othBAiL6R2F0y+TpIvXLiQzz//nM6dO9O0aVMArl27xokTJ/jkk0/w9/dn/PjxpKWlMXr0aJ12WAghhBB5J7VbCCGEKFqkdgshhBD/nnydJL906RLLli1j3Lhxasu3bNnCn3/+yYEDB6hXrx4bNmyQYi2EEEJuIPIakNothBAiL6R265/UbiGEEHkhtbtg8nTjzudOnjxJ+/btX1jerl07Tp48CUCXLl148OBBwXonhBBCCJ2Q2i2EEEIULVK7hRBCiH9Pvk6S29vbc/To0ReWHz16FHt7ewDi4+OxsrIqWO+EEEIUCxlKhc5/RN5I7RZCCJEXUrv1T2q3EEKIvJDaXTD5mm5lwYIFjB8/nrNnz6rmRrt+/Tq///47mzdvBuDUqVO0bdtWdz3Ng2mk6WW9/5bPNNy8pbipqUzQdxcK1Q/psfruQqHaYGSu7y4UqhLfbtd3F4qc1+EGIps2beLLL78kODiY+vXrs3HjRlUN02Tfvn0sWLCAgIAAqlWrxqpVq+jSpYvq8YMHD7J582bc3NyIjIzEw8ODBg0aqLWRlJTEtGnT2L17N8nJybi4uPDNN9/g7OxcWGlq9brX7gbtI/Sy3n9Lq/Nl9N2FQtfcuJK+u1CoSqTquweF60m+jgqKjkoXv9F3F4qc16F2/9e97rU7iQy9rPffMiP4gr67UOi2JpXVdxcKVWeLyvruQqFKoXjPrTGmyQx9d6FQ7Qg4oPM2X4farY/j7ueUSiVdunThxIkTHDp0iF69euWp7/kaST569GjOnz+PpaUlBw8e5ODBg1hYWHD+/HlGjhwJwLRp09izZ09+mhdCCCF0as+ePUydOpVFixbh7u5O/fr1cXFxITQ0VGP8X3/9xYABAxg5ciQeHh706tWLXr16cevWLVVMfHw8rVq1YtWqVVrXO2XKFI4ePcq+ffs4f/48T5484YMPPtB5fq9CarcQQghRtEjtFkIIUZTo67j7uXXr1qEowMBihVJZ/KZ196zQQ99dKFSf6bsD/4KZqcV7ONNsAxlJXpS96bpe310oVMaOuh9xcbWM7k8MN3ty8NVjmzXjrbfe4uuvvwYgIyODN954g4kTJzJ79uwX4vv160d8fDzHjh1TLXv77bdp0KCBauTWcwEBAVSqVOmFb7RjYmJwcnJi165dfPjhhwDcvXuXN998kytXrvD222/nJd1iL3rQe/ruQqHa8x8YSZ6u/4ErhapE8R4wWexHkk9zK96foItj7RavvwkV++m7C4Vq85NL+u5CoatmKyPJi7LiPpI8vpjPElEYI8n1Xbv1cdz9nKenJ926dcPV1ZXSpUvnayR5vj8OZ2Rk4OfnR2hoKBkZ6kcNbdq0yW+zQgghiiF9fnxLSUnBzc2NOXPmqJYZGBjQvn17rly5ovE5V65cYerUqWrLXFxcOHz48Cuv183NjdTUVLUbbtWsWZPy5cvr7SS51G4hhBCvqnifeik6pHYLIYR4Vf/F426AhIQEBg4cyKZNmyhVqlSe+/5cvk6S//333wwcOJDAwEByD0RXKBSkp6fnu0NCCCHEq0hOTiY5OVltmampKaampmrLwsPDSU9Pf2EecGdnZ+7evaux7eDgYI3xwcHBr9y/4OBgTExMsLW1LVA7uiK1WwghhChapHYLIYTQt9f9uBsypzlt0aIFPXv2zNPzcsvXnOTjxo2jSZMm3Lp1i8jISKKiolQ/kZGRBeqQEEKI4qcw7rK9YsUKbGxs1H5WrFih71RfW1K7hRBC5EVh1G6RN1K7hRBC5MV/8bj7yJEjnDlzhnXr1hW4rXyNJPf19WX//v1UrVq1wB0QQggh8mPOnDkvXJqV+9tsAEdHRwwNDQkJCVFbHhISovVSrFKlSuUpXlsbKSkpREdHq40mz2s7uiK1WwghhChapHYLIYTQt9f9uPvMmTPcv3//hSu4e/fuTevWrTl37twrt5WvkeTNmjXDz88vP08VQgjxH6RUKnT+Y2pqirW1tdqPpmJtYmJC48aNOX36tGpZRkYGp0+fpnnz5hr727x5c7V4gFOnTmmN16Rx48YYGxurtXPv3j2CgoLy1I6uSO0WQgiRF4VRu0XeSO0WQgiRF//F4+7Zs2fj5eWFp6en6gdg7dq17Nix45XbgXyOJJ84cSLTpk0jODiYunXrYmxsrPZ4vXr18tOsEEKIYirjn0MK1dSpUxk6dChNmjShadOmrFu3jvj4eIYPHw7AkCFDKFu2rOqysU8//ZS2bduyevVqunbtyu7du3F1dWXr1q2qNiMjIwkKCuLJkydA5glwyPw2vFSpUtjY2DBy5EimTp2Kvb091tbWTJw4kebNm+vlpp1Su4UQQuSFvmu3kNothBAib/Rdu/Vx3P38J7fy5ctTqVKlPPU/XyfJe/fuDcCIESNUyxQKBUqlUm4gIoQQ4rXTr18/wsLCWLhwIcHBwTRo0IATJ06obhISFBSEgUH2xVUtWrRg165dzJ8/n7lz51KtWjUOHz5MnTp1VDFHjhxRFXuA/v37A7Bo0SIWL14MZH57bWBgQO/evUlOTsbFxYVvvvnmX8j4RVK7hRBCiKJFarcQQoiiRF/H3bqiUOa+TfYrCAwMfOnjFSpUyHeHdMGzQg+9rr+wfabvDvwLZqbm6/ubImO2Qay+u1CoNhiZ67sLhepN1/X67kKhMnasrPM2L5Tqo/M22wTv03mbxdnrXrujB72n1/UXtj3ny+i7C4UuvZjPpFBC30NzCtmT4v3Ri2luxfsTtNTu4ul1r90TKvbT6/oL2+Ynl/TdhUJXzbasvrtQqDpb6H7f+DpJIc+n84qUeNL03YVCtSPggM7blNpdMPn6OKzvYiyEEEKIvJHaLYQQQhQtUruFEEKIf88rnyQ/cuQInTt3xtjYmCNHjrw0tkeP4j2SWwghRN5kFO9BDq8tqd1CCCHyS2q3fkjtFkIIkV9SuwvmlU+S9+rVi+DgYEqWLEmvXr20xsncaEIIIXLLoJjPw/CaktothBAiv6R264fUbiGEEPkltbtgXvkkeUZGhsb/CyGEEOL1JLVbCCGEKFqkdgshhBD6YfDPIepSU1Np164dvr6+hdEfIYQQxZAShc5/xKuT2i2EECKvpHbrl9RuIYQQeSW1u2DyfONOY2NjvLy8CqMvQgghiikZB6VfUruFEELkldRu/ZLaLYQQIq+kdhdMnkeSAwwePJjvv/9e130RQgghRCGR2i2EEEIULVK7hRBCiH9PnkeSA6SlpbF9+3b+97//0bhxYywtLdUeX7NmjU46J4QQonj4r12m9TqS2i2EECIvpHbrn9RuIYQQeSG1u2DydZL81q1bNGrUCAAfHx+1xxQK2SBCCCHE60ZqtxBCCFG0SO0WQggh/j35Okl+9uxZXfdDCCFEMSZzo+mf1G4hhBB5IbVb/6R2CyGEyAup3QWTr5PkQgghRF5IsRZCCCGKFqndQgghRNEitbtg8nWS/N13333p5V1nzpzJd4eEEEIIoXtSu4UQQoiiRWq3EEII8e/J10nyBg0aqP2empqKp6cnt27dYujQobrolxBCiGJEbiCif1K7hRBC5IXUbv2T2i2EECIvpHYXTL5Okq9du1bj8sWLF/Ps2bMCdUgIIUTxkyG1Wu+kdgshhMgLqd36J7VbCCFEXkjtLhgDXTY2ePBgtm/frssmhRBCCFGIpHYLIYQQRYvUbiGEEEL3dHrjzitXrmBmZqbLJoUQQhQDGXLZ12tLarcQQghNpHa/vqR2CyGE0ERqd8Hk6yT5Bx98oPa7Uqnk6dOnuLq6smDBAp10TAghhBC6I7VbCCGEKFqkdgshhBD/nnydJLexsVH73cDAgBo1avDZZ5/RsWNHnXRMCCFE8aHUdweE1G4hhBB5IrVb/6R2CyGEyAup3QWTr5PkO3bs0HU/9MZxSBdKjnkfIyc7Eu/483jRVhJu+GqNt+nSktLTBmFSriTJAU94svJH4s66ZT/eqTkOgzphUbcKRnbW3Ov8KYne/mptKEyNKTN/BHbdW6MwMSbuggeP5m8mLTy6UHLsNKQLvca8j62THQF3/Nm2aCt+L8mxeZeWDJg2iJLlSvI04Ak/rfwR9xw5AvSfOpAOAzpiYW3JXdc7bJ33LU8DnqoeL12pDEPnDqdmkzcxMjYi8G4Av67+hVtXbuo8P+dhnSgzvhfGTrYkeAfgP38b8Z5+WuPtuzXnjZkDMC1XkiT/pwR9/hPRZ9xVj9t1bobzEBcs61bB2N4Krw5TSbgdoNaGwtSYCouG4dCjFQamRkSf8yRgzlZSw2N0nl+voT3oP64v9k72+N25z4YFX3PX857W+LZd2zByxjBKlSvFo4DHbFn+HVfPXFOLGT59KN0GdKGETQluXb/Nmrnreez/WPV4uUplGTd/LHXfqo2RsREP7vjz/Vc78Pzrhs7zc/ioC05jP8DIyY6kO/48XrSFxH94DzpPG5z5HvR/QvDKH4g7l/36tHZpjsOgzphnvQd9ukwiScN7sPS8kdhmvQefXfDg8YJvC+U9+OuBo+zYtZ/wyChqVK3M3CnjqVurhtb4k2cu8vV3O3kcHEKFcmWZMn44bVo0VT1+6txl9h4+jvc9P2Ji49i/42tqVq+i1saSLzZw5boHYeGRWFiY0aBOLaZ8PILKFd7QeX6vKkNvaxbPFafabdKhJ2Zd+6GwsSc96D6JP24k/cFdrfHGTdti1mc4Bo6lyAh5ROKv35F242r2401aY9K+O4YVq2FgZUPc3NGkB95XPa6wtMKs9zCM6jbBwLEkythoUt0uk7hvByTGF0qOtYe2p/64rpg72RBxJ4jLC3YS5vlAa3zlrk1pMuNDrMo5EhMQwtXlu3l4JnufXalzE94c3A6nehUxs7Nif8e5RHgHqbVhaGpM8wUDqdLzbQxNjHl43otLc38gMTxW5/nVGdqeBmO7YpGV38WFOwl9SX5Vujal6fTs/K4s303Q2ez8KndqQu2P2uFUNzO/PS6a82uxYCDVemTmF3TeiwvzCie/GkPbU3t85vaL9A7i2oKdRLwkvwrdmtJgxoeUKOdIrH8I7st38zjH9ivfuQnVP2qHQ72KmNpZcbTjXKJuq+dnYGpMk4UDqdTzbQxMjHlyzourc38gqRDyazSkPc3GdMXSyYbQO0GcWrSTpze051ejS1PaTPsQm3KORAaEcG7lbh7k2H7VOzWh4aB2lKpbEXM7K7Z3nkuohu333vyB1Oqeuf38L3hxcv4PJBRCflK7M0nt1r/iVLvbfNSRdmO7Y+1ky+M7gexbtIPAG/e1xjfs8jZdp/XFoZwTYf7BHF75C97nPFWP13dpSqtB7SlftzKWdlas6DKTx96Bam20HNCOJj1bUq52JcytLJhRbziJsQmFlSLjxw1l2tTxlCrlhJeXN59OXsB1V0+t8b17d2PJ4hlUrFAOXz9/5s5dzh8nzqjFLF40nZEjBmJra81ff7nyycQ5+PllH9tUq1aZVSvn06L5W5iYGHPz5h0WLf6Sc+f/0nl+A0d8yIiPB+NY0oG7t335fO5X3PTw1hrv0r0dk2aPpewbpQl88JDVS7/mwmn1fk2cNYY+g3thZV0Cj+teLJmxikD/h6rHa9WtwbSFE6jToBYZ6Rn8eewMqxatIyE+Uef5tfyoI++O7Y6Vkw1P7gRxaNEOgl7yGq3fpRmdpvXFvpwT4f7BHFu5izs5XqN1Xd6ixaAOlKtbCUs7K77qMosnOV6jFjaWuEzpQ43W9bAr68iziFhu/XmdP9bsJSlO9/kV9/fgex91ovPYntg42RJ0J4BfFn2P/w3t54WadGnOB9MG4FjOiRD/p+xb+TNe57LPCzV2acY7gzpSsW4VSthZsbDLNB56B6i10XZAB97u2YoKtStjbmXBx/U+KtR9zKuQ2l0wBbpxZ0pKCo8ePSIoKEjtp6iw7daKMvNHErx+N/e6TSHxTgCVf1qCkYONxniLxjWpuHE6EXtPca/rZGL+vEqlrXMxq15eFWNgbkr8dW+erPxR63rLLhiFTbumBHz8BX5952LsbE/FLXN0nh9Ay26tGD5/JHvX72Z6tykE3Alg4U9LsNGSY43GNZm6cTqn955iWtfJXPvzKrO2zqV8jhzfH/cBXYd1Y/Pcb5ndcwbJCcks+GkJxqbGqph52xdgaGTAogHzmdFtCgF3/Jm7fQG2TrY6zc+hR0sqLBrOozV7uekynXjvAN7ctVDrNizRpAbVvplK6K+n8eo4jcgT16i+fRbmNbLzM7QwI+7aHYKW/6R1vRUXD8euQxN8x36J9wcLMHG2p/r3s3SaG8C73d/h44Xj+GHtT4zuPI773g/48ueV2DrYaoyv3bgWCzfN4/juE4zqNI5LJy6zbNsSKtWoqIoZ8HE/eg9/nzVz1jO++wQSE5L48ueVmOTYfit+/BxDI0Om9JvOmC4f4+d9nxU/LMPeyU6n+dl0a0Xp+aMIWf8rvl0nk+jtT6Wdn2Go7T3YqCblN8wgas+f+Hb5lNg//6bC1nmY5nwPWpgR7+pN8Eveg2UWjMK6XVMCP17Fg35zMHK2p8Jm3b8H//jfeb7YuJXxIwaxb/tGalStxNip84mIitYY73HTm5mLV/J+Nxf27fia91o3Z9Kcpfg+CFDFp0WqMQABAABJREFUJCYl0ahebaaMH6F1vbVqVGXZvKkc2bWVLWs+R6lUMmbKPNLT03WcoSiKinrtNn77HcwHjSfp4E7i5o8lPeg+lrNXobC21RhvWK02FhPmk3LuD+LmjSHV9TKWUz/DoFzF7CAzM9Lu3SRp93ca21DYOaCwcyBx12biZo0kYcsXGNV7C4sx03WfIFClezOaLxyE29pDHOg8n0jvILr+PAszB2uN8c6Nq9Fu0yfc232eA53mE3DCDZdtU7CrUU4VY2RhSvD1e1xdvkfrepsvGkT5Dg05NXYjRz5chqWzHR2/m6zr9KjavRktFwzCdd0h9nWZT7h3EN1+moW5lvxKNa5Gh68/4c7u8+zrPB//k2503jYF+1z5Pb12jysvya/lokFUbN+Qk+M2crhPZn6dtk7WdXpU7NGMJosGcWPNIY51mk+UdxDtf9G+/ZyaVKP1pk/w+/U8x1zm8/CkG+98PwXbXPmFXruH2+fa83tr8SDe6NCQ82M3crL3MixK2fHOtsm6To+a3Zrx3vxBXFp/iB3d5hN6J4h+P83CQkt+ZRtXo+fGT7ix9zw7us7H9083em+dgmP17PyMzU15dP0eZ1dqz6/dgkFUbdeQwx9v5Je+yyjhbMcHWybrOj2p3eK1VNRrd6NuzXl//hD+WH+AVV1n89g7kE92zqWElv1GpUbVGbZhElf2nGVll9nc+PM6Y7bOoHT17C+NTCxMue96j8Mrd2ldr7G5Kd7nb/DnN4d1ndIL+vTpwVdfLmLpsjW81awTN7y8+f34Lzg5OWiMb/52E375aRM7dvxKk6YuHDlykgP7v6d27ewv5GZM/5gJn4zg4wmzadGqO/EJCfx+7BdMTU1VMb8d/hEjQyM6uPSl6dudueHlzW+Hf8TZ2Umn+XXu2Z5ZSyaz6att9G4/hHu3ffluzwbsHTUfHzZ4qy5fbVnKgV1H+KDdR5z+4zwbf/ySajUrq2JGTRzC4FH9WDxjJf06jyAhPpHv9m7AxNQEACdnR77f/zVB/o/o12k4o/tPomrNyizfsFCnuQE06NacnvM/4uT6/azpOocn3oGM2TlH62u0YqPqDN4wiWt7zrK6y2xu/unK8K3TKZWjtplYmOHvepdjWl6j1s522DjbcWT5z3zRcQa/Tv+WGm0b0G/VOJ3nV9zfg027taD//GH8tn4vi7vO4KF3INN2LsBKS35VG9Vg3IYpXNhzmkVdpuP+5zUmbp1JWbX8zPB1vcu+ldrPC5mYm3DzvCfHvjmo85yEfuTrJLmPjw+tW7fG3NycChUqUKlSJSpVqkTFihWpVKmSrvtYaJxG9SRi959E7jtNsu9DHs39hozEZOz7ttccP7w7sefdCdtyiGS/RwSv/oXEWw9wHNpVFRN16BwhG/bw7JLmEbcGVhbY92vP42Xf8+wvLxJv3Sdo+npKNHkTi4baR6jkV/dRPTm1+0/O7DvNI9+HbJn7DcmJybynJcduw7vjcd6d37Yc4rHfI35d/Qv+tx7QOUeO3Ub2YP/Xe7l+6iqBdwPYMHUt9iXtadrxbQCs7KwoU7ksB785QODdAJ4GPOWnlTsxszCjfPUKOs2v9JjuhO46RdieMyT6PsJ/1hYyEpMpOeA9zfGjuhF91oOn3/5Gkt9jHn35K/E3/Sk1vLMqJvzAeR6v3UfsBc3b0NDKAqcB7Qhc/AOxl28Rf/MB96d+jdVbNSnRqLpO8+szpjfHf/2dE3tPEugbxJrZ60hKSqZL/04a43uP/IBr566zZ/NegvyC2P7VD/je8uP9YT1VMR+O/ICfNvzC5T//4sEdf1ZMXoWjswOtXFoCYGNnzRuVy7Fr0688uOPPY//HbF2xDXMLcyrV0O3722lULyJ3nyRq32mS/R7yeN43KBOTse/bQWO844gexJ13J2zrIZLvPyJkzS8k3r6P49BuqpjoQ2cJ3bCbuMueGtswsLLArm8Hni7bRvyVzPfgoxnrsWxSS+fvwZ17DvFh986837UjVSpVYOGMiZiZmnLo2J8a43/e+xstmzVhxKAPqVKxPBPHDKFW9Srs2n9UFdOjUzvGjxhE87caal1vn55daNKgLmVLO1OrRlUmjhlKcEgYj5+G6DS/vMhQKHT+I/KmuNRu0859SDn7OykXTpDxOJDE7WshORmTtp01x3f6gDSvayQf30PGkyCS9u8gPcAX0469VDGpl06RfOgn0m65aWwj41EACesXk+ZxhYzQJ6R5e5C0dzvGDZuDQYHGG2hUd0xn7vx6lnt7LxDt+4QLs3eQlpRMzf5tNcePdOHhOS9ubD5OtN8TXL/aT/itAOoMy96X+h64jPu6wzy6eEtjGyZW5tTs/w5XPvuFJ395E34zgHNTt1LqreqUbFRF43Pyq/7oznj/epa7ey8Q5fuE83Oy8uunOb96I10IOueF55bjRPk94dpX+wm7FUDdodn5+Ry8jOv6wzy6pD2/N/u9w+XPfuHxX96E3QzgzLStlH6rOs4NdZvfm6M747vrLPf3XiDG9wl/z95BemIyVbVsvzdHuvDknBe3Nx8nxu8Jnl/uJ/JWADWGZ+f34MBlvNYd5qmW7WdsZU7V/u9wfckvBF/2JvJmAJenbKXkW9Vx1PH2azqqMzd2n+XmvgtE+D7hxNwdpCYmU6+v5vyaDHfhwXkvrm05ToTfEy6u3k/wrQAa59h+tw9d5vKGwwRq2X6mVubU7/cOZ5b9QuBf3oTcCuD49K2Ua1KdMjreflK7s0nt1r/iUrvfG9WVv3af5u995wj2e8zuedtISUyhed93Nca/M6Izd857cnrrUULuP+b4mr08vO1P26Euqpjrhy5yYsMB7l3WfqXyue2/c+rb3wjw0H6Vqq5M+XQ0277fxY8793Lnji8ffzKbhIREhg/rrzF+4sSRnDx5jtVrNnP3rh+LFn+Jh8ctPh4/XBUzaeIolq9Yz9Gjf3Lz5h2GDf+UMmWc6dkz8+/g4GBH9WqV+eLLr7l58w5+fv7MnbccS0sL6tSuqdP8ho4byL6fD3No9zHu+/izeMZKkhKT+GBAd43xQ0b359KZv9m+6Wce+AawYdUW7njdZeDIvtkxY/qzee12zpy4gI+3H7MnLKaksyPtO2fWk3c6tiItLY3PZn1BwP0gbnneYfGMlbh0b0f5SuU0rje/2o7qyt+7z3B933lC/B6zf942UhNTaNr3HY3xrUd05u75G5zdeozQ+084sWYvj2/70yrHa9Tt0EX+3HAQn8uaa1uwzyN+GL8W79PuRASF4HflNn98tZva7RphYKjbz5fF/T3YcVR3Luz+H5f2neWJ3yN2zttCSmIyrfu20xjfYURXbp734MTW33h6/zGH1uwm8LY/7YZmH09cOXSeIxv2cfuyl9b1ntp+nN+/PcR9Dx+d55RfUrsLJl/vvOHDh2NgYMCxY8dwc3PD3d0dd3d3PDw8cHd3/+cGXgMKYyMs6lbl2SXP7IVKJc8u3cCykeaCYtmo5gsnv+MuuGuN18SiblUMTIzV2km+/5iUR6FYNtLtCTojYyOq1K2KV44clUolXpduUENLn6s3qolXrhw9Lrir4p3fcMaupD03csQkxCXg6+lDjaz+x0XF8cjvEe/0fhdTc1MMDA1wGeRCdFg0929qv9wlrxTGRljWq0LMxRw7LaWSmItelGis+W9ZonF19Xgg5ryH1nhNLOtVxsDEmJiL2X+DJL/HJD8Ko0Rj3Z0kNzI2okbd6rhdzH5PKZVK3C66U6tRLY3Pqd24llo8wLXz16nVODO+dPnSODg7qMXEx8Xj7XlHFRMTFUuQXxAuH3bEzNwMQ0MDegzuRmRYFPdu6m7nrzA2wrxOVZ5dzvF6UyqJu+yJhZb3gkXDmjzLdfL72QUPLPLwHjSvk/kejLuc8z34iJRHoXlq55+kpqbifc+Xt99qoFpmYGDA200acOPWHY3PuXH7Ds2bNFBb1qJZY27c1hz/KhISkzh8/E/KlSlFaR2PKMkLZSH8iLwpDrUbQyMMK1VXP5mtVJJ2yw2japr3i0ZVa5F2Sz2/NK/rGFWtXaCuKCwsUSYmQIZuL2o0MDbEqW4lHl+8nb1QqeTRxds4N6qq8TklG1flca6Tp4/Oe+HcWHO8Jo51K2FoYqS23uj7T4l7FI5zo2p5S+Ilnuf36NKL+ZXS0l/nRlVfOPn9MI/5OWXll3O9qvwa6zY/h3qVeJpr+z29dBsnLf11alz1hZPfT855aY3XxKFeZn451xt7/ynPHoXjpOP8StWtRECu7Rdw6TZltbw+yzSqSkCu7ed/wUtrvCalsrZfzvVG3n9KzKNwyurw9Sm1W53Ubv0rDrXb0NiQN+pUVjuRplQquXf5JpW0vH8rNazO3VwnFu9cuEFFHQ9I0hVjY2MaNarH6TMXVcuUSiWnz1zi7bcba3zO280aq8UD/HnqnCq+UqXylC7tzOkzl1SPx8bGce2aB283y4yJiIji7j0/Bg/+EAsLcwwNDRkzejAhIWG4uWs/sZf3/IyoXb8mVy5cV8vvyoXrNGhSV+Nz6jepy5UL6lN+Xjr3tyq+XIUyODk7qsU8i4vHy/029bNiTExMSE1JQ6nM3nskJyUD0Khpfd0kR+ZrtFydSvjkeo36XL6p9TVXsWE1fHOdHL6rg9eomZUFSc8SyUjX3efL4v4eNDQ2omKdKmons5VKJd6Xvaiqpb9VGlbHO9fJ71sXPKmi43Ny+iC1u2DyNSe5p6cnbm5u1KxZsBNKEydOpG/fvrRu3bpA7eSHoZ01CiNDUnPNQZwaHo1plbIan2PkZKsx3igPU1AYOdmSkZxKeqz6HKZ5bedVWNlZY2hkSHSuPkeHR1NWS462TrYvxMeER2Ob1TfbknaqZbnbtMvR/yWDFjDru7n84r0HZYaSmIholg5dTHys7uZuNbK3ytyGYep9SQ2Pxryq5vyMNW3DsBiMS9q+8nqNS9plbUP1uaZSw6IxKam7bWhjb4OhkSGRYVFqy6PCoyhfVfP8lPZOdkSG54oPi8beyV71OPDSGIBpA2aybNsSfr93BGWGkqjwKGYOnsOzmGcFzuu55+/BtFx9SQuLxqyK5pEBRk62L8wbnhYWjZGj7Suv19gpc/tl5HotpoVHY6TD6YCiomNJT8/AwV79NeFgb4d/0CONzwmPiHoh3tHejvCIKI3xL7P74DFWf/M9iYlJVCpfjq1rP8fY2PifnyiKreJQuxVWNigMDcmIUX9PZMRGYVSmvObn2Nq/GB8ThcI2//trRQlrzN7/iJQzx/LdhjZm9lYYGBmSGKZ+j4vE8Bhsq5bW+BwLJ9sX5mVOCIvFPA/7NIuSNqQnp5KSq7YlhsdgUVLzFFj58Ty/BA352eUlv/BYLHSQX0J4DBZOusvP9Pn2y3WPksSwGKyraM7PzMmWxDD1/JLC87b9zJ0y80vNlV9SWAzmOszPwi4zv/hc+cWHx+CgJb8STrbE59p+8eGxWOYhP0snG9KSU0nOlV98eAyWOsxPard43RSH2l0i65g0Ltd+IzYsBucqZTQ+x9rJlrhcn/njwmKwdtTd+12XHB3tMTIyIvT/7N13WBRXF8DhH9I7SLW32Hsv0RiNvUS/GI0m9t5b7L0ktthbsJdYY4kxGlvsXQFRFAVREBXpVXrZ7w9wZWFRgSWIOW8eHsPs2bv3MrNzZu7cueMfpLI8ICCQCuXV3+1ib2+Df0CgyjJ//yDsUy+M2dvZpi5LFxMQhL29rfL31m26c+jgFsJCPEhOTiYgIIj2HX8gLExzz8qyKGiBjo4OwYEhKsuDA0Mo9Zn6O8Wtba0IUhNvbVtQ+TpAcIBqTFBgCDapr9284sjkeWPpP6Inv23ch6GRIeNnjABSpmLRFONMttHIwHBsM+k3MbWxUBtvmoNt1NjSlJajvuH63rPZLkOdT/07aGppiraONhHp+7ECw7HPZP2Z21gQke7vER4YhnkW+hXEpylbI8krVapEUFDQ+wPfY926dXz55ZeUK1eOxYsX4+fnl+Uy4uLiiIiIUPmJV8jcfXlt0PyhhAeHM6PrVCZ3+pFbp28ybcsMLDXYiSxyz5ifRhMaHMbob8YxtMMIrpy6xsLt8yloW/D9bxYfhfatmnFw21q2r1tCiWJFmDBrIXFx8XlWn+Rc+BFZ87Hn7jgNjpjJVYZGGE9cSNJLb2IPZ/7sAyGEyCrJ3SK9jz13J8l5d55bs/pnAgOC+LLZ/2jYqD1/Hj3FkcM7VDrS8ytP96dMHTWXvsN+wPnZJS7fP8ELH18CA4JVRpd/CvRNDBm4bTL+ni85tfJgXldH5GOSu3MmW53kixcvZtKkSVy4cIHg4OAMyTIrTp8+Tbt27Vi6dCnFixenU6dOHDt2jOQPvH154cKFmJubq/xsDX//lB5JoREoEpPQTXelSNfagsR0I5PfSAwMyyT+w0eKJAaGUUBfF20z4xyV8yEiQyNISkzCIl2dLawtCMukjWGBYRniza0tCEutW1hAqHJZ+jJDU2Oqfl6N2l/VYfnIX3jk+JCn95+ycYYDcbHxfNlF/Vzh2ZEYEpmyDtONRNK1tiA+k/YlqFuHNuYkBKiPV1tGQGjqOjRKV44F8QGaW4fhIeEkJSZleFimpbUlIZl8TkhgaIaHp1jaWBCSehX/zaj0d8XU+rwmDVvUZ97wn7nv+IDH9z1ZOX01cbFxtOnaSiNtg7ffQZ10ddGxsSAhk++CulHj6kaXv0tCYMr6K5DuO6jzju9+dlhamKGtXYDgENW2BIeEYl1Q/cUiayvLDPFBIaFYW2X94pKpiTElihWhTo2qrPh5Ol7PnnP2kuafci/yj489d6948Oy971NEhqNISqKAuep3ooCZJYrwEPXvCQvJGG9uiSIsG/trA0NMJi1GERtN1IpZkAsP1IsNiSQ5MSnD6F9Da3NiAtSPCosODMPIWvXBREY2ZsRkYZ8WHRCOtr4ueulym6G1OdGZfG52vGlf+tHbhtbmGUaXK+umrn3WZkRroH1G7/jc7Ih7s/7SjbQytDEnNpPPiQ0Mw9BGtX0G1llbfzGBKe3TTdc+AxvzDHcl5ER0aEr7jNO1z9janKhMPud1YBjG6dafsbUZUVloX1RgODr6uuina9+7Pjc7JHeLj83Hnrudwt8/rdDr1HPS9CNszWzMichkPxARGIZpumN+UxvzDCM/PxZBQSEkJiZim250s62tDX7pRoK/4ecXiJ2t6nRKdnbWyng//4DUZelibK3x80t5rXmzxrRv14Lvew7n2nVH7rjcZ9ToacTExNK7V1eNtA0gLCSMxMRErGxUB0xZ2RQkKCBY7XuCAoKxVhsfonwdwCrdICxrm4IEpinz+OFTfFGlLV9W70DDCi1Z98smClpZ8Nz7ZY7b9UZUJtuoqY05kZlso5GBYerjs7GN6hsbMHjHVOJex7BtyDKSEzV7fPmpfwcjQyNJSkzCLH0/1jvaFx4YlmFUvLmNRYYZE8R/T7Y6yVu0aMGNGzf46quvsLW1xdLSEktLSywsLLC0zNoBYdWqVVm5ciW+vr7s2rWLuLg4OnfuTLFixZg+fTqenu/u8J46dSrh4eEqP/3N3z/HoSIhkWhXT0w+TzOXlZYWJp9XI8r5kdr3RDk/wuTzairLTJvUyDRenWhXT5LjE1TK0S9dBL2itkQ5u39wOR8iMSGRJ66eVEvTRi0tLap9Xg33TOrs4fyIqunaWL1JDWW8/3N/QgNCVMo0NDGkbI1yuKfWX98g5WnbimTVq7uK5GQKaPABZ4qERKLuPcG8cZr6amlh1rgar53U/y1fO3lg3kR13jTzL6pnGq9O1L2nJMcnqHyuQZnC6Be14bWT5ubsTkxIxN3Vg1qNaymXaWlpUbtxTdyc3dS+54GTG7Uaqz4Uqk6T2rg5pcS/8nlFsH+wSoyRiRGValRUxugbvll/qgfMyckKtDT40AZFQiIx9z0xaaS6/kwaVSc6k+9C9J1HmDRSnX/OpHENorPwHYy5n/odTFPOm+9gVsp5H11dXSqVL8tNRxflsuTkZG46uVC9SkW176leuSI3nFxUll2/fYfqldXHfyiFQoFCAfHxCTkqJyeStTT/I7LmY8/d4yp/wIOdkxJJ8vJAp/Lb/SJaWuhUqUXiY/X7xURPN9V4QKdKHRI9H6iNz5ShESZTlkBiAlHLZkBC7nyfkhOSCHT1okjjNHOma2lRpHFl/J3V/10DnDxV44EiTarg7/ThzwEJcvUiKT5RpRzz0oUwLWqNv7PmHrakbN/nqu0r2rgyfpnU19/Zk6Kfq7avWBbbF5javrTlWLxpn5Nm2xd8z4tC6daffePKBGZS30AnT+zTrb9CX1TJNF6d4Hsp7Uv7uWZlCmFS1JpADbfPz9WLkunWX4nPK/Myk+3T19lTNR4o2aRKpvHq+KWuv7TlFCxdCPOi1rzU4PYpuVuV5O6897Hn7trm79/OkxKSeH7/KeUbvT0H09LSolyjKnhl8v31uuNB+UZVVJZVaFwVb+eP5+F4aSUkJODsfI/mzRorl2lpadG8WWNu3FD/UPAbN51o3ryxyrIWX32hjPfy8uHVK3+VMk1NTahXryY3bqbEGBkZAmS40JGs0Ox5d0JCIg/uPqJBk7rKZVpaWjRoUgcXR/UPbbzr6KoSD9CoaX1l/ItnvgT6B6nEGJsYU61WZe6qKTM4MIToqBjadmpJXGw81y7e1ETTgJRt9MV9L8qm2ea0tLQo26hKptuc953HKvEA5RpXy/I2qm9iyJDfppGUkMiWgb+QGKf5ff6n/h1MSkjE+/4TKqVrX8VG1fDMpL5P7nhQqZFqv1flxtV4ouE+ubwguTtnsjUn+fnz5zVdD3R1denWrRvdunXDx8eHrVu3sn37dhYtWkTSO0Zq6evro6+vr7JMT0v7gz4zcPOfFF82luh7nkTf9cCm/9cUMDIg5EDKHFDFl48lwS+EV0t2psRv+4uy+xdgM6gzEeduY9nxCwyrfsbzKeuUZWqbm6BXxAYdu5QrovqlU+ZASggMJTEwjOTIaEL2/0ORGQNICntNUmQ0RecNJsrpIdF3NP+F/Gvzn4xaNhbPe548vutBx/5fo29kwLnUNo5ePpZgvxB2p7bx2La/mL9/AV8P6ozTuds07vgFZap+hkOaNh7bcpRvR3XjlZcv/s/96fHjD4QEhHDr9A0A3J0fERUexajlYzmwah9xsfG07NEK22J2OJ27nbGSOfBq41+UWTmK13c9eX3nMYUGdUTbSJ/AfecAKLNqNPF+wTxfuDslfvMxKh2aT6EhXxN61gnrTo0xrlaGpxMdlGVqW5igX8QavdR1aJg6j1VCQBgJgWEkRUYTuPcsJeb0IzF1HZb8eSCRjo94reGkcWDjIaaumIT7XXceurjz7cBvMDA04MT+kwBMXTmZIL8gNi3aAsChLYdZdXA53QZ/y42zN2neqRnlq5Vj2eQVyjIPbjlMr9E/8MLrJa+e+zFgQl+C/IO5cuoqAG5ObrwOf82UlZPZueI34mLj6PBDewoVs+fGWc0djAAEbj5CsWXjiHH1JNrFA+sBnShgZEDogX8AKLZsHAn+wfilbp9BW49SZv9CrAd2JvK8IxYdm2BY9TNeTF2rLFPb3ATdIjbo2qp+BxPTfAdDfz9D4RkDSAqPJDkymsJzh+TKd7D3d/9j+s/LqFyhLFUqlWfX70eIiY2jc/uWAEydvxRbayvGpT7Fvme3TvQbMYntew/xRaN6nPjnIg8ePWbO5NHKMsMjInnlF0BAUMoIizdzpFpbWWJtVZDnL19x8uwlGtWrRUELc/wCg9jy2+/o6+vRpFFd8koy/7Hs+hH62HN3svaHnczFnTiA0ZApJHq5k/TkEfptuoC+AfEXU/aLRkOnkBwaROz+zSnxJw9jMmMF+u26knDnBnoNm6NduhzRW5Ypy9QyNqWAtS1aFikjwAoUSnnuQ3JYCIrwUGUHuZaePlHrF6JlaASGKSNaFRHhoNDsjYiuG0/w5YohBN71IsDlCVUHtkHXUB/3/RcBaLZyCFF+odxa9HtK/JZTdDw4nWqD2+Jz1oUynRpiU600lyZvVZapb2GMSWErjOxTnzGSOn90dGA4MYHhxEfG8GjfBRrO+oG4sNfER8bw+fze+Dl6EOD8RKPtu7vpBM2XDyHwXkr7qg1og46hPo9+T2nfVytS2ndjcUr77m05RacD06k+uC3PzrpQ9uuU9l2YkrF9xnYp7bNU076H+y/w+awfiA17TcLrGJrMS2mf/x3Ntu/hphN8vmIIQfe8CL7zhIqDUtrnmbr+Pl81hOhXodxJXX8Pt5yi9cHpVBrSlhf/uFCqU0OsqpXmxqS37dOzMMa4iBVGqe0zT21fTEA4sYHhJETG4LnvAnVmp6y/hMgY6v3UmwBHD4I0vP5ubT5Bh2VDeHXPi1d3n1Cnfxv0jPS5dyClfR2WDyHSL5SLS1La57jtFN/vn069QW3xPOdCpY4NKVS1NCfTrD8Dc2PMilhhktq+gqVT2hcVGE5UYDhxkTHc3X+B5jN+ICbsNXGRMbSc15sXTh74anj9Se5+S3J33vvYc7f2B553n9t8nF7LhuPj+gRvlyc0G9AOfSN9bhy4AECvZSMI9w/h6JK9AFzYeoKx+2fTfGAHHpx3pnbHRhSvWoa9UzcpyzQyN8ayiDXmqdN52pVOmVs5IjCMyNQ7TExtzDGzscC6hD0AhcsXJzYqhtCXQUSHa+5ZWQArVm1i25YVODnf4/btO4weNQhjY0O279gPwLatq/D1fcX0GYsAWLNmC+fOHmTc2CH8feIfvuvWidq1qzF0+CRlmavXbGba1NE89nyKt/dz5s6ZiK+vP3/+eQqA6zccCQ0NZ9vWlfz080piYmIZ2P97SpUsxt8nNDuv9Q6HPSxcM5v7dx/i6vyA3kO6Y2hkyB/7Up7PsmjtHPxfBbDi5/UA7Ny0j51HNtB32PdcPHOVdv9rReXqFZn94wJlmTs37mPouP48e/qcFz6+jJ4ylAD/IP45cVEZ833/rrjcvkd0VAyNvqzHhFmjWf7TWiIjNPesLICLm4/TY9kwnrs+xcfFk6YD2qFnpM+t1NzWY9lwIvxDOL5kHwCXt55gxP5ZNB3Ynofn71CzYyOKVS3NgakblWUamRtjkWYbtU3dRiNTt1F9E0OG/jYNXQM9do9dh4GpIQamKRc+XgdHZBh0mBOf+nfw9Oa/GLhsFN6uT3jq8phWAzqgb6TPlQMp/UIDl40izD+Eg0tS+oXObD3O5P3zaD2wI3fPO1O/4+eUrFqG7VPf9gsZm5tQsIg1lqn9CoVS2xceGKYcoW5mY4G5jQV2qe0rWr4EsVExhLwMIkqDz3PLCsndOZOtTvKmTZtquh4qihcvzpw5c5g9ezb//PNPrn1O2LEr6FiZU2j89+jYWBLj9pSnvecop27QK2wDaXZM0U6P8B69jEITfqDQxF7EefviNXgBsR4+yhjzlvUovmys8veS61KSnN+KvfitTNnhvJy/GYUimZIOU9DS0yXy0h1ezPg1V9p49dgVzKzM6TH+eyxsLPFye8r83nOUt5FYF7YhOU0b3Z0esWL0Mr6f8AM/TOzFK29fFg9egE+aNv7hcBh9IwOGLhyBsZkxDx3dmN97DgmpVz0jQyOZ33sO30/sydy9P6Gto8Pzxz4sGvQz3g+9Ndq+4KNX0bEyo9jEHujaWBD9wItHP8wnIfU2IP0i1pDmyvprR3c8R6yg2OTvKTblB2K9XuHRfzEx7m/bV7BVXcqsHKX8vazDjwC8WLafF8tSDnK852yjhEJBuU0T0dLXJfyCC15pEqKmnP/rAhZW5vSb0JeCNpZ4uj1hUq+phKauP7sitiojvh84uTF/5AIGTOrHwMn9een1khkDZ+Pl7q2M2bt+PwZGBkxYPA4TMxNcb99nUs8pxKeuv/DQCCb1nMqASf1Z/vtSdHS08fZ4xvQBs3jy8KlG2xd+7Ao6Bc2xG/cDOjaWxD58ilef2crvoG4RG5X55qKdH+EzZin2P/bEfmJv4r19eTb4Z+LSbJ9mLetTbOlY5e8l1k4GwH/lHvxTv4O+8zdTKFlBiV+nUkBPl8hLzrycqfnvYNsWTQkNC2ft5l0EhYRQoWwZHJbNV96y/co/gAJpRufXrFqJxXMms2bjDlZt2E6JokVYvXAmZUuXVMacv3yDGQuWK3+fODvlQHtY/x8YMaAn+np6ON+9z2+/HyEi8jVWBS2oU70KuxyWY2VpofE2ivzjU8ndCTcuEGNqgeG3/dAytyTp2ROiFk9GEZEy3UEBK1uVTuukxw+IXvczBl37Y9BtAMl+L4laPovkF97KGN3ajTAaMln5u/GoWQDEHtpB7OEd6JQsi85nlQAwW7FLpT4RY3qQHOSv0TY++esmBlZm1JnQBSMbc4LcnvF3ryXEpD780KSItcqJk7/TY86NXE/dSV2pN7kb4V5+nBq4glD3tw8aLNGyFs1WDFH+3uLXlDznuPwwTssPA3B97m5IVtBy4xi09XR4cdGVy9O2a7RtAJ5/3cSgoBn1fnzbvmPp25dm3+/n9Jh/Rq2n3sSuNJjUjTBvP04MXEFImvaVbFmLr5a/bV+r9Sntu738MLdXpLTv6tzdKJIVtElt3/OLrlycrvn2eR+9iX5BM2pM6IKhjTkhD55xtucSYlPbZ1xYdf0FOj7m8sj11JjUlZqTuxHh5ceFASsIS9O+Yq1q8Xma9fdF6vq7u+wwd1PX3+05Ke37cuMYCujr4HvBlZu5sP4eHbuJkZUZTcZ3wdjGnAC3Z+zvvUT5cFWzdO176fSYo6PX88WErnwxsRuh3n4cGryCII+37Svbshbtl71tX+d1Ke27suIwV1amtO/s/N0oFAr+55Cy/rwuuXJ6hubbJ7lbfEw+ldztfOw6JgXNaD+uG6Y2Frx86M26PguVU1MULGKFIk3u9nL2YPuYNXT48Ts6TuxOoLcfGwf/wiuP58qYqi3r0GvpcOXv/deOBeDvlQf4O3VO5yY/tKTd2LfTjow7MBeA3yas5+bBtx2xmnDgwFFsrAsyZ9YE7O1tuHv3Ae079CQgIGVO+eLFCquM+L5+w5GevUcyb+4kfpo/mceeXnT5dgAPHrwdtPPL0vUYGxvhsH4JFhZmXL16m/YdexIXFwdAcHAo7Tv8wPx5kzlz6nd0dXVwc/Pgmy79uXdP/R122XXiz3+wtLJk9KTBWNta8fC+B4O7j1E+zLNQETuV9rncdmXi0JmMmTqUcdOG8+zpc0b1mcjjR2/PJzev2YmhkQFzl03DzMwE51t3GfzdGOLTPIuhWq3KjJo0GCNjQ556PmPOxIUcPXBCo20DcEndRtuM64qZjQUvHz5jY59FvE7dRi3THZt4O3uwa8wa2v74He1Tt9Ftg5filya3VW5Zhx5Lhyl/7712DACnVh7k1MqDFK1SihI1ywIw/dIqlfrMbzyK0Bfqp+rJjk/9O3jr2DVMC5rTeVx3zG0s8HnoxfI+Pymnh7FKt/48nd3ZMGYl3/zYgy4Tf8Df+xVrBi/hZZr21WhZl4FLRyp/H7Y2pV/oyMr9/LkyZSBAsx9a0Xnsd8qYaQd+AmDzhLVcPaj5i5wi92kpsvnEg8uXL7NhwwaePn3KgQMHKFKkCL/99hulSpWicePG7y8AKFWqFI6OjlhZWWWnCplyKfG1Rsv72MzL6wr8CyYlZOv6Tb4xpUDW5hDMb1brGOZ1FXJVRcdV7w/Kx3StS2u8zF2Fe2q8zJ6+u94fJFR8zLk77AfNPbPiY7T/YuG8rkKuS/rEB66YfOJPLvL9tA+9+NHp0z6Cltz96fqYc/fIkt+9Pygfc/C9ktdVyHVlLYrkdRVyVVsjze8bPybxfFoPME0visS8rkKu2uZ9SONlSu7OmWxNVHXo0CFat26NoaEhzs7OyiuZ4eHhLFiw4D3vfsvLy0vjiVoIIYQQGUnuFkIIIfIXyd1CCCHEvydbneQ//fQTDg4ObNq0CV1dXeXyzz//HGdnZ41VTgghxKdBHiCS9yR3CyGEyArJ3XlPcrcQQoiskNydM9m6sdLd3Z0vvvgiw3Jzc3PCwsJyWichhBCfmE98loJ8QXK3EEKIrJDcnfckdwshhMgKyd05k62R5Pb29nh6emZYfuXKFUqX/rTnfBJCCCHyI8ndQgghRP4iuVsIIYT492Spk3znzp3ExcUxaNAgxowZw82bN9HS0sLX15fdu3czYcIEhg0b9v6ChBBC/KcocuFHfBjJ3UIIIbJDcnfekdwthBAiOyR350yWplvp168fbdq0YcqUKSQnJ/PVV18RHR3NF198gb6+PhMmTGDUqFG5VVchhBD51H9tLrOPieRuIYQQ2SG5O+9I7hZCCJEdkrtzJkud5ApFyjUELS0tpk+fzsSJE/H09OT169dUqlQJExOTXKmkEEIIIbJHcrcQQgiRv0juFkIIIf59WX5wp5bW28sSenp6VKpUSaMVEkII8emRB4jkLcndQgghskpyd96S3C2EECKrJHfnTJY7yb/66it0dN79Nmdn52xXSAghhBCaJblbCCGEyF8kdwshhBD/rix3krdu3Vpu7xJCCJElckU7b0nuFkIIkVWSu/OW5G4hhBBZJbk7Z7LcST5x4kRsbW1zoy5CCCE+UQp5gEiektwthBAiqyR35y3J3UIIIbJKcnfOFMhKcNp50YQQQgjx8ZPcLYQQQuQvkruFEEKIf1+WRpK/ecq2EEIIkRVy21fekdwthBAiOyR35x3J3UIIIbJDcnfOZGkkuZeXFzY2NsTGxmYa8+rVqxxXSgghxKclORd+xIeR3C2EECI7JHfnHcndQgghskNyd85kqZO8RIkSaGlpUatWLVxcXDK8fujQIapVq6apugkhhBAihyR3CyGEEPmL5G4hhBDi35elTvI3vvzySxo0aMDixYsBiIqKom/fvvTq1Ytp06ZptIJCCCHyP0Uu/IiskdwthBAiKyR35z3J3UIIIbJCcnfOZGlO8jfWr19P+/btGThwIMeOHePVq1eYmJhw69YtqlSpouk6CiGEECKHJHcLIYQQ+YvkbiGEEOLfk61OcoC2bdvyzTff8Ouvv6Kjo8Nff/0liVoIIYRayVp5XQMBkruFEEJ8OMndHwfJ3UIIIT6U5O6cydZ0K0+ePKFhw4YcO3aMU6dOMWnSJL7++msmTZpEQkKCpusohBAin5MHiOQ9yd1CCCGyQnJ33pPcLYQQIiskd+dMtjrJa9SoQalSpbh79y4tW7bkp59+4vz58xw+fJh69eppuo5CCCGEyCHJ3UIIIUT+IrlbCCGE+Pdkq5N8/fr17Nu3DwsLC+WyRo0acefOHWrVqqWpugkhhPhEyBXtvCe5WwghRFZI7s57kruFEEJkheTunMlWJ3mvXr3ULjc1NWXLli05qpAQQohPjzxlO+9J7hZCCJEVH0PuXrduHSVLlsTAwID69etz69atd8YfOHCAChUqYGBgQNWqVfn7779VXj98+DCtWrXCysoKLS0tXFxcMpQRGxvLiBEjsLKywsTEhC5duuDv75+N2uec5G4hhBBZ8THk7vws2w/uBHBzc8PHx4f4+HjlMi0tLTp27JjjigkhhBBC8yR3CyGEyA/279/P+PHjcXBwoH79+qxcuZLWrVvj7u6Ora1thvhr167Ro0cPFi5cSIcOHdizZw+dO3fG2dlZ+aDLqKgoGjduTLdu3Rg0aJDazx03bhzHjx/nwIEDmJubM3LkSL755huuXr2aq+19F8ndQgghRO7LVif506dP+d///oerqytaWlooFCnXFrS0Uh6jmpSUpLkaCiGEyPfkKdt5T3K3EEKIrMjr3L18+XIGDRpEv379AHBwcOD48eNs3bqVKVOmZIhftWoVbdq0YeLEiQDMnz+fM2fOsHbtWhwcHIC3I7O9vb3VfmZ4eDhbtmxhz549NG/eHIBt27ZRsWJFbty4QYMGDTTdzHeS3C2EECIr8jp353fZmm5lzJgxlCpVioCAAIyMjHjw4AGXLl2iTp06XLhwQcNVFEIIIUROSe4WQgiRX8THx+Pk5ESLFi2UywoUKECLFi24fv262vdcv35dJR6gdevWmcar4+TkREJCgko5FSpUoHjx4lkqR1MkdwshhBD/nmyNJL9+/Trnzp3D2tqaAgUKUKBAARo3bszChQsZPXo0d+7c0XQ9hRBC5GP/tQd+fIwkdwshhMiK3MjdcXFxxMXFqSzT19dHX19fZVlQUBBJSUnY2dmpLLezs+PRo0dqy/bz81Mb7+fn98H18/PzQ09PT+VBmdkpR1MkdwshhMgKOe/OmWyNJE9KSsLU1BQAa2trfH19AShRogTu7u6aq50QQohPgjxAJO9J7hZCCJEVuZG7Fy5ciLm5ucrPwoUL/9V25SeSu4UQQmSFnHfnTLZGklepUoW7d+9SqlQp6tevz5IlS9DT02Pjxo2ULl1a03UUQgghRA5J7hZCCJHXpk6dyvjx41WWpR9FDikdwtra2vj7+6ss9/f3x97eXm3Z9vb2WYrPrIz4+HjCwsJURpNntRxNkdwthBBC/HuyNZJ8xowZJCenDOKfO3cuXl5eNGnShL///ptVq1ZptIJCCCHyv2QUGv8RWSO5WwghRFbkRu7W19fHzMxM5UddJ7menh61a9fm7Nmzb+uTnMzZs2dp2LCh2vo2bNhQJR7gzJkzmcarU7t2bXR1dVXKcXd3x8fHJ0vlaIrkbiGEEFkh5905k62R5K1bt1b+f9myZXn06BEhISFYWloqn7Sdl/ZoGed1FXJVk2TtvK5Crmsd8e8/GOfftMe4Xl5XIVf5JnzaO9KyLqfzugq5SrfFUI2XKXOj5b2PPXevuVIor6uQq2okJuV1FXJdJeuQvK5CrnIMts7rKuSq7pYBeV2FXHWp8tS8rkKu+sp/v8bLzOvcPX78ePr06UOdOnWoV68eK1euJCoqin79+gHQu3dvihQpopyuZcyYMTRt2pRly5bRvn179u3bh6OjIxs3blSWGRISgo+Pj3LakjdTltjb22Nvb4+5uTkDBgxg/PjxFCxYEDMzM0aNGkXDhg1p0KDBv/wX+Phz98Gwe3ldhVxV4CP4G+c2cx2jvK5Crmoam61xofnGRYO83lPnrvuJ4XldhXzn094icl+WOsn79+//QXFbt27NVmWEEEIIoVmSu4UQQuRH3333HYGBgcyaNQs/Pz9q1KjByZMnlQ/n9PHxoUCBtx1gjRo1Ys+ePcyYMYNp06ZRtmxZjhw5QpUqVZQxR48eVXayA3Tv3h2A2bNnM2fOHABWrFhBgQIF6NKlC3FxcbRu3Zr169f/Cy1+S3K3EEKI/GrdunX88ssv+Pn5Ub16ddasWUO9epkPFD1w4AAzZ87E29ubsmXLsnjxYtq1a6d8/fDhwzg4OODk5ERISAh37tyhRo0aytdDQkKYPXs2p0+fxsfHBxsbGzp37sz8+fMxNzfPUt2z1Em+fft2SpQoQc2aNVEoPu2RokIIITRHMkbekdwthBAiOz6GjDFy5EhGjhyp9rULFy5kWNa1a1e6du2aaXl9+/alb9++7/xMAwMD1q1bx7p167JSVY2S3C2EECI78jpj7N+/n/Hjx+Pg4ED9+vVZuXIlrVu3xt3dHVtb2wzx165do0ePHixcuJAOHTqwZ88eOnfujLOzs/Iid1RUFI0bN6Zbt24MGjQoQxm+vr74+vqydOlSKlWqxLNnzxg6dCi+vr4cPHgwS/XPUif5sGHD2Lt3L15eXvTr14+ePXtSsGDBLH2gEEIIIf49kruFEEKI/EVytxBCiPxo+fLlDBo0SHnXloODA8ePH2fr1q1MmTIlQ/yqVato06YNEydOBGD+/PmcOXOGtWvX4uDgAECvXr0A8Pb2VvuZVapU4dChQ8rfy5Qpw88//0zPnj1JTExER+fDu76zNEHTunXrePXqFZMmTeKvv/6iWLFidOvWjVOnTskVbiGEEJlKzoWfrFq3bh0lS5bEwMCA+vXrc+vWrXfGHzhwgAoVKmBgYEDVqlX5+++/VV5XKBTMmjWLQoUKYWhoSIsWLXj8+LFKjLOzMy1btsTCwgIrKysGDx7M69evs1H77JPcLYQQIjs+htz9XyW5WwghRHbkZe6Oj4/HycmJFi1aKJcVKFCAFi1acP26+ucOXr9+XSUeUp7HkVn8hwoPD8fMzCxLHeSQxU5yAH19fXr06MGZM2dwc3OjcuXKDB8+nJIlS/7rJ/5CCCHyh2Qtzf9kxZvbvmbPno2zszPVq1endevWBASof1Ddm9u+BgwYwJ07d+jcuTOdO3fm/v37ypglS5awevVqHBwcuHnzJsbGxrRu3ZrY2Fgg5bavFi1a8Nlnn3Hz5k1OnjzJgwcP3nubd26Q3C2EECKr8jp3/9dJ7hZCCJFVuZG74+LiiIiIUPmJi4vL8NlBQUEkJSUpnx3yhp2dHX5+fmrr6+fnl6X4DxEUFMT8+fMZPHhwlt+bo0f9FihQAC0tLRQKBUlJSTkpSgghhMg1aW/7qlSpEg4ODhgZGWX6wKu0t31VrFiR+fPnU6tWLdauXQukjCJfuXIlM2bMoFOnTlSrVo2dO3fi6+vLkSNHADh27Bi6urqsW7eO8uXLU7duXRwcHDh06BCenp7/VtMzkNwthBBC5C+Su4UQQuSVhQsXYm5urvKzcOHCvK6WWhEREbRv355KlSopH8idFVnuJI+Li2Pv3r20bNmScuXK4erqytq1a/Hx8cHExCTLFRBCCPHpS0ah8Z8PvaKdG7d9eXl54efnpxJjbm5O/fr1lTFxcXHo6elRoMDbVGtoaAjAlStXsvmXzB7J3UIIIbIqN3K3+HCSu4UQQmRVbuTuqVOnEh4ervIzderUDJ9tbW2NtrY2/v7+Ksv9/f2xt7dXW197e/ssxb9LZGQkbdq0wdTUlD/++ANdXd0sl5GlTvLhw4dTqFAhFi1aRIcOHXj+/DkHDhygXbt2Kp0AQgghRG770CvauXHb15t/3xXTvHlz/Pz8+OWXX4iPjyc0NFT5sJJXr15lo8XZI7lbCCGEyF8kdwshhPhY6OvrY2ZmpvKjr6+fIU5PT4/atWtz9uxZ5bLk5GTOnj1Lw4YN1ZbdsGFDlXiAM2fOZBqfmYiICFq1aoWenh5Hjx7FwMAgS+9/I0szmDs4OFC8eHFKly7NxYsXuXjxotq4w4cPZ6syQgghPk25MXZs6tSpjB8/XmWZumSdVypXrsyOHTsYP348U6dORVtbm9GjR2NnZ/evnuBK7hZCCJEdMu4770juFkIIkR15nbvHjx9Pnz59qFOnDvXq1WPlypVERUXRr18/AHr37k2RIkWUg9vGjBlD06ZNWbZsGe3bt2ffvn04OjqyceNGZZkhISH4+Pjg6+sLgLu7O5AyCt3e3l7ZQR4dHc2uXbuUd5kD2NjYoK2t/cH1z1Inee/evdHSkieuCCGEyJqsPBX7Q+nr639Qp3hu3Pb15l9/f38KFSqkElOjRg3l799//z3ff/89/v7+GBsbo6WlxfLlyylduvQHtVETJHcLIYTIjtzI3eLDSO4WQgiRHXmdu7/77jsCAwOZNWsWfn5+1KhRg5MnTyrvwPbx8VEZMNaoUSP27NnDjBkzmDZtGmXLluXIkSNUqVJFGXP06FFlJztA9+7dAZg9ezZz5szB2dmZmzdvAvDZZ5+p1MfLy4uSJUt+cP2z1Em+ffv2rIQLIYQQeS7tbV+dO3cG3t72NXLkSLXveXPb19ixY5XL0t72VapUKezt7Tl79qyyUzwiIoKbN28ybNiwDOW9OSjYunUrBgYGtGzZUnMNfA/J3UIIIUT+IrlbCCFEfjVy5MhMz7MvXLiQYVnXrl3p2rVrpuX17duXvn37Zvr6l19+iUKhmTH0WeokF0IIIbIjrx/WpenbvrS0tBg7diw//fQTZcuWpVSpUsycOZPChQsrO+IB1q5dS6NGjTAxMeHMmTNMnDiRRYsWYWFh8W//CYQQQogsyevcLYQQQoiskdydM9JJLoQQItfldarOjdu+Jk2aRFRUFIMHDyYsLIzGjRtz8uRJlYeE3Lp1i9mzZ/P69WsqVKjAhg0b6NWr17/XcCGEECKb8jp3CyGEECJrJHfnjHSSCyGE+E/Q9G1fWlpazJs3j3nz5mUas3PnzizXUwghhBBCCCGEEP8u6SQXQgiR6/L6ASJCCCGEyBrJ3UIIIUT+Irk7Zwq8P0QIIYQQQgghhBBCCCGE+DTJSHIhhBC5Th4gIoQQQuQvkruFEEKI/EVyd85IJ7kQQohcJ6laCCGEyF8kdwshhBD5i+TunJHpVoQQQgghhBBCCCGEEEL8Z8lIciGEELlOHiAihBBC5C+Su4UQQoj8RXJ3zkgnuRBCiFynkBu/hBBCiHxFcrcQQgiRv0juzhmZbkUIIYQQQgghhBBCCCHEf5aMJBdCCJHr5LYvIYQQIn+R3C2EEELkL5K7c0ZGkgshhBBCCCGEEEIIIYT4z5KR5EIIIXJdssyNJoQQQuQrkruFEEKI/EVyd85IJ7kQQohcJ6laCCGEyF8kdwshhBD5i+TunJHpVoQQQgghhBBCCCGEEEL8Z/3nR5I37NWSpkM6YmpjzquHPvw5ezvP7z7JNL5qu/q0/rErlkVtCPLy48SivTy64KIS02rct9Tr0RxDM2O8Hd35Y8ZWgrz9lK8XqVyStlO+p1j10iQnJXP/xC3++uk34qPjcqWN1Xu3oPaQ9hjbmBP40Ifzs3bif/dppvFl29ej0Y/fYlbUmjBvfy4v3If3+bsqMQ3Hd6Hq983QNzPC19GDs9O2Eebtr3zdtkpJGk/9DrtqpVEkJ+N54jYX5+0mIRfaOHBwT0aPGYSdnQ33XR8yccJcnJ3uZRrf+X9tmT5zHMWLF+XJE29mz1zCmdMXVGKmzRhLn77fYW5uxs0bTowbO4unT7wBaNykPsdP7FFbdrMvOuPs7KqppgFQol9LSg/viL6tORFuPjyYtp3wO5lvo/Yd61N+clcMi9kQ5eXHo/l7CTzr8vb1dnUp3qcF5tVKoVfQlMvNpxDx4JlKGQX0dak4pyeFOzekgL4ugefvcn/KNuIDwzXaNoDi/VpRanhH9GzNiXTz4eG0be9sn13H+pSd3A3DYjZEe/nhPn8PQWnaZ9euLsX6tMQstX1Xm08mUk37ys/pSaHOjSigr0vQ+bu4TdmaK+3bd9GFHf84ERwRRbkiNkzu1oyqJe0zjT/t7MH6Y9fwDY6guK0FYzo1oUmVUsrXz7o85sDlezx8HkB4VCz7pvxAhWK2ytfDo2L59fh1rj98hl9oBJYmRjSrVobhHRthaqiv8fZ9KLntS2hSnd4taTi4PSY25vg/9OHk7B34viOvVWxXjy9/7IpFUWtCvP05u2gvnmnyWoU2daj1QwsKVS2JkaUpG9tOw99Ndb+hra9Lyxk/ULljA3T0dHly6R4nZmwjKigiV9pYsl9LygzviL5Nyr7//vTthL1j31ioY30qTHq773/4014C0u37S/Z+u++/+JX6fX+lOT0p0untvv/elG3EB2l+32jWvSMW/b5F27og8e5PCVqwnrj77pnGG7dqQsGRfdApYkfCs5eErNhC9OXbb19v8Tlm3dqjX6ks2hZmPO8yjHh31W3C9Nu2mLZvhn7FzyhgYoxXw29IjozSeNsAPuvbkgrD22NgY06Ymw/O03cQ4pL5Nlq0Qz2qTu6KcVFrIr38uffTXl6de7uNFmlXh896t8Cyakn0C5pyqsU0wtSsvxqzf6B4pwYU0NfF78I9nKZsIy4XtlHT777GvE9XtK0KEu/xhODF64h/x/ozavkFlsP7oFPYngSfl4Su2kzMlVtvX2/eGNOuHdCrmLL+fL8bSry76vZu0qUdJm2bo1chZf35NOmca+uvaL9WFB/eET1bC167PcNj2jYi3vH9s+3YgNKTu2FQzIYYLz885+8mOM33z6ZdPYr0aYFZtdLoFjTlZvNJvE63/gr3+gr7/32OabVS6JgacbFsPxIjonOlfR9KcrfQpH4Dv2f46P7Y2Frjdv8R0yf9zJ13nDd17NSaSdNHU6x4EbyePOOnOcs4e+aSSsykaaP4oXdXzMxNuX3zDpPHz8Xr6dvvVtXqlZgx50dq1KpCUlIyx4+eZvb0xURH5c53a+jQPowfNxR7exvu3XvI2HEzcXR0yTS+yzftmTNnIiVKFMXT05tp0xdw8uQ5lZjZsybQv38PLCzMuXb9NqNGTcPT00v5etmypVi0cAYNG9ZFT08XV9eHzJm7lIsXr2m8fV36dqbnsO4UtCmIp5sny2asxs3lUabxzTs0ZfCkARQqas9zrxes+3kD18/dVL7+Zdsm/K/311SoWg7zgub0ajmQxw88VcrQ09dj9OxhtPy6Obr6ety8cItfpq4kJChU4+0r1a8lnw3voDz2ujd9xzuPvQqnHnsZFbMmysuPBz/tUzn2KtSuLiV7f4VF6rHX+a+mZjj2qr5kADZfVMHAzpLE6FhCbnvg9tM+Xnv6arx9n/dqRbPUvi/fhz78MXsbPu/o+6rerj5tfuxGwdS+r2OL9vAwTd9X1dZ1afRDS4pWLYWxpSlL203GN83xs5G5Ma3HdaV8k2pYFrHmdXAE90/f5sTy34mNjNF4+zr3+ZruQ7ulbJ8Pn7B65loeuWR+bNK0/RcMmNgX+6L2vPB+yYYFm7h57u2xSZO2jfm6ZwfKVSuHuaUZA1sNwdNN9e+lp6/LsJlDad6pGXp6uty66MjKaasIDQrTePs+lOTunPlPjySv3qEBHWf04p9Vh1jVfhqv3J4xYOcUjK3M1MaXqFWW71eP4vb+C6xqN5UHpx3pvfFH7MoVVcZ8ObQjn/drw+HpW1jTeSbxMXEM2DkFHX1dAMxsLRm0ezrBz/xY23kmW/oswq5cUbotHZYrbSzXsT5fzPyBGyv/YHf7GQQ99OGbXZMxzKSNhWqXpd2aEdzff5Hd7WbgecqJrzeNwypNG+sM60CNfq34Z+pW9n49m4ToOL7ZNRnt1DYa21nQZc8Uwrz92ddpDn/0+gWrckVpvXyIxtv3TZf2LFg4jcULV/NF46+5f/8RfxzZjrWNldr4evVrsWXbSn7bcYAmn3fk+LEz7Nn3KxUrlVPGjB03mCFD+zBuzEy++vIboqKi+ePINvT19QC4ecOZsqXrq/zs2LYfby8fjXeQF+rUgIpze/F42SGutJxG5INn1N83BT1r9evPsk5ZajqM4vmeC1xpMRX/E47U2f4jJhXerj9tI31Cbrrz6Ke9mX5upXm9sGtVC+dBq7jeeR4G9pbU3jpOo20DsO/UkApze+G57CDXWk4l8sEz6uybmmn7LOqUo7rDaF7sOc+1FlPwP+FIre0T0rXPgNCbj/D4Sf2FDIAK83pj26o2LoNWcqvzXAzsLam5dbzG23fKyZ1lhy8xpF0D9k75gXJFrRm+9jAhkeoPzF2e+jJ12990bliFfVN/oFm1zxi38SievkHKmJi4BGqWKcKYTo3VlhEY/prA8NeM/6YJB6f3Zl6vVlx96M3cXac13r6sSM6FH/HfVKlDA1rO+IFLqw6zqcMM/B/68P1vUzDKJK8VrV2Wb9aMxOX3C2xqPx3304502zgemzR5TdfQgOe33Tm7aF+mn9tqZk/KfVWTQ8NXs6PbfEztLOm6QfP7RYDCnRpQaU4vPJYd4lKraUQ8eEb9ve/e99f6dRQ+ey9wqeVU/E44Unfbj5im2TfqGOkTfMudh+/Y91ee1wv7lrVwHLSKa/+bh769JXVzYd9v3KYp1pMGE/rrbl50HUG8+1MKbfgZ7YLmauP1a1TCbslUIv84yYuuw4k6dw371bPR+6yEMkbL0IBY5wcEr9iS6ecWMDAg+oojoZsyX8+aUOzrBtSY8wMPlh3mdOsZhLn50HTvFPQz2Uat6pSl4a8jebrnAqdaTeflSUc+3zYe8/Jp158BgTfdufdz5nWvObcnhVvV5Nrg1Zz/Zj6GdpY03qL59WfUqikFfxxC2IZd+PYYRrzHU+zWL6SApYXaeP3qlbBZOI3IIyfx7T6M6PNXsV0xB90yJZUxWoYGxN65T+iqzZl+bgEDfWKu3iZ8S+bbsCbYdmpI2bm98Vp2iNstp/D6wTNq7JuGbibfP/M65ajsMBrfPee51WIKgSduU237RIwrFFPGaBvpE37THc93HJtoG+oTfP4u3quOaLpJ2Sa5W2hKp/+1Zc7Pk1m2eB2tmnbhwX139h7ehLV1QbXxderV4NctS9n72yFafvENJ/4+y7bda6hQsawyZuSYgQwY0pNJ4+fQrsV3REdHs+/wJuU5m529Db8f2YL3Ux/affUd33cZRPkKn7F6/YJcaWPXbzvyy5JZ/PTzCurXb8s9VzeOH9uFTSbnpQ0a1Oa339axbfs+6tVvw9GjJzl4YDOVK5VXxkz4cTgjRvRj5KipNG7ckeioaI4d24W+/tuBL0f+2IG2jg6tW39Hg4btuOfqxpE/tmNnZ6PR9rX4uhljZg9n8/Lt9Gk9iMduT1i55xcsrSzUxletU5l562fx197j9Gk1kEsnr7Bk60+ULv928I+BkQF3b7mybsHGTD937JwRNG7ZiGlD5jDsmzFY21mzaMs8jbYNUo69Ks/pifuyw1xsNZ3wBz40fM+xV+1fR+Kz9wIXWk7j1Qkn6m8br3LspZ167PXgHcdeYfe8uDN2A2e/mMD17otAS4uG+6ZAAS2Ntq9Gh4Z0mtGLU6sOsrz9VHzdnjF451RMMjk2KVmrHD1Xj+bW/vMsazcF19OO9Ns4Afs0x896RgZ4OT7i2CL1uc3MzhJzO0uOLtjFklYT2TvhV8o3rcF3i4dqtG0AzTp+yfBZQ9m+4jcGtR3KE7en/LJrERaZbJ+Va1di1rrpHN93koFthnLl5FV+2jyXUuVLKmMMjAxwvX2fjQs2Zfq5I2YPp1HLhswZMo8x347H2s6KeZvmaLZxWSS5O2f+053kTQa25+a+czgeuEiA50sOT99CQkw8dbt9qTa+cf+2eFy8y8WNxwh44svp5Qd4+cCLz/u0Vok5u+YP3M444ffIh/3j12NmZ0nlVnUAqPhVTZISkjgycxuBT1/x4t5TDk/fQrV29bEqYafxNtYa2Jb7e8/jduASIY99+WfqNhJj4qjyXVO18TX7t8b74j2cNhwnxNOX68sOEnDfmxp9W74tc0Abbq35k6dnnAl69JyT4xwwtrWgTKvaAJRObeO5GTsIffoK/3tP+WfqVsq2q4e5hts4YmR/dmzfz+5dh3B/5MnY0TOIjomhV69v1cYPG96Xf85cYvWqTXi4P+Hn+Su46/KAwUN6vY0Z0Y+lS9bx9/F/ePDAnaGDJ2BfyI4OHVsBkJCQQEBAkPInJCSMdh1asGvXIY22DaDU0PY833WOF/su8trjJa4Tt5AUE0+xHl+qjS85uC2B5+/ydP0xXj/2xWPxAcJdvSjZ/+02+vLgFTyXHybokvoOfR1TQ4p93wy32b8RfOUBEfe8uDtmAwXrlcei9mcabV/J1Pa93HeRKI+XPJi4maSYeIpk0r4Sg9sSdP4u3uuPEfXYF8/FvxPh6kXxNO3zPXiZJ8sPE3zpfqbtK/p9Mx7N/o2Q1Pa5jnHAsl55zDXcvt/OOvNNoyp0bliZMoWsmNG9BQZ6Ohy5rr5ue87foVGlkvRtWYfS9laM6NiIisVs2XfRRRnToX4lhrRrQP0KxdWW8Vlha5YN6kjTqmUoZmNBvfLFGdnxcy7e9yIx6b+W4sSnqMHAttzZd567By4R9Pglx6dtJSEmjhrd1Oe1ev3a4HnxHtc3HCfI05cLyw7y6r43dfu0Usa4/nGFy6v/wOuK+u+mvqkhNb/7kjM/7cb7mht+9705OmEDxeqUo0hNze43AEoPaY/P7nM8T93335uUsu8v3v1LtfGlBqXs+5+k7vvdl6Tu+/u93Te+OHiFx8sPE3g5831/8R7NeDDnN4KvPiD8nhd3x6bu+2tpto0Wvb8h4uBJIo+cJuGpD4HzVqOIjcP0f63Vx/fsTPRVR8K2HSTh6XNC1+4kzs0Ts+87KWNe/3WWUIfdxFy/k+nnhu/6g7AtvxN7L/NRb5pQfkhbnu4+j9f+S0R4vMRx0lYSY+Io1UP9NlpuYBv8zt/D/dfjRD725f6Sg4S5evNZ/7fb6LODV3Bb8Qd+meQ2XVNDSvX4EpfZuwm46kboPW9ujduAdb1yWGl4/Zn36kLk4RO8/vMUCU99CP5pVcr666x+/Zl9/z9irt0mYscBErx8CFu/g/iHnph1f7v+oo7/Q/jGXcTedM70cyN2/0H4tv3EuT7UaHvSKz60PS93neXVvgtEebzkUeqxSeEezdTGFxvclpDzLvis/4voxy95uvh3Il29KJrm2MTv4GW8lh8iJJNjL4DnG//m2Zo/CXd6rPE2CZHXhozow+4dB9i3+w883J8wadwcYqJj6d7zG7Xxg4b25vw/V1i/ZiuPPZ6y5OfVuN59SL9B37+NGdablb84cOrvczx84MGooVOws7elTfsWALRs/SWJCYlMmTCPJ57euNy5z6Txc+jQqTUlS6k/js6JMWMGs2XrXnbu/J2Hjx4zYsQUoqNj6dunu9r4USMHcOr0BZYvd+DRI0/mzF3KnTv3GTa879uYUQNYuGg1f/11Gtf7D+nXfyyFC9nR6euU/YuVlSVly5bml1/W4Xr/IZ6eXkyfvhBjYyMqVy6v9nOzq8fgrvy55zjH95/E+/EzFk9eTmxMLB16tFMb/93ALtw4f4vdv+7H29OHjb9sxd31Md/2+58y5uShM2xdsZPbl5zUlmFsakzHHu1YNWc9Tlfv4O7qwU/jF1OtblUq16qk0fZ9NqQdz3afx2ffRSI9XnJ30haSYuIo0V197i4zqA0B5+/imXrs9WjJAcJcvSjV723ufnHwCh7L/yDwsvrcDfBs1zmCbzwi5nkQ4a7ePFr0O0ZFrTEqptmLHE0HtufGvnPcPnARf8+XHJy+mYSYeOpl0vfVpH9bHl28y/nUvq+Ty3/n5QMvGqfp+3L64zKnVx/G46r69vl5vGD7sBW4nXUm2Mcfz+sPOLF0H5W/qkUBbc12RXYd3IXje//m5O+nePbYh+VTVhIbG0e77m3UxncZ8A23Ltxmv8Pv+Hj6sHXpdh7f9+R/fd8em5w59A87V+7C6bL6YxNjU2PadW/D+nm/cueaCx6uj1k8/heq1q1CpVoVNdo+8e/56DrJFYp/59YAbV1tilQphWeaL7RCoeDx1fuUqFVW7XuK1yzL43Q7AI9L9yieGl+wmC1mtpYqMbGRMTx3eaIsU1tPl6SERJV2JsTGA1CyrmYTWQFdbeyqlsLnyoO3CxUKfK48oFAmJ0yFan2GT7pOgmeX7injzYvbYGxroRITHxmDn8sTCtd+00YdkhMSIU0bE2MTAChStxyaoqurS42aVbhw/u2tZAqFggvnr1G3Xk2176lbryYXzl9VWXb27GVlfMmSxbC3t1WJiYh4jaOjS6Zltmv/FQULWrD7t4M5bZIKLV1tzKuVIihtUlUoCLp0H4s66rdRy9plCUp3Ah14/h6WmcSrY169NAX0dFTKifL0Jfp5YJbKeR8tXW3MqpUiOG2HjUJB8CVXLOqo304sapclON0JZtD5u5nGq2OW2r605UR5+hLzPDBL5bxPQmISD5/7q3RmFyigRf0Kxbn39JXa99zzekX98qoH7Q0rluCel/r4D/U6Jg4TAz10NHwwkhWKXPhPfDz+rdxdQFebQlVLqXZmKxR4XblP0Uxyd9Fan2Xo/H566R5Fs9BxWKhqKbT1dHiappzgJ68IexGUpXI+hHLffyndvv/y/Uz3wQVrlyUw3b4/4EIW9/3VUvaNact57elL9ItACmpw34+ODvqVyhJ9I80Jh0JBzI07GFRXf8KrX71ihs7v6GtOGFT/+E5ACuhqY1mtFP7pcrf/5ftY11b/d7Sq85lqPPDqwj2ss3Dh1rJayjaatpxIz1dEvQjCqo4Gt1EdHfQqllPtzFYoiL3pjH61TNZftUoZOr9jrjuiX+3jW39autqYVitNSLpjk9BLrphn8j0wr12OkHTfv+DzdzHX4DFFXpHc/Wn7t3K3rq4u1WpU5tLF6yqfffniderUq6H2PbXrVleJB7hw7ooyvniJotjZ26jEREa85o7TPerUqw6Avr4e8fEJKu2MjUmZ+rN+w1qaaJqSrq4utWpV5dy5y8plCoWCc+cu06CB+s+qX7+2SjzAmTMXaVA/ZeBZqVLFKVTIjnNn38ZERERy65YL9RukxAQHh+Lu7knPH77FyMgQbW1tBg3qib9/oEbvcNbR1aF8tfLcvvy2M1uhUHD7shNVa6vf91epXVklHuDGxVuZxqtToVo5dPV0Vcp55unDqxd+WSrnfd4cewWmO/YKfMexl2Umx145OWbSNtKnePemRD0LIMY3ONvlZChXV5uiVUrhcfXtNqFQKPC46krJWupzVcmaZXl8VXUbenTpbqbxH8rA1IjY1zEka3Dwlo6uDuWrllPpzFYoFDhddqZSJhdTKteulKHz+9bF21TKwnZVrmpZdPV0VcrxefIcvxf+mX7uv0Fyd858dJ3k+vr6PHyYuyNEAIwtzdDW0SYy3TybrwPDMbWxUPseUxsLXquLt7ZIfd1cuSytyDRlPrn2AFMbc5oO7oC2rjaGZsa0ndwDSJmKRZMMC5pSQEeb6HR1jg4Kx8hG/S3NxjYWRAeqzl0ZFRiBUWr93/wbnW5+y+igCGWZz6+5YWRjTu0h7Smgq42+uRFNpn6XUr6dRQ5b9ZaVlSU6OjoEBASpLA8MCMr09jI7O2sCAoMzjbdN/TcrZfbq3Y2z/1zG19dP7evZpVfQjAI62sSl257iAsPRt7VQ+x59W4sM82rHvyNefRnmJMUlZJgHMz4oHP1MvhvZ8aZ96eub1falxKvfnjMrI1lN++I03L7Q1zEkJSuwMjVSWW5lakRQJnOMBkVEYWWWLt7MONP4D63HphM3+ebzqtkuQ4j3+bdyt5FlSl5Ln4ujgiIwySSvmdhYEJU+dweFY5yF77uJjQWJcQnEpfsuRgWFY6LB/QZkf9+vLt4gC/t+g0z2/e/63OzQtjRDS0ebpOAwleWJwaFoW6s/DtKxtiQpWHXu0aSgzOPzkl7qsVdsuvURGxiBQSa5ysDGIkN81tefBUlxCSSkW3+xgeEYaHAb1bY0T11/6dbHO9aftrVlhvWdEq9+moW8pJvJsUl8YDh6mawPPVsL4gPDMsRn5dhEiLzwb+XuglYW6OjoEBiQ/hwsGFtba7XvsbWzJjDD+djbeFs7a+Uy1ZggbG1TztmuXLqJrZ01w0f1R1dXF3NzM2bMGZ/6fs2O0rW2LoiOjg7+/oEqywMCgrCzs1X7Hnt7GwL8VdvoHxCoPOd8869/ur9DQEAg9mnq36ZtD2rUqExIsDuREU8YM3oQHTv2JCxMc88TsShojo6ONiGBISrLQ4NCsbJRvy+3silISFC6+MBQrGw/fN9vZVuQ+Lh4Xke8VlkeksVy3kc/NXdn5VjKIJNjr+wcM5Xs24L2T7bS4ek2bJvX4Fq3BSgSkrJcTmYy6/uKfE/fl9p46+znNmNLU1qO+obre89muwx1zAuao62jTUig6rFJaFAoBTPpYytoY5lhXvvQwDAKZrI9qy1DuX2qPh/lXZ8rPn559uDO8ePVz/+blJTEokWLsLJKmbtr+fLl7ywnLi6OuDjVh0EmKpLQ0dLWTEU1zP/xC/b/+CsdZ/aizaTuKJKSubr9JJGBYSiSP42pEII9XnJq/AaazvyBxpO7kZyUjMu200QFhKFI/rSuQhUubM9XLZrQt/eovK6KEBm8jolj1PojlC5kxdD2DfK0Lp/G3k38V3O3EEL8F0nu/jTkZu5WKJLR0vroxt0B4P7Ik9HDpjL358lMmz2OpKRktmz4jQD/wE/qnHT1qp8ICAymWfNviImJpX//Hhw+vJ1Gn7fHzy8gr6snPsCLQ1cJvHgfAzsLygxrT92NY7j89RyS4xLyumoao29iyMBtk/H3fMmplZq9A1+oktydM3nWSb5y5UqqV6+OhYWFynKFQsHDhw8xNjZGS+v9DytYuHAhc+fOVVnWyLwyn1u8e9RkVGgESYlJGa6EmdiYE5luNMgbkYFhmKiLT31ybWTqlcT0ZZjamOPr5q383eXoNVyOXsPE2pz46FgUipT50YN9NJvEYkIiSU5MwihdnY2szYkOVH9lOSowDCMb1Yc3GNuYEZ3anjf/GlmbERUQlqZMMwLdfJS/u/95Hfc/r2NkbUZCdBwKBdQa1JZwDbYxODiUxMTEDCMQbGytM1zFf8PfPwjbdA9PSRsfkPqvbboybGytcb2XcaTFD72+JSQkjL+Pa/ZqKEB8SATJiUnopxsdqW9jTlyav31acQFh6KWL13tHvPoywtHW10XHzEhlRKGetTlxmXw3suNN+9LXN6vtS4n/8JEScQFhFFDTPn0Nt8/SxBDtAloEp3tIZ3BkNNbpRou/YW1mTHC6UYDBEVGZxr9LVGw8w9f9gbGBLssHd0RXO287H/9rt2l9qnIzd39pVoXmFtXe+b7o0JS8lj4XG1ubZbiL643XgWEYp8/d1uZEZeH7/jowDB19XfTNjFRGkxtbm/Nag/sNyP6+X118bBb2/bGZ7Pvf9bnZkRQagSIxCe10D1LSsbIkKd2InjcSg0LRtlIdkaNtnXl8XopPPfYySLc+DGzMiM0kV8UGhmWIz/r6C0NbXxddMyOV0eQGNubEanAbTQoNT11/6dbHO9ZfUlBohvWdEh+iNj4vJWRybKJnY058JusjPiAMvXQj8fSyeGzysZLc/WnIzdxtrG+FicG7R2WHBIeRmJiIjW36czCrDHfvvhHgH4RNhnO8t/FvRmDb2Fopz99SfrfmfprnFvxx8Dh/HDyOtY0V0dExoFAwZERfnnk/f09rsyYoKITExMQMdx6nnFOqP//18wtUjoh/w87WRnkO+uZfO1trlc5uW1sb7t5LmU61WbPPadeuBbZ2lYmMTBltPXr0dL766gt69ezKL0vXaaR9YSHhJCYmZRhla2ltSXCg+n15cGAIBdPdMWRpY0lwwIfv+4MDQtDT18PEzERlNHnBLJbzPnGpuTsrx1KxmRx7ZeeYKTEyhsTIGKK8/Ahxekw7900UaluHl0euv//NHyCzvi/T9/R9qY0Pynpu0zc2YPCOqcS9jmHbkGUkJ2pulDxAeEg4SYlJFLRRPTaxtLYkJED9sUlIYCgF090BZ2ljkeFuiXcJUW6fxiqjyd/1uf8Gyd05k2eXfRcsWEB4eDgzZ87k/Pnzyh9tbW22b9/O+fPnOXfu3HvLmTp1KuHh4So/9c3fP/9PUkISL+978VmjKsplWlpafNaoMs+c1T8wx+fOYz5rVFllWdnGVfFJjQ95HkBEQChl05Spb2JIsRpl1Jb5Oiic+Og4qndoSGJcPI+vaG7eMIDkhCT8Xb0o9nmaOmtpUezzyrxy9lT7nlfOnhT/XLWNxRtXUcaH+wQSFRCmUqaeiSH2Ncrgq+ZBQ9FBESREx1G+Y32S4uLxecdDK7IqISEBlzv3afplI+UyLS0tmn7ZkNu31D+46/atOyrxAM2aNVbGe3s/x88vQCXG1NSEOnVqqC2zZ88u7NvzB4mJiZpokgpFQhLh97ywbvJ2e0JLC6smlQlzVL+Nhjo9xrqJ6vqzaVqV0Ezi1Qm/+5Tk+ESVzzUuUwijYjZZKud9FAlJRNzzwipD+6oQ5uih9j1hTo9V4wGrptUyjVcnIrV9VunaZ1jMJkvlvI+ujjYVi9lxy/3tQXhysoJb7s+pVrqQ2vdUK1WIW+4+KstuPPKhWin18Zl5HRPHsLWH0dXRZuXQTujr5tn1UPGJyc3c/YV55fe+LzkhiVeuXpRMl9dKfV6FF5nk7hfOnpRKl9dKNanCi0zyoDqvXL1Iik9UKceqdCEsilpnqZwPkdm+37px5Uz3wSHq9v1fZHHffy9l32iTft9f1IYQDe77SUwkzu0xRvXTPOdDSwvD+jWIveum9i1xdx9i2KCGyjKjhrWIvZv70wRkVXJCEqH3vLBrrLqN2jWuQlAmD2QMdvTEtrHq+rP/ogpBTh++bYXeS9lG7dJsB6ZlCmFc1JpgRw1uo4mJxD/0wKCe6vozqFeTuHuZrL97bqrxgEGDWsSpGXyQ1xQJSUTee0rBJmkG22hpYdmkCuGZfA/CnTywTHdsUrBpVcI1eEwhRE7kZu421rd67/sSEhK45/KAJk3f3tWopaVF4y8a4HjLRe17nG7fVYkH+OLLRsp4n2cv8PcLVIkxMTWmZu1qON66m6G8oMBgoqOi6fRNW+Ji47h44VqGmJxISEjA2dmVZs0aK5dpaWnRrFljbtxQ/9C/mzedaJ4mHuCrr5pw42bK/NteXj68euVPs+ZvY0xNTahXrwY3b6TEGBkZApCc7o50RXIyBQq8/8LHh0pMSMT9njt1G7+dX11LS4u6jWvj6qR+33/f6QF1m6jOx17vizqZxqvz6J4HCfEJKp9bvEwxChW1z1I57/Pm2MumiWrutnnHsVeo02OVYyYA2y+q5viYKeWClRYF9HVzVE5aSQlJvLjvpdJPpaWlRdlGVfB2Vp+rvO88VokHKNe4WqbxmdE3MWTIb9NISkhky8BfSMyF0fGJCYm4u3pQK932WbtxTdyc1W8nD5zcqNVY9dikTpPauGVhu/JwfUxCfILK5xYrXRT7onaZfq74+OVZz8mUKVP46quv6NmzJx07dmThwoXo6mZ9R6Cvr4++vr7Ksg+9Xfvy5uN0WzaMF65Pee7iSeMBbdEz0sfxwEUAvls2jHD/UE4u2QfAla0nGLp/Fl8MbM/D83eo0bEhRauW5tDUTcoyr2w9QfNRnQny9iPkeQCtfuxKhH8oD047KmMa9W7FMycP4qJjKdu4Ku2n/cCJxXuJzcG8w5lx3nyC1suGEODqhZ/LE2oOaIOukT4Pfk9pY+sVQ3jtF8rVxb8DcGfrKbr+Pp1ag9ridc6F8l83xK5aaf6ZsvVtmVtOUn90Z8K8/Qn3CaDRhG+JCgjjyem3D9So3qclr5weEx8VS4kmVWgyvQdXFu3PMJ9rTq1bu5VfN/zCHWdXnJzuMnxEP4yNjNi1K+UWHoeNS3nl68fcOUsB+HX9dv4+uYeRowZw6tR5unzbgZq1qjBm9HRlmb+u28bESSN48sSbZ8+eM33GePxe+XPsr9Mqn930y0aULFWcHTv2a7RNaXk5HKf66mGEuTwl/I4nJQe3RcdIn+f7UtZf9TXDiPULxf3nlG3Ue+MJGhyZRamh7Qn45w6FOzfEvHpp7k14u43qWhhjWMQaffuUK6fGn6V0wMYFhBEXGE5iZAzP95yn4tyeJIS9JiEyhioL+hJ624OwLJywfwhvh+NUXT2McGX72qFtpM/L1PZVXTOcOL8QPFLb92zjCeodmUXJoe0J/OcOhTo3wrx6aR5M2KjSPgOV9hVWti8+tX0v9pynwtxeJIS9JjEyhooL+hF624NwDbev11e1mLnzFJWK21KlpD27z90hJi6BTg1SDsBm7DiJrYUJozulHPx+36wmA1ccYOc/TjSpUoqTTu64+fgz6/sWyjLDo2J5FRJBYHjK1epnqVeprc2MsTY3VnaQx8Yn8nOfNkTFxBMVk/JwYEtTQ7QL5M21Ubnt69PwMeTuG5tP0GnZEF7d88L37hPq9U/Ja3dTc3en5UOJ9Avl3JKUffOtbSfpvX8GDQa14/G5O1Tu2JDCVUtzfMoWZZkG5saYF7HGNPW5GVapF7JeB4YRFRhOXGQMd/ZfoOWMnsSERREXGU2beX147uTByzua3W8APN1wnBqrhhF29ylhdzwpPagt2kb6+KTuG2usGUbsq1AeLUjZN3ptOkGjP2ZROs2+36J6ae5NzLjvN0jdN5qo2ff77D1Ppbk9iU/dN1b5uS8htz0I0/CFgLCdh7H9eQJxDzyIve+Oec//oWVoQOSRlDxru2AiiQFBhKzclhK/6whFtv2CeZ8uRF+6hUnbpuhXLkvgnJXKMguYmaJTyAad1JGKuqWKASmjmN/Mn61tZYm2tSW6xVPygl7ZUiRHRZP4KpDkiEiNtc99wwnqrxpCyF0vgl2eUH5QG3SM9PFKXX/1Vw8l2i8U1wUp26jH5pM0PzyD8kPa4Xv2DsU7NcSyemkcJ77dRvUsjDEqYo1h6jZqWiZl/cUGhBEbGE5CZAxeey9QY05P4kOjSHgdTa2f+hB024NgDa+/8N8OYTN/EnFuHsTfd8fsh9T19+cpAKznTyIxIIiwNSnHjhF7/sB+8zLMen1LzOWbGLf5Ev1K5Qiet1JZZsr6s0U79W4/nRJFAUgKCkm3/gqiU6wIALqflUIRHUPiqwCNrj8fh+NUWj2cCJcnRNx5QvHUY5NX+y4AUGnNCOL8Qnjy814Anm88Qa0jsyk+tANB/zhj17kRZtXL8CjNsZdOumMTo9Rjk/jUYxNIGX2uZ2uBUSl7AEwqFifxdQyxL4NIDFOd7/TfIrn705CbuftDp1rZsG4Hq35dyN0797nj5MqgYb0xMjZk3+4/AFjjsIhXvv4smLcCgE0OO/nj+E6GjuzLP6cu0rlLO6rXrMzEsbOVZW76dSdjJwzl6ZNn+Dx7weTpo/H3C+Dk8X+UMf0Hfc/tWy5EvY6mabNGzJw3gZ/nLiciXHP7jDdWrdrIli0rcHa6y21HF0aNGoixsSE7dqbs67duWYmvrx8zZi5KafPaLZz95yBjxw7mxImzdOvaidq1qzF8+GRlmWvWbGHqlNF4enrh7fWcOXMm4PvKnz+Ppuxvb9xwIjQ0nK1bVvLzzyuIiY2lf/8fKFmyGCdOaPZO570bDzBz5VQe3nXH7c5Dvhv0LQZGBhzfdwKAWaumEugXxK8LU/Z9+zcf4tdDq/h+SDeunr1By07NqVitPIsmLlOWaWZhil0RO6ztUvb9Jcqk5O7ggBBCAkOIiozir71/M3rOcMLDIoiKjObHn0dzz/E+DzTcCem54W9qrRpK2N2nhN55QplBbdE2MlAee9VaM4yYVyE8TM3dTzadpPEfMykztB3+/7hQJPXYy2XiZmWZ7zv2MipuS5FODQi46Ep8cAQGhQpSdtTXJMfG43/WRaPtu7j5OD2WDeO561N8XDxpOqAdekb63Eo9fu6xbDgR/iEcT+37urz1BCP2z6Jpat9XzY6NKFa1NAemvj3vNjI3xqKINeap82/blk7JbZGBYUQGhqNvYsjQ36aha6DH7rHrMDA1xMA05cLO6+AIjU57dGDjIaaumIT7XXceurjz7cBvMDA04MT+kwBMXTmZIL8gNi1KObY6tOUwqw4up9vgb7lx9ibNOzWjfLVyLJu8QlmmqYUpdoVtsbJP2T6LpW6fIYEhhASGEhUZxd/7TjJ81lAiwiKIjoxm9PyR3Hd8gJtz3g0EkNydM3k6vLBu3bo4OTkxYsQI6tSpw+7duz/oVi9NuXvsBsYFzWg17ltMbSzwffiMLX0WKR8IZlHEWuVp2M+cH7NnzFra/NiNNhO/I8jbj52Dl+Hv8UIZc8HhL/QM9emycCAGZkZ433ZnS59FKlfMilUvQ8tx36JvZEDAU18OT9uM8x9XcqWNHn/dxLCgGQ3Hd8HIxpxAt2f80WuJ8sGbpoWtVXZOr5wec2L0ehpN6Mrnk7oR5u3H0UErCE7TRsdfj6FrqE+Lhf3RNzPC19GDw72WkJSmjfY1StNw/DfoGhkQ+sSXs1O38vDwVY237/Ch41hZF2TajLHY2aVMifLN//opH+JStFghlSvrt246M7D/OGbMHM+sOT/y5Mkzvu8+jIdub6+IrlyxESNjI1at+RlzczNuXHfkm//1Iy4uXuWze/Xuyo3rTjz2eKrxdr3x6s8b6FmZUW7St+jbWhDx4Bm3eixSnlAZFlFdf6GOj7kzbC3lp3Sj/LTviPbyw7HvMl4/erv+7FrXpvrqYcrfa20cA4DHLwd5vPQQAG6zfqNisoJaW8ZRQF+HoPP3uD/57YUSTfH78zp6VmaUndRV2T7HdO0jTfvCHD24O2wN5aZ8R7lp3Yny8sO571KV9tm2rkPVNO2rkdo+z18O4rk05eLJo1k7USQnU2PLeGX73Ca/7YzQlNa1yxMaGcOvx64TFBlN+SI2rB/xP6zMjAF4FRqpss+rUbowC/q1Zd1f11jz11WK21iwYvDXfFb47a2YF+49YfautxdsJm/9G4Ah7RowrH1DHj4PwNU75SGyHedsU6nP8Xn9KWKVNw8SS1bIbV+firzO3W7HbmBkZUrT8d9iYmOOv9sz9vReTFRqXjMrbKWyX3zh9Jg/Rq+j2YSuNJvYjRBvP34fvJzANHmtXMvadFo2RPl7l3Upz5m4uOIQl1YeBuD0/F0oFAq6OoxBW0+Hp5dc+XuG6ndMU3xT9/3lJ32Lvk3KvvFmj0XEB6nfN4Y6PsZ5+FoqTO5GhanfEeXlx+1+y4hMt++vuertvrH2hpR9o/vSg3ik7vsfzPoNRbKCOptT9v2B5+/hOkXz+/6okxcJtjTHcmRvdKwtiXv0lFdDpysf7qhTyEblOS1xLm74T15EwVF9sBrTl4RnvviNnku85zNljHGzBtj+PEH5u/3SaQCErP+N0PW7ADD7rj0Fh/dSxhTZmXKiHjB9KZF/ntFY+54fvYG+lSlVJn2LgY05YQ+ecfH7xcSlbqNGRVS30WDHx1wfvo6qk7tSdWo3Xnv5cbXfcsLd366/wq1qU3/V22200YaUbfT+0kM8WJayjd6ZvQtFsoJGm8egra+D3wVXnKZofhuNPn2REEsLLIf1Qdvaknj3J/gPn0ZySBgAOoVsIc0+P+6uG4HTFmI5oi+Wo/qR4POSgHFzSHjirYwx+rIh1vMmKn+3XTIDgDCHnYQ5/AaAadcOWAztrYwptC3lRDZo1i+8Pqo6kCEnAlKPTUpP6oa+rQWRD7xx6bFQeWxiUMRKZfsMd/TgwbA1lJ7yHWWmdSfay497fX8h6tHbO8lsWteh0urhyt+rbhwLwNNfDuCVemxSpE9LSk/sqoypfTRlWgu30et5tf+ixtqXFZK7Px15nbv//OMEVtaWTJo2Ghtbax64PqRHl8EEBaacsxUpqnrO5njLheEDJzJ5xhimzhyH15Nn9PthFI8evh2lu3bVZoyMDVm6ci5m5mbcuuFMjy6DVc7ZatauxoSpozA2NsLz8VMmjZvDwf1Hc6WNBw7+hbWNFbNmTcDe3oa7d93o0LGXcoqYYsWKqLTxxg0nevceydy5k5g/bzKenl5823UgD9zclTFLl63H2NiI9esWY2FhxtVrt+nYsadybvjg4FA6dOzJvHmTOHXqd3R1dXBz86DLtwO456rZTrp/jp7HwsqCQRP7YWVTkMcPPBn3wyTlww/ti9ip5DZXxwfMGjGfIZMHMHTKQJ57vWRS/xk8dfdSxjRp9TkzV05R/v6TQ8pFkM3LtrN52XYAVs5ZR7IimYWb5qGnr8vNC7dZMnWlRtsGKcde+lZmVEhz7HWjxyJl7jZMt+8PdXyM0/B1VJzclYqpx143+y1XOfayb12bWquGKn+vu2E0AI+WHsJ96SGS4+KxalCB0oPbomduTFxgOEE3HnG54xziUz9XU1yOXcekoBltxnXFzMaClw+fsTFN35dlur4vb2cPdo1ZQ9sfv6P9xO4EevuxbfBS/NIcP1duWYceS98eW/Zem3JseWrlQU6tPEjRKqUoUbMsANMvrVKpz/zGowh9oX6K3Ow4/9cFLKzM6TehLwVtLPF0e8KkXlMJTZ0a2a6Ircr6e+DkxvyRCxgwqR8DJ/fnpddLZgycjZe7tzLm85YNmbJikvL32b+mHJtsX76T7ct3ArBu7nqSk5OZt3E2unq63L7oyMppqzXWruyQ3J0zWgrFx/EX3LdvH2PHjiUwMBBXV1cqVXr/lCmZmVSyhwZr9vEplPzpP9hsTohm5t/6WO0xrpfXVchV2p/4PFhNd3+Z11XIVYYthr4/KIt6lfhG42X+9uywxssUWaPJ3D2/xA8arNnHp0bcpz+uo5L1xzfHtCY5Blu/Pygfq2/3aT/g7cmrgu8Pyse+8tf8nY2Suz9Nmszd9hYVNVizj09IjOZHnH9sall9ltdVyFVTkwvndRVy1UWDT/v40jlR/XMLPhUXXvzz/qAsktydMx/NRLXdu3encePGODk5UaJEibyujhBCCA36tC+b/HdJ7hZCiE+X5O5Pk+RuIYT4dEnuzpmPppMcoGjRohQtWjSvqyGEEEKIDyS5WwghhMhfJHcLIYQQGX1UneRCCCE+TclyTVsIIYTIVyR3CyGEEPmL5O6ckU5yIYQQuU4hyVoIIYTIVyR3CyGEEPmL5O6cKZDXFRBCCCGEEEIIIYQQQggh8oqMJBdCCJHrPu3nrgshhBCfHsndQgghRP4iuTtnZCS5EEIIIYQQQgghhBBCiP8sGUkuhBAi18kDRIQQQoj8RXK3EEIIkb9I7s4Z6SQXQgiR6+QBIkIIIUT+IrlbCCGEyF8kd+eMTLcihBBCCCGEEEIIIYQQ4j9LRpILIYTIdfIAESGEECJ/kdwthBBC5C+Su3NGOsmFEELkOoVCbvsSQggh8hPJ3UIIIUT+Irk7Z2S6FSGEEEIIIYQQQgghhBD/WTKSXAghRK6Tp2wLIYQQ+YvkbiGEECJ/kdydMzKSXAghhBBCCCGEEEIIIcR/lowkF0IIkevkASJCCCFE/iK5WwghhMhfJHfnjHSSCyGEyHUKue1LCCGEyFckdwshhBD5i+TunJHpVoQQQgghhBBCCCGEEEL8Z8lIciGEELlOHiAihBBC5C+Su4UQQoj8RXJ3zkgnuRBCiFynUEiyFkIIIfITyd1CCCFE/iK5O2dkuhUhhBBCCCGEEEIIIYQQ/1kyklwIIUSuk6dsCyGEEPmL5G4hhBAif5HcnTMyklwIIYQQQgghhBBCCCHEf5aMJBdCCJHrFPIAESGEECJfkdwthBBC5C+Su3NGOsmFEELkOnnKthBCCJG/SO4WQggh8hfJ3Tkj060IIYQQQgghhBBCCCGE+M+SkeRCCCFynUIhV7SFEEKI/ERytxBCCJG/SO7OGekkF0IIkevkti8hhBAif5HcLYQQQuQvkrtzRqZbEUIIIYQQQgghhBBCCPGfJSPJhRBC5Dp5yrYQQgiRv0juFkIIIfIXyd0580l2kneOi8/rKuSqPfqf5GpTERUfm9dVyFXD9O7ndRVyVXuzinldhVzVzL5MXldBiE/O3FcX8roKuerHwl/kdRVy3dTA8LyuQq4qrKeV11XIVe3bmuV1FXKVXeXP8roKQnxyKpsUy+sq5CozM/28rkKusy5gkNdVyFXjXj/M6yrkKuv4Tzt3a2vJ5Bfi3/Xp97YKIYTIc8nyABEhhBAiX5HcLYQQQuQvkrtzRi7LCCGEyHWKXPgRQgghRO6R3C2EEELkLx9D7l63bh0lS5bEwMCA+vXrc+vWrXfGHzhwgAoVKmBgYEDVqlX5+++/VV4/fPgwrVq1wsrKCi0tLVxcXDKUERsby4gRI7CyssLExIQuXbrg7++f5bpLJ7kQQgghhBBCCCGEEEKIbNu/fz/jx49n9uzZODs7U716dVq3bk1AQIDa+GvXrtGjRw8GDBjAnTt36Ny5M507d+b+/bdTFEdFRdG4cWMWL16c6eeOGzeOv/76iwMHDnDx4kV8fX355ptvslx/mW5FCCFErkuW8WNCCCFEviK5WwghhMhf8jp3L1++nEGDBtGvXz8AHBwcOH78OFu3bmXKlCkZ4letWkWbNm2YOHEiAPPnz+fMmTOsXbsWBwcHAHr16gWAt7e32s8MDw9ny5Yt7Nmzh+bNmwOwbds2KlasyI0bN2jQoMEH119GkgshhMh1ySg0/iOEEEKI3CO5WwghhMhf8jJ3x8fH4+TkRIsWLZTLChQoQIsWLbh+/bra91y/fl0lHqB169aZxqvj5OREQkKCSjkVKlSgePHiWSoHZCS5EEIIIYQQQgghhBBCiHTi4uKIi4tTWaavr4++vr7KsqCgIJKSkrCzs1NZbmdnx6NHj9SW7efnpzbez8/vg+vn5+eHnp4eFhYWOSoHZCS5EEKIf4FCodD4T1Zp+gEiCoWCWbNmUahQIQwNDWnRogWPHz9WifHw8KBTp05YW1tjZmZG48aNOX/+fJbrLoQQQvzb/qu529nZmZYtW2JhYYGVlRWDBw/m9evXWa67EEII8W/Ljdy9cOFCzM3NVX4WLlyY103NFdJJLoQQ4pOXGw8QWbJkCatXr8bBwYGbN29ibGxM69atiY2NVcZ06NCBxMREzp07h5OTE9WrV6dDhw5ZvqIthBBC/NfkRe729fWlRYsWfPbZZ9y8eZOTJ0/y4MED+vbt+280WQghhPjoTJ06lfDwcJWfqVOnZoiztrZGW1sbf39/leX+/v7Y29urLdve3j5L8ZmVER8fT1hYWI7KAekkF0II8S/I63lN0z5ApFKlSjg4OGBkZMTWrVvVxqd9gEjFihWZP38+tWrVYu3atUDKFfqVK1cyY8YMOnXqRLVq1di5cye+vr4cOXIESLnd7PHjx0yZMoVq1apRtmxZFi1aRHR0tMoJuxBCCPEx+i/m7mPHjqGrq8u6desoX748devWxcHBgUOHDuHp6Zmjv6cQQgiR23Ijd+vr62NmZqbyk36qFQA9PT1q167N2bNn39YnOZmzZ8/SsGFDtfVt2LChSjzAmTNnMo1Xp3bt2ujq6qqU4+7ujo+PT5bKAekkF0II8S9Q5MJ/Hyo3HiDi5eWFn5+fSoy5uTn169dXxlhZWVG+fHl27txJVFQUiYmJbNiwAVtbW2rXrv3B9RdCCCHyQm7k7ri4OCIiIlR+0s9zCnmXu+Pi4tDT06NAgbenyYaGhgBcuXIlm39JIYQQ4t+Rl+fdAOPHj2fTpk3s2LGDhw8fMmzYMKKioujXrx8AvXv3VhmFPmbMGE6ePMmyZct49OgRc+bMwdHRkZEjRypjQkJCcHFxwc3NDUjpAHdxcVHenW1ubs6AAQMYP34858+fx8nJiX79+tGwYUMaNGiQpfpLJ7kQQoh86UNPtN/1AJHMpj153wNE3vz7rhgtLS3++ecf7ty5g6mpKQYGBixfvpyTJ09iaWmZvUYLIYQQ+diHzmuaV7m7efPm+Pn58csvvxAfH09oaChTpkwB4NWrV9losRBCCPHf8d1337F06VJmzZpFjRo1cHFx4eTJk8rc6+Pjo5JPGzVqxJ49e9i4cSPVq1fn4MGDHDlyhCpVqihjjh49Ss2aNWnfvj0A3bt3p2bNmjg4OChjVqxYQYcOHejSpQtffPEF9vb2HD58OMv118luw4UQQogPlZ2Hdb3PwoULmTt3rsqy2bNnM2fOHI1/VnYoFApGjBiBra0tly9fxtDQkM2bN9OxY0du375NoUKF8rqKQgghRKZyI3dPnTqV8ePHqyxTd8t2XqlcuTI7duxg/PjxTJ06FW1tbUaPHo2dnZ3K6HIhhBDiY5QbuTurRo4cqTISPK0LFy5kWNa1a1e6du2aaXl9+/Z977NBDAwMWLduHevWrctKVTOQTC+EECJfyssHiLz5910x586d49ixY+zbt4/PP/+cWrVqsX79egwNDdmxY0f2Gi2EEELkYx86r2le5W6A77//Hj8/P16+fElwcDBz5swhMDCQ0qVLZ73BQgghhMg3pJNcCCFErvvUHiBSqlQp7O3tVWIiIiK4efOmMiY6Ohogw8izAgUKkJycnI2/ohBCCPHvycsHd+ZV7k7Lzs4OExMT9u/fj4GBAS1btvzg+gshhBB5Ia8fup3fyXQrQgghcl1e3/Y1fvx4+vTpQ506dahXrx4rV67M8ACRIkWKKOdFHTNmDE2bNmXZsmW0b9+effv24ejoyMaNG4GU+cbHjh3LTz/9RNmyZSlVqhQzZ86kcOHCdO7cGUg5Wbe0tKRPnz7MmjULQ0NDNm3ahJeXl3I+NSGEEOJj9V/M3QBr166lUaNGmJiYcObMGSZOnMiiRYuwsLD4t/8EQgghRJbkde7O76STXAghxCfvu+++IzAwkFmzZuHn50eNGjUyPEAk7YjvNw8QmTFjBtOmTaNs2bIZHiAyadIkoqKiGDx4MGFhYTRu3JiTJ09iYGAApNwqfvLkSaZPn07z5s1JSEigcuXK/Pnnn1SvXv3f/QMIIYQQ+Uxe5G6AW7duMXv2bF6/fk2FChXYsGEDvXr1+vcaLoQQQog8oaX4BC8zXCvUJa+rkKv26H/61zYcfK/kdRVyVWGTgnldhVzV3qxiXlchV608Niivq5Cr9Kto/nbi6vaNNF7mXb9rGi9T5B0dvSJ5XYVc9WPhL/K6CrnueIxXXlchVxXWs8jrKuSqwz2N87oKuUq7coW8rkKuMuz5s8bLlNwt3ueroq3yugq5yqzAx/NQ2dxiXcDg/UH52NnXnnldhVxlrWeW11XIVdpan/YM0ddfntd4mZK7c+bT720VQgiR5xT/sbnMhBBCiPxOcrcQQgiRv0juzplP+7KMEEIIIYQQQgghhBBCCPEOMpJcCCFErkv+9Gb2EkIIIT5pkruFEEKI/EVyd87ISHIhhBBCCCGEEEIIIYQQ/1kyklwIIUSuk7nRhBBCiPxFcrcQQgiRv0juzhnpJBdCCJHr5LYvIYQQIn+R3C2EEELkL5K7c0amWxFCCCGEEEIIIYQQQgjxnyUjyYUQQuQ6ue1LCCGEyF8kdwshhBD5i+TunJFOciGEELlObvsSQggh8hfJ3UIIIUT+Irk7Z2S6FSGEEEIIIYQQQgghhBD/Wf/5TnL7vm2odetXGnjtperxhZjU+Oyd8VYdGlLj8moaeO2l+rnlWDSvpfJ6wXb1qbRvJnUfbKfRq0MYVS6ZoQwtfV1KLRhI3Qfbqe+5i/KbJ6Jrba7JZqn4olcr5l5Zwwr335hw5CdKVC/zzvia7Row4+xyVrj/xrSTv1DpyxoZYtqP68rPtxxY/ug3Ru6agU1Je5XXi1YuxcjfprPk3lYW39lMjwWD0DPS12SzlIYN7YOnxw1eRzzh2pW/qFsnY33T6tKlA/ddL/I64gl3nP+hbZvmGWLmzJ7A82fORIZ7curEPj77rJTytaZfNCQx/qXanzq1q2u6efQe0J2rLifx8HXkzzO7qV6ryjvj23dqxbkbR/HwdeT0lcM0a9EkQ8z4qSNwdDuHx8vb7Dm8iZKli6u8XqpMCTbvWo3L40s8eHadQ3/voGHjuhpt1xtNe7XmpytrWe2+i0lHfn7v9lmrXQNmn13BavddzDi5lMpf1swQ02FcNxbd2sCqR7sYo2b7LFa5FKN/m8Gye9v45c4Wvl8wGP1c2j73nbhIm6GzqNN9LN9P+QXXx97vjD99zZmvR82nTvexfDPuZy47PVB5/Z8bLgyZt5YmfSZRrctIHnm9yFDGPIe9tBs+h7o9xtG03xRGL9qA1ws/TTYryxS58J/47/q39/sAZcuW5vChrfj5uhIS9IiL5//gy6aNNNksFQ17tWTyldX85L6DEUfmU/Q9+8aq7erz49ml/OS+g7EnF1M+Xe6u3LouA3ZOZdadjSz23kuhSiUylKGjr0unef2YdWcj8x5so+evYzHJpeOT7v26cOr2Hzg9u8ieE1uoUrPSO+NbdWzO0Sv7cHp2kcMXdtHkq4YZYkZMGsT5e8dw9L7ApgNrKF6qmMrrFauWZ9Pvq7nmcYYrD08xe+kUDI0MNdquNzr26cjOazs49vgoq4+upHyNcu+Mb9K+CVvOb+LY46NsOPMrdZtlzLm9f+zFXsc9/PX4TxbtWUjhkoVVXv+symcs2r2Aw/cPcvDe74xdNBoDIwONtusN3QZtMJr0K8bz9mI4fCEFir77+Fm7SkOMxq1OiR+zHO3yqsfP2pXrY9B/JsYzt2Oy8BAFCpVULcDQBL2OAzAavxrjeXswmuyAXsf+oG+k4Zal2Hfbk7ar/6begsP03HIW15ch74w/7faCzutPUW/BYb51OM3lx69UXj/78CVDd1+i6dKj1Jh/kEd+YSqvh8fEs+jkHTqtO0n9hYdps+o4i0+6EBmboOmmZYnkbqFJnfp0ZPf1nZzwPMbav1ZTvkb5d8Z/0b4J2y5s4YTnMTb9s4F6zVX3i43bfs7i3Qv5w/UgZ1+cpkyl0hnK0NXXZfRPI/nD9SDH3P9k9saZWFpbaLJZKtr2bseGq5vZ73GIxX8upWz1su+Mb9T+c9ac+5X9HodYeXoNtZrVVnm9QZuGzN41j513d/OHz1+UrFQqQxktv2/N/P0L2P1gP3/4/IWRmbFG25TWl71as/DKOta772bqkQWUrP7ufX/tdg2Yd3Yl6913M/vkMqqkO2+r2boeY3fOYMWdrWzyPkCxSiUzlNGkRwsm7JvDatcdbPI+gKFZ7uz3AXr178Yl5+M8fHGDw6d2Uq1m5XfGt/26BWeuH+bhixucuPQ7X7ZonCFm7JRh3HhwGrfn1/ntkEOG8+7K1Sqw8+CvuDy5hJPHeX5ePgMj49w5Nvm2b2eO3NzH5aen2XrsVyrVqPDO+K86fMnvl3Zy+elp9pzdRqPm9VVe/7JtE1bvXcqZ+0e55XuRspUzbg96+npMXDCWM/ePcuHxCRZtmkdBa0uNtuuNLn06c/jGXi48OcXmv9a/t33NOzRl38UdXHhyil3/bKFhuvY1bduElXuWcPL+Ea6/PE/ZyhmPxfX0dZnw8xhO3j/CWY+/WbBxLpa51L4PJbk7Z/7TneRWXzei5Jy+vFj2O3dbTyTK7RmV9s5E18pMbbxpnfKU+3UcAXvOcrfVBEJO3qLCtkkYlX97EqZtZEDEzUc8+/m3TD+31Nx+FGxVB/fBS7n/zSz07Cwpv2WSxtsHUKtDQ/43ozcnVh1icfspvHR7xoid0zDJpI2lapWj7+rRXN9/nkXtpnD39G0Gb5xIoXJv29hi6Nc07deWfdM3s7TzdOJjYhmxcxo6+roAmNtaMmr3DAKf+bG083TW9VmIfbli9Fo6XOPt69r1a5b+Mpv5Py2nbv023L3nxt/Hd2NjY6U2vmGDOuz+bR3btu2lTr3WHD16ikMHt1C58tuDtIkThjNyRH+Gj5xCo8YdiYqO5u9ju9HXT+lEvXbdkSLFaqj8bN6ym6dPn+HodFej7ev4v9bM/GkiK5c40L5ZNx7e92DXwQ1YWRdUG1+7XnXWbFrM/t2HafdlV079fY5Nu1ZRruLbhDVsdH/6Df6eqT/O5+uWPxAdHcOugxvQ19dTxmzbuxZtHW26dxpI+2bf4Xbfg21712Jjq/7vml21OzSky4zeHF91kAXtJ/PC7Rmjd07HNJPts3StcvRfPYZr+8+xoN1k7p6+zdCNEymcZvtsNbQTzfq1Zc/0TSzpPI24mDhG75yusn2O2T2TwGd+LOk8jbV9FlC4XFF6Lx2h0bYBnLzqxC/b/2Bot7bs/2Uy5UsUYej8dQSHR6qNd3n0lMkrtvO/rxry+9IpNK9XnTFLNvLYx1cZExMbT80KZRjbq3Omn1updDHmjejJkVUz+HXmCBQKBUPmryMpKVnTTRTiX5cX+32AP4/sQEdbh5atu1GvQVvu3nPjzyM7sLOz0Xgbq3VoQIcZvTi76hCr20/jldszBuycgnEm+8YStcrSY/Uobu+/wOp2U3E77UjvjT9iV66oMkbPSB9vR3dOLNqb6ed2mNmLSl/VYvfwVWz4bh5mdpb0chin8fa16dSCSXPH8OuyzXRt2Qf3B4/ZsG9lpidNNepUZYnDPP7Y8xddW/Th3IlLrN6+hM8qvO0Q6T+yFz8M7Ma8SYv5vt1AYqJj2LB/JXqpuc3GzprNB1bj4/WC79sOYGiPsXxWvjQ/r56p8fY17fgFQ2YOYtfKXQxvN5Knbk9Z8NvPWFipv+BQqXZFpq2dwsl9pxjWdgTXTl1nzuZZlCz/9kJGt2Fd6dyvE6unrWZ0x7HExsSycNfP6KbmtoJ2BVm0dyEvn/ky+uuxTOs1gxLlSjBx+Y8ab59O1Ubote9L/NnfiV47keRXzzDsPxMtY/XbZ4Hi5THoPo4Ex7NEr5lAktstDHpOooDd29ytpWdAkvcj4k6oP34uYGZJAbOCxP29k+iV44g7sBadcjUx6KL5Y8tTD56z7Mw9hnxRib2DWlDOzoLhey4TEhWrNt7leRBTD9+kc42S7BvUgmblCzPu92t4BoQrY2ISEqlZzJoxX1VVW0ZgZAyBkbGMb1mNg0NaMe/rulx94sfcvxw13j4h8sKXHZsydNYQdq7YxdC2w3ni9pTFuxZgYWWhNr5S7UrMWDeNE/tOMqTNMK6evMa8zXMoWb6kMsbAyID7t++zacHmTD93+OyhNGjZgLlDfmLctxOwtrNizqbZGm5dis87NqbfzIHsX7mXH9uPxfuhF7N2zcM8k31/+doVGL9mImf3n+bHdmO4eeoGUzZNp3i5t52o+kYGPLztxs6FOzL9XH1Dfe5cdObQugMab1NadTo0otuMPvy16gDzU8/bxr7jvK1MrXIMWj2WK/vPMa/dJFxO32LExkkq5236RgZ4Oj7i0KJdmX6unqEe9y+68Pf6PzTeprTad27FtPk/svqXDXRs/j0PH3iw48B6rDI5NqlVtzqrNi7k991H6NCsB6f/voDDzuWUq/C2I3XIqL70HdSDGRMW8E3r3kRHx7D993XKYxNbext+O+TAM6/n/K91L/p9N4Ky5cvwy5p5Gm9fi6+bMXb2CDYv30Hv1oN47PaE1XuWYpnJd7BqncrMXz+To3v/plerQVw8eZlftv5M6fJvL9QYGhly95YraxdsyPRzx80ZSZOWjZg6ZDZDvxmDjZ01i7fM13Tz+OrrZoyePYwty3fQt81gHrs9YcXuJe9s39x1M/lr79/0aT2IS6eusHjLfEqn2ccYGhlw79Z91v28MdPPHTNnBJ+3bMj0IXMZ3mUs1vZWLNqs+fUn/j3/6U7ywkM64r/7HwL2nyfG4wVPJ20gKSYO2x5fqY0vNLA9oefv4Pvrn8Q8fsnzJfuIcvXCvn9bZUzgwYu8WHGA8Ev31JahbWqEbY/meM/eTsTV+0Tde4rnuHWY1auASa13X2nOjuYD23Nt31luHLiAn+dL9k3fTHxMPA27NVMb/2X/tjy86MLZjX/h/+Qlx5f/zvMHXjTt01oZ06x/O06tOYzrGUd8H/mwc/w6zO0sqd4q5ep+la9qkZSQyO8ztxLw9BU+956wf/omarZrgHUJO422b9yYQWzesocdO3/n4cPHDB8xhejoGPr17a42ftSoAZw6dYFlyx149MiT2XN+4c6d+wwf1k8ZM3rUQBYsXMVff53G1fUhffuNoXBhOzp1SvkbJCQk4O8fqPwJDg7l646t2bHzd422DWDg8N7s3XmIA3uO8Nj9KVPHzyMmOobvfvif2vj+Q3py8exVNqzZjqeHF8sWrOX+PTf6DuyhjBkwtCdrlm3kzInzPHLzYNywadja29CqfcrISsuCFpT+rCS/rtzCIzcPvJ/6sGjeCoyMjShfUbPb6FcDO3B131mup26fe6dveuf22ax/O9wuunBm41/4PXnJX8v38/zBU5r2aaOMad6/HSfWHObeGUdePvJh+/i1mNtZUiN1+6yaun3um7kF/6eveHbvCXumb6JWuwbYaHj73PnXObq0aETn5g0pU6wQM4d0x1BfjyNnr6uN3338Ap/XrEi/zi0oXdSekT06ULFUMfaduKiM6fhlPYZ2a0uDapmPvvm2VWPqVP6MIrZWVCpdjFE9OuIXFIpvYLBG25cVyQqFxn/Ef1Ne7PetrCwpV7Y0S35Zi6vrQzw9vZg2fQHGxkZUqfzuUSrZ0WRge27tO4fjgYsEeL7kj+lbSIiJp263L9XGf96/LR4X73Jp4zECnvhyevkBfB940ShN7r7zxxXOrj6M51VXtWUYmBpSt1szjv30G0+uP+DlfS8OTNxAyTrlKV7z3SPFsqr30B4c3PUnR/Yd56mHN/MmLiY2Jpb/9eigNr7n4O+4ev4G29bv5uljb9Yu3oibqzvf9/9WGdNr8HdsXLGN8ycv4+HmybSRc7G1s+artl8A0LTV5yQmJvHTlF/wfuLDfZeHzJu0mFYdm1OsZFG1n5tdXQZ9w4m9Jzn9+xl8Hvuwauoa4mLjaP1da7XxnQd05vYFRw5sOMhzz+fsWLoTz/uefN3na2XM/wb8jz1r9nL99A28HnmxZOwvWNlZ8XnrlLsZGnxVn6SERNZOX8eLpy/wuOvBqmlraNK+CYVLFtJo+3SbdCTh9j8kOp1HEfCCuCMbUMTHoVNH/fGz7uftSXp8h4TLf6IIfEn8mX0k+3qh2/Dt8XPinYsknDtAkqf64+dk/+fE7v6FpEeOKEL8SXp6n7hTe9CuWAcKaPZ05rcbHnxTsxSda5SkjI0ZM9rXwkBXmyMu3mrj99zypNFndvRtVJ7SNmaMaFaFioUs2Xf7iTKmQ7USDPmiEvVL2aot4zNbc5Z1bUjTcoUpVtCEeqVsGdmsChcfvyIxOe8ucEvuFpry7eAu/L33BKd+P82zxz6snLKKuNg42nRXv1/8ZkBnbl+4ze8OB/DxfM72pTt4fN+Tzn3f7hf/OXSW31buxunyHbVlGJsa0bZ7GxzmbcDlmguPXR+zZPwyqtStTMVams/dXw/szJm9pzh34CwvHj/HYep64mLi+Oq7lmrjO/T/mjsXnTmy4Q9eeL5g77LdPL3/hHZ93+bCi4fP8/uqfdy94pLp5x7bcpTD6w/i7vxI001S0XJgBy7vO8u1Axd45fmCXdM3Eh8Tz+fdMt6dB/BV//Y8uOjC6Y1H8Xvykj+X78fnwVOapzlvu/HHJY6tPsjDTI5NAM5u/ZuTvx7h6R0PjbcprQHDerL/t8Mc3HsUT4+nzPjxZ2JiYun6fWe18X2H9ODSuWtsWruTJ4+9WLFoPQ/uPaT3wLfHo/2Gfs/a5Zv458QFHrk9ZsLwmdjZ29CqXcq5bvNWTUhMSGTWpIV4eT7j3h03Zk74mbZft6BEurvhcur7wd04sucYx/afwOvxMxZNXkZsTCwde7RTG9994LfcOH+LXb/uw9vzGRt+2cojVw+69XvbD3Hi0Gm2rNjBrUtOasswNjXm6x7tWDlnHY5X7/DI1YN54xdRvW5VqtR69x2EWdVjUFeO7jnO8d9P4v34GUumLCcuJpYO3duqje82oAs3L9xit8N+nnn6sPGXbbjff8y3adp38tAZtq7cye3LmbevY/d2rJ67Hqerd3B39eDncYupVrcKlWtV1Gj7skJyd878ZzvJtXR1MKlWhvDLaQ7GFQrCL9/DtLb6W2JN65RTjQfCLrhgWvvdt4qlZVytNAX0dAlLU06M50viXgRiWufDy/kQ2rraFKtSGvc0SUehUOB+1ZVSmXTIl6pZjkdX76sse3jpLiVrpfxNrIrZYm5ryaM0ZcZGxuDt4knJ1DJ19HRJSkhEkebLFB8bD0CZupo7INHV1aVWrWqcPXdZuUyhUHD23BUaNKit9j0N6tdWiQc4feaCMr5UqeIUKmTH2XNXlK9HRERy69YdGtRXX2bHjq2wsrJk+479OW2SCl1dHapWr8SVizeUyxQKBVcu3qBWXfXTutSqW10lHuDSuWvK+OIlimJrb8OVC29jIiNf4+LkSu3UmNCQMDw9vOjSvSOGRoZoa2vzQ9+uBAYE4+riprH2aetqU7xKaZVtSaFQ8OiqK6Vrqf8Olq5ZTiUewO3SXUqnbnvWyu3z7fcrNjIGLxdPSqWWqaOnS2K67TMhF7bPhIREHj55rtKZXaBAAepXK89dDy+177nr4UX9aqp1aFSjInfdvbNdj+jYOI6cv0ERWyvsrfLu1i+57UtoQl7t94ODQ3nk7knPnt9ilLpfHDyoJ/7+gTg5q+/Uyy5tXW2KVCnF4zS5WKFQ4Hn1PsUzyd0lapbFM13u9rh0L9N4dYpUKY2Ono7K5wY+8SX0RWCWynkfHV0dKlUrz43Lt5XLFAoFNy7dpnod9aNsq9euwvVLt1WWXTt/QxlftERhbOysVWJeR0Zxz/mBMkZPT4+E+ASVfX9sTBwAteprbqo0HV0dylYty50rbzttFAoFdy7foWJt9SdMlWpVVIkHcLzopIy3L26PlV1BnNN0BEVHRvPI5REVU0/CdNXktvjYlPZVrvvuadqyRFuHAoXLqHZmKxQkPbmHdnH1uVu7eLkMnd9Jj10oUDxnx71aBkYQGw0a7EROSErm4aswlc7sAlpa1C9lx70X6i8033sRTP1SqhfZG5bOPP5DvY5LwERfBx0NXwTICsndQhN0dHUoV7Wsyj5MoVDgfPkOlTLpSKpUu1KGzm/Hi45UymQ/qk7ZquXQ1dPF6bKzctnzJ8/xf+FPJQ130Ono6lCm6mfcvfL2rmKFQsG9Ky6Ur6V+X1e+VoUMnd8ul+5QLhc68HNKW1eHElVK8zDNOZZCoeDh1XuUecd5m9tV1X3/g0t3Mz3Py0u6ujpUqV6RqxdvKpcpFAquXrxJzbrV1L6nVp1qKvEAl89fp2adlPhiJYpga2ejEhMZ+RoX5/vKGD09PeIT0h2bpObuOvVraKRtkLJ9VqhWTqWzV6FQcPuyE1Vrq59SpmrtytxK1zl84+LtTOPVqVgt5TuYtpxnnj68euGXpXLeR0dXh/Lq2nfFmSqZfE6V2pUydH7fvHA703h1KqS2L205z54813j7skpyd8581J3kz58/p3///rlStk5BU7R0tIkPDFNZnhAYjq6thdr36NpYkBAYni4+LNN4dfRsLUiOSyApIlpleXxgGHo2H17OhzCxNENbR5vIINU6RwSGY5bJZ5nZWBAZFKayLDIwHLPUOUnfvC8y3d8hMk2Z7tfuY2ZjwVeDO6Ktq42hmTGdJn8PpEx1oSnW1gXR0dEhwD9IZXlAQCD2mdz+bm9vg39AoMoyf/8gZby9nW3qsnQxAUHY26sf/dO/b3dOn77Ay5ev1L6eXQWtLNHR0SEo3ejfoMBgbOzUTytgY2tNYIBqfGBAMDa21imvp75PbZmpMQDffzOIylUr8tDnBo9fOTJoWG96dx1KeHhEjtv1xpvtMyLd9hYRGPbO7TNC3facOrfgm/dFvGf7NLexoGXq9mlkZkznyT8Amt0+QyNfk5ScjJWFqcpyK3MzgsLU/x2DwiKwMk8Xb2Gaafy77Dt5ifo/jKfBDz9yxdmNjbNHoqurk+VyhMiq3Mzdebnfb92mOzVqVCEsxIOoyKeMHTOY9h1/ICxMdX+TU0ap+8bXQRn3Y6aZ7BtNbCwy5PrIwHBMszDvqqmNOYlxCcSmOz55HZT552aHZUELdHR0CA5UneM5ODAU60ym9LK2tcoQH5Qm3jp1qp2MZYYoY25eccTK1op+w39AR1cHM3NTxs1Imaojs5yaHWYFU9ZfaLrjy9CgMAraqM8xljaWhKbLhWFp4t/8G5YuJjQwDMvUvOVy7S6WNpZ0HfItOro6mJibMGBKyvfQylb9FG3ZoWVkipa2NorXqnVRRIajZWqh/j0mFiheq26fya/D0DJRH/9BjEzRa96VhNv/ZL8MNUKj40hSKLAyUZ3L3cpYn6DX6qdbCXodi5Wx6nNNrEwMCMpkepYPrcemyw/5pmbGOZaFyA25mbvNlfvFUJXloUGhFMxk/1TQxpLQoHTxgWEUtPnw/VlBW0vi4+KJiohS87maHThimtrG8HR1DgsKwyKTfb+FjQVh6XJFWGAYlhruE9AEE0vT1PO2D+9XMFdzbBIRGIZ5Ls4Jn12WyvPu9McawZlON2pta50xPuBt/Jtza7Uxqccd1y/fwsbWikEje6ObemwyaeZoAGw1OJ2fRUFzdHR0CEn3HQwJCsUqk++UlU1BQtJtz/9n776jmsjaMIA/oYXem1gAQVQUG1Ys2BvWtbsq9rr23rvo2ntvn6urYlvLqmtBd+0odhAVwYY0qYLUzPcHEo0EDEqMyPM7J2fXmXfu3JuZzBtu7tyJjsz5Myu3DEszpKak4l38u2zl5Od3k8z2qcutb67tk/t+KH5tMLMw/dC+z64xkTF5ulbRj+WH7iSPjo7Gzp05z78FACkpKYiPj5d5pQoZ36mGJE/Yk1fYNXYdGg1ohWUBu7DAdyPevoxAfGQsJCq8ZVQZihYtgqZN62Pbjr2qrkq+mvf7VERFRaOjhyfaNO6O03+fx7Y/18DSyvzLG//g3jx5hZ1j16LRgNZYGfAHFvpuwtuXEYiLjIUg+Xl+JfWoWw37F0/CtjmjYGtjgXFLtyElVXUPABMESb6/6Mf0tblb+MFv5Vu9aj4iI6JQv0F71HLzwF9HT+PIoZ05/oBKP5agwGBMHTEHnkO642bIBVy4fwKvX4QiKuItJD/Btf/54+dYPGYJOgz8Bcce/4W9t/Yg7GU4oiOif7rvXhDrQKf3FEgiXiL1bP7exfcjeJeShuF/XkJJcwMMds/f0a55xdxdeHxt7pbwmBJ9tSeBzzD+txnoP6QnHr68iuv+Z/HyxWtEhkf9fLmbvhvm7m+j0mGFR48ezXX9s2fPvliGl5cXZs+eLbOsr14Z9DPI/UtlenQChPSMbKO3NS2MkBYRK3ebtMhYaFoYfRZvnGO8PKkRsVATa0LdUFdmNLmWhXG2Ue3f6l1MPDLSM2BgLltnQwsjxOewr/jI2GwjzwwsjKS/GmdtZ/BZGQYWRnjlHyL9982jl3Hz6GUYmBshJSkZEICG/Vvh7YuIb22WVFRUNNLT07N13FpaWiDssxGBWcLCImFlKfurrJWVuTQ+LDziwzILhIV9rKuVpTnu3H2Yrbzenl3w9m0Mjh3755vaIk/02xikp6dLR8hlMbcwQ2S4/Ft4IyOisv3abWFphsiIzFGXWduZW5jJjMQ0tzCD/4PMeexq16uBRs3qwaVkbbxLyPxVdNr4+ahbvxY6dm2LdSu35kv7ss5Pw8/ON0ML41zPT0N55/OH0XVZ231+jn9+fvoevQzfD+dnalIyBCFzfvSoF+Hf2KqPTAz0oa6mhrexsg/pfBsXD3Nj+Q+4MTc2zPZQz7exCTnG58ZATwcGejqwtbFERSc71PacgHPX76Jl3ap5Lis/SArZbVo/M2XlbpGaPkTquZ/rqrruN2xQBx4tG8Pc0hkJCZmjYYaPmILGjeqhV89O+H3x2i81WWFJH66N+p9d6wwsjJCQw7XxXWRstlxvYGGU7c6w3CRExkFDrAltQ12Z0eT65jnv92vERMciPT0928geMwsTREXIz21REW+zxZt/Ep91d5SZhalMGWYWpgh8+ET6778P/YO/D/0DMwtTJCW+ByCg1+BuePX8dX40DQAQH515/D4fCWhibpxtxFKWmMgYmHyWC40/ic/6r7G5MaIjPo5IM7EwRtDDj583nyMX4HPkAozNjZGclAwIAn4Z0B5vXoTlQ8syCUkJEDIyso0CFxkYQUiIlb/Nu1iI9GXPTzV942yj0RWipQ2dPtMgpCQj+Y/fAUn+Dowx0RVDXSTC289Gjb9NTIH5Z6PLs5jra+NtYops/LtkmOvJj89NYkoahu75D3piTSzr7AZNddWOZ2Lu/nkoK3fbGZRESUOHHLbIFCe9LsqO0DQxN5G5pn0qOjIGJp89MNHEwhjRkfLj5ZYREQMtsRb0DPVkRpNn7lf+9fhrJXxoo9FndTY2N0ZsDtf+2MhYGH+WK4wtjLPdifQjeBeT8OHvNsX7FeLkfDcxtDBGXB6+m3wvMdK/uz//rmGW7S7tLFERUdnjLT/GZ/39bW5hishP/+62NIP//UDpv48ePIWjB0/B3MIUSUnvIQgC+g3pgRfPX+VL2wAgNjoO6enp2e5oMzU3yXYXXpa3kdHZHqhuapHzZ1ZuGRFvoSXWgr6hvsxoclMLE7zNQzlfktm+DLn1zbV9ct8Pxa8NbyOjP7RPT2Y0uYmFSZ6uVfmNufvbqPSbV7t27dC+fXu0a9dO7mvMmDFfLGPy5MmIi4uTefXU//Ich0JaOt7dC4JRnU/mvxSJYFSnAhJuyX8oRMLNxzCqIzsnlVG9Cki4FSg3Xp7Ee88gSU2DUd2P5Wg72EBczAIJNxUvRxEZaRl4+eAZSrt9bKNIJIKTW3kE+z2Ru03w7cco7SY7d2WZOi4I8ct8T96+jEBcRIxMmdr6OrCr5IgQOWUmRMUhNSkFVVrVQlpKKh5dyr+5W9PS0uDndw8NG9SRLhOJRGjYoA6uXZP/cIVr12+hYcM6MssaN6onjQ8OfoE3b8JlyjQw0Ef16pVx7Xr2Mj17dcYffxxAenp6fjRJRlpaOu7f9UftejWky0QiEWq714Sf71252/j53pWJB4A69WtJ4188f4WIsEjUdv8Yo2+gh0quLrj1IUZHJ/OPus9/vZZIJBCpib69YR9kpGXgxYNnMuebSCRCabfyeOYn/zP47PZjmXMPAMrUqYBnH869qBzOT/tKjgiWU2ZCVBxSklLg2soNaSmpCMjH81NTUwNlHYrj+idfgiQSCa7fe4yKTvZyt6noZI/r92SvA9fuPULFT56y/TUECIAgIC0t/89TKnyUlbtFagZf3E5V131dXR0Acq6LggRq+TxfcEZaBl4/CIbjZ9dGR7dyeJFD7n5++wkc3GTnPixVxyXHeHleP3iG9NR0mf2alywCk2IWeSrnS9LT0uF/LxA16laTLhOJRKhRtxru3pT/4K67tx6g5ifxAFDLvbo0/tXzUESGR8nE6OnrokKVcnLLfBsZjfdJ79G8bWOkpKTi6sUb+dE0AJnte3L/CSrVriRdJhKJUKlOJQTcCpC7jb9fACp/Eg8AVepWkcaHvQjD2/BoVK7zMUZXXxdlKpVBgF/2MmOjYpGclAz3Nu5IS0mD3yfz8X6zjHRIQoOg7iD7/VndoQIyXsjP3RkvHkPdQfb7s7pjBUhe5PF7r1gHOv1mABnpSP6fF5Ce/3dHaaqroWwRY9wI+fiDmUQQcCM4AhWKyb/lvkIxM9wIlh0Eci04PMf4nLxLScOQ3f9BU10NK7q4QayhnvcGEOVAWbnbzkD+d9pPpael4/H9JzLXMJFIhMp1KsFfzjUMAPxv+aNKncoyy1zrVoF/DtdReZ7cf4y01DSZcoqVLAarYlbw98u/5ywBmW0Muv8UFWp/vNaJRCK41K6IQD/517pAv0eoUFv2mRgV61TCYyU/gPNrZKSl4/mDZyj7Wb9CWTcXBOXyd1vZz/5uK1unQo5/56lSWlo6HtwNgNtnf3e71auO277y/z70u3kPbvWqyyyr7V4Tt29mxr98/hoR4ZEyZerr66FSlfLSmE9FRUYjKfE9WrVrhpTkVJlniH2r9LR0PLr3GNXqfHx+j0gkQtU6VXD/VvaBgABw/9ZDVKsr+7yfGvWq5hgvT8C9zM9gtTpVpMtKOBRHkWLWeSrnS9LT0hF47zGqfrKfrPY9yGE/D275y8QDQPV6rjnGy/PoQ/uqfvK+KqN99H2ptJO8SJEiOHToECQSidyXn9+Xv9SLxWIYGhrKvLREin2pDN14DFa/NoZFp/rQKVUUJRcNhLquGBF7zwMAHFcNR4kpv0rj32w5AeMGlWAzqDV0HIui+NjO0K/ogLBtJ6UxGsb60C1nBx2nzKcR6zjYQLecHTQ//EqckZCEiD/Pw35Wbxi6lYdehZJwXD4M8b6P8C4f/wjNcn7LCbh1a4gaHerByqEouszvD7GuGNe8LwAAei4dhjYTuknjL2w7CWf3imjYvxWsHGzQclRHlHBxwMWdp6UxPtv+RvPh7eHS2BU2pYuj57JhiAuPwd1/Pj4wq16vZihWzh6W9kVQr2dTdJ7TF0d//xPvP5vr9FstX7kZ/ft1R8+enVCmjCPWrlkIPT0d6UM0t29bifnzJknjV6/eimZN62P0qEEoXdoBM6aPgatrBaxbv10as2r1FkyZPAKtWjVB+fJlsGP7SoSGhuOvv07L7LthgzooWdIWW7fvydc2fWrLuv+hW68O6Ni1DRyd7LFg6XTo6upg/54jme1fNx8Tp4+Uxm/b+AfcG9XGgGG94FDKHqMnDkGFSuWwY8uf0pitG/7AiLGD0KR5fZQuWwrL1y1ARFgk/jmRed7f8r2LuNh4LFs3H2XLOcHewRZTZo9BcdtiOP/Pv/navnNbjqNOt0ao2cEd1g5F0e3D+Xn1w/npuXQY2n5yfvps+xvl3Cui0Yfz02NUJ9i6OODizlPSmPPb/kbL4b+gwofz03PZb4gLj8GdT85P917NUPzD+enesxm6zumLv5RwfvZq3RAHz17BXz7X8OxVGOZt2of3KSlo17AmAGDKqv9h5R9/SeN/9aiPK3f8sfPoOQS/CsO6fSfwMOgFurZwl8bEJSTiUfArPHuZOTIwJDQcj4JfISomc97yV2FR2HLoNPyDXuBNZDTuPHqGsUu2QqyliTqqfICIIOT7i1RDWblbJFLsRzhVXPevXruJmJg4bN+2AhUqOKNUqZJY5DUN9nbF8ffJc3l5+xTy35YTqN6tAap0qAdLBxu0n98Xmrpi3PS+CADovHQImk/oKo2/vO0kSrtXRN3+HrBwsEHjUR1Q1KUkrnySu3WM9FDE2RaWjsUAABYli6CIsy30P9whl5zwHr77fdBqWg+UrOWMouXt0XnxYDy/9Rgvbj/N1/b9b8Of6PhrG7Tp3BIlS9lh+u8ToKOrjSN7TwAAFqyegVFTh0jj/9i0D7Ub1ITn4O6wd7TF0HH9Ua5iWezZdkAas2vTPgwc3Rv1m9VFqbIOWLBmJiLCo3Du5Me81a1vR5R1KQ3bksXRtU8HTFkwDivnr0fCZ3NlfquDmw+hZbcWaNKxMYo7FseIBcOhraON0/sz7zobv3wc+k7sI40/svUIqtavig4Df0Fxh2LoOboHnCqUwtGdH0d+Ht56GN2Hd0PNJjVhV8YOE1aMw9vwt7h8+oo0po1naziWd0RR+6Jo7dkaw+YOxbaF27PNx/ut0v47Bs1qjaFRpT5EFkUhbjsQIi0x0m9lfo8QdxoOrWYfvz+nXT4BdadK0KzTGiKLotBq1BlqRR2QdvXj92fo6EOtiB3UrDK/P6uZ20CtiN3HEetiHej0nQFoaiP54DqIxLoQ6Rtnrhfl758zPWs64ZBfMI7eDcGzyHjM/9sP79PS0baiHQBg2pEbWHXu448v3as74kpQGP539TGCo+Kx/uJD+IfGoGu1j6Nr496n4lFYLJ5FZubq528T8CgsVjrPeVYH+fu0DMxqVRWJKemIepeMqHfJyFDhdEDM3T8PZeVuNQU/fwc2HYRHt5Zo2rEJSjgWxyivEZnXxX2ZeWriivHS5ygAwKGtR1CtflV0GtgBxR2Ko9eYnnCq4IQjOz5eFw2MDeDgXBK2TiUAAMUdisPBuaR0xHpiQhJO7j2FITMGoZJbRZRyKYUJy8bi4c2HCFBCR/TRLUfQpFszNOjYEMUci2HQgqHQ1tXGuf2Zz04YsXw0ekzsJY0/vu0oKrtXQZsB7VDUoRi6jO4GhwqO+HvHcWmMvpE+7JztUbxU5rWxqENR2Dnby4xAN7Ywhp2zPYrY2QAAbMvYws7ZHvpG+vnavjNbjqNut0ao9eHvtl/nD4CWrhiXvX0AAH2X/ob2E7pL489tO4Fy7pXQpH8rWDvYoPWoTrBzccD5T/5u0zXSR3FnOxT58N3EqqQNijvbycxzbmhhjOLOdrC0tQYAFCtdAsWd7aCbz+3buv4PdO3ZHr90aQ2HUvaYu2QKdHV1cODPzL/Vlqydi/HThkvjd2z8E/UauqHf0J4o6WiHkRMGwaWSM/635eM0rNs37MFvY/qjUXN3lC7riCXr5iI8LBL//O0jjenZrwvKVSgDe4cS6Nm3M2YtnIjF81bn+3eTPZv2o213D3h0agY7R1tMXDgGOro6OL43MxfPWjkFQycPkMbv3XIAtepXR/dBnWHrWAIDxvZG2QqlsX/7YWmMobEBSpVzhL2TLQDA1qE4SpVzlN79l5iQiKN//o1Rs4bB1a0yyrg4YcbySbh38wEe5PMPVX9u9kab7q3QslMz2DqWwISFo6Gto43j+zLPtxkrJ2PIpP7S+P1bD6Jm/eroNqgTbB2Ko98YT5SpUBoHsrXPAfZOdgCAEg4lUKqcg3QEemJCIo7t/RsjZg5BFbdKKO3ihGnLJuD+zQd4mMMPgN8Dc/e3Uel0K66urrh16xbatm0rd71IJFLqAXl79Ao0zYxQYkJXaFoYI/FhMPy7z0Pah6lFxEXNgU++mCbcDMSToStQYmI3lJj8K5KD3+BRn9+RFPhSGmPStBpKrfxN+u/SG8cCAF4u2YeXS/cDAIJnbocgkaD0lnFQE2si9sIdPJu0WSlt9Dt+FfqmhvAY3RkGFsZ4HRCCtZ5e0odomBY1k5ljKNjvMXaMXI1WY7ug9fiuiAwJw6aBi/Hm8cc2nt1wFGIdMbp5DYSOoS6CfAOxztML6SkfR/TYVnSEx+hO0NLVRvizUPw5ZTN8D/+X7+3z9j4KC3NTzJoxDtbWFrh79yE8WvVAxIfbm0oUt5EZ+Xf12k306PUb5syegHlzJ+LJ02B06NgPDx9+/IV/8ZJ10NPTxYZ1v8PY2BCXL/vCo3UPpKTI3krbp09XXLnii8DAoHxvV5Zjh0/D1MwUYyYPg4WlOfwfPELPToOlt5bbFCsiM5fqrRt3MWLgJIyb8hsmTBuJkGfPMaDHSDwO+NjBsX7VNujo6cBr+UwYGhng5rXb6NlpMFJSUgFk3grfq9NgjJ82Anv/2goNTQ08fhSE/j1GIOBh/v7yf+vD+dlqdGcYWhjjVUAIVnsu+OT8NJe5Bjzze4xtI1ehzdiuaDu+GyJD3mDDwMUI/eT8/GfDX9DSEaO71yDoGuoiyPcRVnsukDk/7So6otXozhDraiP82WvsnrIJN5Rwfjav7YqYuHdYt/cEomITUNq+KNZPGwazD9OnhEVFQ+2TjsFKZUpi4ajeWP3ncazafQwlilhg5YSBKFXCRhpzwfc+pq/9Q/rvCcsyO/oGd26BoV08oKWlAT//IPxx/ALiE5NgZmQAV2dH/G/B2GwPBSX6GqrO3aq47r99GwOPVr9i7pyJOHN6PzQ1NeDv/xi/dOiLe/fy90s+ANw7fg16poZoOrojDCyMERrwHNs8F0of5mn82bXxud8T/DlyDZqN7Yzm47sgKiQM/xu4FOGPP96q69zEFZ2XfOx4/nVN5g+sZ1YcwNkVBwEAx+fugiAR0HP9aGhoaeDxv/dwePq2fG/fqb/OwsTMGL9NGABzSzM8evgEg7uNlt4SW6SotUxuu3PzPiYOmYHhkwZh5JTBeB78EiN6T8DTRx+nB9i2Zhd0dLUxa8kkGBjqw+/GPQzuOgqpH3IbALhUdsaw8QOgq6eD4KfPMWf8Qhw78PGP9fxy8di/MDI1Qq+xPWFiYYJn/s8wtec06YM3LYtayhw//1sB8Bq+CL3He6LPhN4IDQnFrP5zEBL4XBqzf703tHW1MWrhCOgb6uOB70NM6TkNaZ/kttKVSqPX2J7Q1tXGy6BXWDlpNc4dyv8fcdLvX4FI3whajbtCZGAMyZtgvN8+T/pwTjVjc0g+aZ/kRSCS966AuGk3aDX7FZKoN0j+43dIwj/mbo2y1aDd6eP3Z+3umd+fU8/uQ+q5/VC3KQn1Ek4AAL3x62Tqk7hoMIRY+dMtfY1m5YojJikF6y/6I+pdMkpbGWFd9zrSh3m+iU+S+VGvUnFzLGhfA2t9HmC1zwOUMNXH8s5ucLT8OM3AhcehmHn0pvTfEw9dBwAMqlcWQ9zLIeBNDO6/zjz/W6+VPSdPDG+BosZ6+dY+KpxUnbsvHLsIIzMj9B7XCyYWJgjyf4ZJPadKH1psWdRS5tlA/rf8Mf83L/Sd0Bt9J/bB6+BQzOg/CyGBIdIYtyY1MWH5eOm/p6+fCgDYuWwX/rdsFwBg3ewNECQCZm6aDk0tLdy8eBMrp6xWShsvH7sEQ1MjdB3zK0wsTBDs/wxzes6UTi9iYWMh08bAW4+wfMQSdB/XAz0m9MKbkFAsHDAfLx6/kMZUa1IDI5aNkv573NqJAIC9y/dg3/LMQVDNerRA19EfO6cXHFgEAFg1ZgV8DuRfDrh5/AoMTA3RdnQXGFoY42VACFZ6zs/x77Ygv8fYMnIl2o3thvbjuyMi5A3WDvxd5u+2Sk2qos+SYdJ/D1ozGgBwdMV+HFvhDQBw/7UJ2ozqLI2Z4D0XALB93FpcOXAh39p34sg/MDUzwehJQ2BuaYaAB4Ho3XmY9MGbNsWsZb5f+vnexahBUzB2yjCMm/obQp69wOBeY/D40ce+gY2rd0BHTwcLlk7L/Lv7+h306TJM5rtJxSrlMWriYOjq6eLZkxBMHTsfR7xP5Fu7spw96gMTM2MMHN8XZhamePzwKUb+Ol76sEuropYy7bt/8yGmD5uLwRP7YeikAXgZ/Arj+07Fs8BgaUzdprUxc8Vk6b8XbJgFANi8dDs2L90BAFg+aw0kggQLN8+BllgT1y744vfJy/O9feeO+sDE1Aj9x/WGmYUpnjwMwugeE6UPALayyd6+mb/Nw8AJfTF4Yn+8DH6Nif2m49kn15g6Td0wffnHgTfz1s8AAGxZugNbl2U+w2HlrLUQJAK8Ns2GplgT1y/4YvGUFfnePvp+RIIKfxb477//kJiYiObNm8tdn5iYiJs3b8Ld3V3u+pxcKdIhP6r3w9ojVulvG9/FhtBLqq6CUtno/9xPO/YwLKvqKijViuMDvhxUgInLN8n3MouZlv9yUB69in6Q72XSlykrd2toFc2P6v2wxtrUU3UVlO7E++AvBxVgNlrGqq6CUh3q8XN3xKqXK6PqKiiVTo/5+V4mc/fPQ1m5u1GxpvlRvR+WoZpY1VVQOnO1vD8/oSA59y5/74b70Zhr5f3ZVQWJej7fLfajufra58tBecTc/W1U2ttat27dXNfr6enlOVETEdGPp7DdpvUzY+4mIiocmLt/HszdRESFA3P3t/m5f5YhIiIiIiIiIiIiIsrFzz9vBxERqZyEv2gTEREVKMzdREREBQtz97dhJzkRESmdACZrIiKigoS5m4iIqGBh7v42nG6FiIiIiIiIiIiIiAotjiQnIiKl4wNEiIiIChbmbiIiooKFufvbcCQ5ERERERERERERERVaHElORERKJ+HcaERERAUKczcREVHBwtz9bdhJTkRESsfbvoiIiAoW5m4iIqKChbn723C6FSIiIiIiIiIiIiIqtDiSnIiIlE7CX7SJiIgKFOZuIiKigoW5+9twJDkRERERERERERERFVocSU5ERErHudGIiIgKFuZuIiKigoW5+9uwk5yIiJSOT9kmIiIqWJi7iYiIChbm7m/D6VaIiIiIiIiIiIiIqNDiSHIiIlI63vZFRERUsDB3ExERFSzM3d+GneRERKR0fMo2ERFRwcLcTUREVLAwd38bTrdCRERERERERERERIUWR5ITEZHSCXyACBERUYHC3E1ERFSwMHd/G44kJyIiIiIiIiIiIqJCiyPJiYhI6Tg3GhERUcHC3E1ERFSwMHd/G3aSExGR0vEp20RERAULczcREVHBwtz9bTjdChEREREREREREREVWhxJTkRESscHiBARERUszN1EREQFC3P3t2EnORERKR1v+yIiIipYmLuJiIgKFubub8PpVoiIiIiIiIiIiIio0OJIciIiUjr+ok1ERFSwMHcTEREVLMzd34YjyYmIiIiIiIiIiIio0OJIciIiUjr+nk1ERFSwMHcTEREVLMzd30igb5KcnCzMnDlTSE5OVnVVlOZnbyPbV7CxfUSUV4Xhc/Wzt5HtK9jYPiLKq8LwufrZ28j2FWxsHxUGIkHghDXfIj4+HkZGRoiLi4OhoaGqq6MUP3sb2b6Cje0jorwqDJ+rn72NbF/BxvYRUV4Vhs/Vz95Gtq9gY/uoMOCc5ERERERERERERERUaLGTnIiIiIiIiIiIiIgKLXaSExEREREREREREVGhxU7ybyQWizFz5kyIxWJVV0VpfvY2sn0FG9tHRHlVGD5XP3sb2b6Cje0jorwqDJ+rn72NbF/BxvZRYcAHdxIRERERERERERFRocWR5ERERERERERERERUaLGTnIiIiIiIiIiIiIgKLXaSExEREREREREREVGhxU5yIiIiIiIiIiIiIiq02EmeTxYuXAiRSIRRo0apuir5IiMjA9OnT4e9vT10dHTg4OCAuXPnoqA+5/Xff/9F69atYWNjA5FIhCNHjkjXpaWlYeLEiXBxcYGenh5sbGzQq1cvhIaGqq7CXyG3NmYJCAhAmzZtYGRkBD09PVSrVg0vXrz4/pXNIy8vL1SrVg0GBgawtLREu3btEBgYKBOTnJyMYcOGwczMDPr6+ujQoQPCw8NVVOO8UaR9WQRBQIsWLXI8xkSkOObuHxtzdybm7h8TczeRajB3/9iYuzMxd/+YmLvpS9hJng98fX2xceNGVKhQQdVVyTeLFi3C+vXrsWbNGgQEBGDRokX4/fffsXr1alVX7askJiaiYsWKWLt2bbZ1SUlJ8PPzw/Tp0+Hn54dDhw4hMDAQbdq0UUFNv15ubQSAoKAg1KlTB2XKlMGFCxdw7949TJ8+Hdra2t+5pnl38eJFDBs2DNeuXcOZM2eQlpaGpk2bIjExURozevRoHDt2DN7e3rh48SJCQ0Pxyy+/qLDWilOkfVlWrFgBkUikgloS/VyYu398zN3M3T8y5m6i74+5+8fH3M3c/SNj7qYvEuibJCQkCKVKlRLOnDkjuLu7CyNHjlR1lfKFh4eH0LdvX5llv/zyi/Drr7+qqEb5B4Bw+PDhXGNu3LghABCeP3/+fSqVz+S1sUuXLkKPHj1UU6F8FhERIQAQLl68KAiCIMTGxgqampqCt7e3NCYgIEAAIFy9elVV1fxqn7cvy+3bt4WiRYsKb968Ueg8JiL5mLsLHubugo+5m7mb6Fswdxc8zN0FH3M3c3dhw5Hk32jYsGHw8PBA48aNVV2VfOXm5oZz587h8ePHAIC7d+/i0qVLaNGihYpr9n3ExcVBJBLB2NhY1VXJFxKJBCdOnICTkxOaNWsGS0tL1KhRo8DeNhQXFwcAMDU1BQDcunULaWlpMp/DMmXKoESJErh69apK6vgtPm8fkDnyonv37li7di2sra1VVTWinwJz98+JufvHxtzN3E30LZi7f07M3T825m7m7sJGQ9UVKMj27t0LPz8/+Pr6qroq+W7SpEmIj49HmTJloK6ujoyMDMyfPx+//vqrqqumdMnJyZg4cSK6desGQ0NDVVcnX0RERODdu3dYuHAh5s2bh0WLFuHUqVP45Zdf4OPjA3d3d1VXUWESiQSjRo1C7dq1Ub58eQBAWFgYtLS0sn25srKyQlhYmApq+fXktQ/IvK3Nzc0Nbdu2VWHtiAo+5u6fE3P3j425m7mb6Fswd/+cmLt/bMzdzN2FETvJv9LLly8xcuRInDlzpkDMLZVX+/fvx+7du7Fnzx6UK1cOd+7cwahRo2BjYwNPT09VV09p0tLS0LlzZwiCgPXr16u6OvlGIpEAANq2bYvRo0cDACpVqoQrV65gw4YNBSpZDxs2DA8ePMClS5dUXRWlkNe+o0eP4vz587h9+7YKa0ZU8DF3/5yYu398zN1E9LWYu39OzN0/PuZuKow43cpXunXrFiIiIlClShVoaGhAQ0MDFy9exKpVq6ChoYGMjAxVV/GbjB8/HpMmTULXrl3h4uKCnj17YvTo0fDy8lJ11ZQmK1E/f/4cZ86c+Wl+zQYAc3NzaGhowNnZWWZ52bJlC8RTtrP89ttvOH78OHx8fFCsWDHpcmtra6SmpiI2NlYmPjw8vEDdIpVT+86fP4+goCAYGxtLrzcA0KFDB9SvX19FtSUqeJi7fz7M3T8+5m7mbqJvwdz982Hu/vExdzN3F1YcSf6VGjVqhPv378ss69OnD8qUKYOJEydCXV1dRTXLH0lJSVBTk/0NRV1dXfrL6M8mK1E/efIEPj4+MDMzU3WV8pWWlhaqVauGwMBAmeWPHz+Gra2timqlOEEQMHz4cBw+fBgXLlyAvb29zHpXV1doamri3Llz6NChAwAgMDAQL168QK1atVRR5Tz5UvsmTZqE/v37yyxzcXHB8uXL0bp16+9ZVaICjbn758Lc/WNj7mbuJsoPzN0/F+buHxtzN3N3YcdO8q9kYGAgM28RAOjp6cHMzCzb8oKodevWmD9/PkqUKIFy5crh9u3bWLZsGfr27avqqn2Vd+/e4enTp9J/BwcH486dOzA1NUWRIkXQsWNH+Pn54fjx48jIyJDOp2VqagotLS1VVTtPcmtjiRIlMH78eHTp0gX16tVDgwYNcOrUKRw7dgwXLlxQXaUVNGzYMOzZswd//fUXDAwMpMfHyMgIOjo6MDIyQr9+/TBmzBiYmprC0NAQw4cPR61atVCzZk0V1/7LvtQ+a2trub/MlyhRIltiJ6KcMXcXLMzdzN0/MuZuou+DubtgYe5m7v6RMXfTFwmUb9zd3YWRI0equhr5Ij4+Xhg5cqRQokQJQVtbWyhZsqQwdepUISUlRdVV+yo+Pj4CgGwvT09PITg4WO46AIKPj4+qq66w3NqYZevWrYKjo6Ogra0tVKxYUThy5IjqKpwHOR2f7du3S2Pev38vDB06VDAxMRF0dXWF9u3bC2/evFFdpfNAkfbJ2+bw4cPfrY5EPyvm7h8Xc3cm5u4fE3M3keowd/+4mLszMXf/mJi76UtEgiAIeehTJyIiIiIiIiIiIiL6afDBnURERERERERERERUaLGTnIiIiIiIiIiIiIgKLXaSExEREREREREREVGhxU5yIiIiIiIiIiIiIiq02ElORERERERERERERIUWO8mJiIiIiIiIiIiIqNBiJzkRERERERERERERFVrsJKdCRyQS4ciRIwCAkJAQiEQi3LlzR+Ht69evj1GjRimlboqys7PDihUrVFqHT82aNQuVKlVSdTWIiOgnxdyd/5i7iYhImZi78x9zN5FysZOcVKZ3794QiUQQiUTQ0tKCo6Mj5syZg/T0dFVXLc+ePn2Kvn37okSJEhCLxShatCgaNWqE3bt3Z2uPj48PWrZsCTMzM+jq6sLZ2Rljx47F69evZd4TeS87OzvVNJCIiAjM3czdRERU0DB3M3cTkWLYSU4q1bx5c7x58wZPnjzB2LFjMWvWLCxevDjP5WRkZEAikSihhl9248YNVKlSBQEBAVi7di0ePHiACxcuoH///li/fj0ePnwojd24cSMaN24Ma2trHDx4EP7+/tiwYQPi4uKwdOlSrFy5Em/evJG+AGD79u3Sf/v6+n51PdPS0r65rURERMzdzN1ERFSwMHczdxPRl7GTnFRKLBbD2toatra2GDJkCBo3boyjR49i2bJlcHFxgZ6eHooXL46hQ4fi3bt30u127NgBY2NjHD16FM7OzhCLxXjx4gV8fX3RpEkTmJubw8jICO7u7vDz88tTnR48eIAWLVpAX18fVlZW6NmzJ6KiouTGCoKA3r17w8nJCZcvX0br1q1RqlQplCpVCt26dcOlS5dQoUIFAMCrV68wYsQIjBgxAtu2bUP9+vVhZ2eHevXqYcuWLZgxYwaMjIxgbW0tfQGAsbGx9N8WFhbSfSclJaFv374wMDBAiRIlsGnTJum6rNvZ9u3bB3d3d2hra2P37t0AgC1btqBs2bLQ1tZGmTJlsG7dOpk2TZw4EU5OTtDV1UXJkiUxffr0bIl+4cKFsLKygoGBAfr164fk5GSZ9RcuXED16tWhp6cHY2Nj1K5dG8+fP8/TcSAioh8TczdzNxERFSzM3czdRPRl7CSnH4qOjg5SU1OhpqaGVatW4eHDh9i5cyfOnz+PCRMmyMQmJSVh0aJF2LJlCx4+fAhLS0skJCTA09MTly5dwrVr11CqVCm0bNkSCQkJCu0/NjYWDRs2ROXKlXHz5k2cOnUK4eHh6Ny5s9z4O3fuICAgAOPGjYOamvyPk0gkAgB4e3sjNTU1WzuyGBsbK1THLEuXLkXVqlVx+/ZtDB06FEOGDEFgYKBMzKRJkzBy5EgEBASgWbNm2L17N2bMmIH58+cjICAACxYswPTp07Fz507pNgYGBtixYwf8/f2xcuVKbN68GcuXL5eu379/P2bNmoUFCxbg5s2bKFKkiEzCT09PR7t27eDu7o579+7h6tWrGDhwoPR9ICKinwtzt+KYu4mI6EfA3K045m6iQkQgUhFPT0+hbdu2giAIgkQiEc6cOSOIxWJh3Lhx2WK9vb0FMzMz6b+3b98uABDu3LmT6z4yMjIEAwMD4dixY9JlAITDhw8LgiAIwcHBAgDh9u3bgiAIwty5c4WmTZvKlPHy5UsBgBAYGCgIgiC4u7sLI0eOFARBEPbu3SsAEPz8/KTx4eHhgp6envS1du1aQRAEYciQIYKhoeGX35hPfFrXT9na2go9evSQ/lsikQiWlpbC+vXrZdq1YsUKme0cHByEPXv2yCybO3euUKtWrRzrsHjxYsHV1VX671q1aglDhw6VialRo4ZQsWJFQRAE4e3btwIA4cKFCwq1kYiICg7m7i9j7iYioh8Jc/eXMXcTkSAIgsb3644nyu748ePQ19dHWloaJBIJunfvjlmzZuHs2bPw8vLCo0ePEB8fj/T0dCQnJyMpKQm6uroAAC0tLektVVnCw8Mxbdo0XLhwAREREcjIyEBSUhJevHihUH3u3r0LHx8f6OvrZ1sXFBQEJyenL5ZhZmYmfWp3/fr1kZqaCiDzFrH8/FX307aLRCJYW1sjIiJCJqZq1arS/09MTERQUBD69euHAQMGSJenp6fDyMhI+u99+/Zh1apVCAoKwrt375Ceng5DQ0Pp+oCAAAwePFhmP7Vq1YKPjw8AwNTUFL1790azZs3QpEkTNG7cGJ07d0aRIkXyp+FERKRSzN1fj7mbiIhUgbn76zF3ExUenG6FVKpBgwa4c+cOnjx5gvfv32Pnzp2IjIxEq1atUKFCBRw8eBC3bt3C2rVrAUCa+IDMW8Q+T36enp64c+cOVq5ciStXruDOnTswMzOT2S437969Q+vWrXHnzh2Z15MnT1CvXr1s8aVKlQIAmdut1NXV4ejoCEdHR2hofPwdysnJCXFxcdIHg3wrTU1NmX+LRKJsD1HR09OTaRsAbN68WaZtDx48wLVr1wAAV69exa+//oqWLVvi+PHjuH37NqZOnarw+5dl+/btuHr1Ktzc3LBv3z44OTlJ90FERAUbc/fXY+4mIiJVYO7+eszdRIUHO8lJpfT09ODo6IgSJUpIE9utW7cgkUiwdOlS1KxZE05OTggNDVWovMuXL2PEiBFo2bIlypUrB7FYnOPDP+SpUqUKHj58CDs7O2nCzXp9mviyVK5cGWXKlMGSJUu++JTvjh07QktLC7///rvc9bGxsQrX82tYWVnBxsYGz549y9Y2e3t7AMCVK1dga2uLqVOnomrVqihVqlS2B3+ULVsW169fl1kmLxFXrlwZkydPxpUrV1C+fHns2bNHeY0jIqLvhrn7I+ZuIiIqCJi7P2LuJqKccLoV+uE4OjoiLS0Nq1evRuvWrXH58mVs2LBBoW1LlSqFXbt2oWrVqoiPj8f48eOho6Oj8L6HDRuGzZs3o1u3bpgwYQJMTU3x9OlT7N27F1u2bIG6urpMvEgkwvbt29GkSRPUrl0bkydPRtmyZZGWloZ///0XkZGR0m2KFy+O5cuX47fffkN8fDx69eoFOzs7vHr1Cv/73/+gr6+PpUuXKv5GfYXZs2djxIgRMDIyQvPmzZGSkoKbN28iJiYGY8aMQalSpfDixQvs3bsX1apVw4kTJ3D48GGZMkaOHInevXujatWqqF27Nnbv3o2HDx+iZMmSAIDg4GBs2rQJbdq0gY2NDQIDA/HkyRP06tVLqW0jIiLVYe5WHuZuIiJSBuZu5WHuJiqYOJKcfjgVK1bEsmXLsGjRIpQvXx67d++Gl5eXQttu3boVMTExqFKlCnr27IkRI0bA0tJS4X3b2Njg8uXLyMjIQNOmTeHi4oJRo0bB2Ng4x6do16xZE7du3ULp0qUxbNgwODs7w83NDX/++SeWL1+OIUOGSGOHDh2Kf/75B69fv0b79u1RpkwZ9O/fH4aGhhg3bpzC9fxa/fv3x5YtW7B9+3a4uLjA3d0dO3bskP6i3aZNG4wePRq//fYbKlWqhCtXrmD69OkyZXTp0gXTp0/HhAkT4OrqiufPn8u0UVdXF48ePUKHDh3g5OSEgQMHYtiwYRg0aJDS20dERKrB3K08zN1ERKQMzN3Kw9xNVDCJBEEQVF0JIiIiIiIiIiIiIiJV4EhyIiIiIiIiIiIiIiq02ElORERERERERERERIUWO8mJiIiIiIiIiIiIqNBiJzkRERERERERERERFVrsJCciIiIiIiIiIiKiQoud5ERERERERERERERUaLGTnIiIiIiIiIiIiIgKLXaSExEREREREREREVGhxU5yIiIiIiIiIiIiIiq02ElORERERERERERERIUWO8mJiIiIiIiIiIiIqNBiJzkRERERERERERERFVrsJCciIiIiIiIiIiKiQoud5ERERERERERERERUaLGTnIiIiIiIiIiIiIgKLXaSExEREREREREREVGhxU5yIiIiIiIiIiIiIiq02ElORERERERERERERIUWO8lJLjs7O7Rq1SrfygsPD0fHjh1hZmYGkUiEFStWYMeOHRCJRLh582a+7aews7OzQ+/evVVdDaUTiUSYNWuWqqtBRPRDYe4umOrXr4/69euruhpKV1i+oxARERFRwcRO8p/Ynj17sGLFClVXAwAwevRonD59GpMnT8auXbvQvHlzldRj/vz5aNOmDaysrBTqaN23bx9q1aoFPT09GBsbw83NDefPn/8+laXvyt/fH7NmzUJISMhXl/EjfeaIqGD6ka4jP0LuDg0NRY8ePVC6dGkYGBjA2NgY1atXx86dOyEIgkzsoUOH0KVLF5QsWRK6urooXbo0xo4di9jY2O9eb/o+QkNDMWvWLNy5c+ery/j777/5wzsRERERsZP8Z/Yj/aF9/vx5tG3bFuPGjUOPHj1QpkwZldRj2rRp8PX1ReXKlb8YO2vWLHTr1g3FixfHsmXLMG/ePFSoUAGvX7/+DjWl783f3x+zZ89mJzkRqdSPdB35EXJ3VFQUXr16hY4dO2LJkiWYN28eihQpgt69e2Pq1KkysQMHDkRAQAB69OiBVatWoXnz5lizZg1q1aqF9+/ff/e6k/KFhoZi9uzZ39xJPnv27PyrFBEREREVSBqqrsCPThAEJCcnQ0dHR9VVKdAiIiJgbGys6mogODgYdnZ2iIqKgoWFRY5x165dw5w5c7B06VKMHj06X+vAc4qISLl4nc0fP0LurlChAi5cuCCz7LfffkPr1q2xatUqzJ07F+rq6gCAAwcOZJu2xNXVFZ6enti9ezf69+//TXVJSkqCrq7uN5VBREREREQ/pgI/knzWrFkQiUR4+vQpevfuDWNjYxgZGaFPnz5ISkqSxqWnp2Pu3LlwcHCAWCyGnZ0dpkyZgpSUFJnysubzPH36NKpWrQodHR1s3LgRFy5cgEgkwv79+zF79mwULVoUBgYG6NixI+Li4pCSkoJRo0bB0tIS+vr66NOnT7ayFfHo0SN07NgRpqam0NbWRtWqVXH06FHp+oiICFhYWKB+/foytxk/ffoUenp66NKlC4DM+S1PnDiB58+fQyQSQSQSwc7OLs/1+dTOnTuhoaGB8ePHAwCio6Mxbtw4uLi4QF9fH4aGhmjRogXu3r0r3SZr7lJBELB27VppXXISExOD6tWro1ixYggMDAQA/PXXX/Dw8ICNjQ3EYjEcHBwwd+5cZGRk5LkNir4HK1asgLW1NUaOHAlBEPDu3bs87+vTfco7pwAgNjYWo0aNQvHixSEWi+Ho6IhFixZBIpHIlLFkyRK4ubnBzMwMOjo6cHV1xYEDB766Tp86c+YM6tSpA2NjY+jr66N06dKYMmWKdH1qaipmzJgBV1dXGBkZQU9PD3Xr1oWPj480Ji0tDaampujTp0+28uPj46GtrY1x48ZJl6WkpGDmzJlwdHSEWCxG8eLFMWHChGyfmZSUFIwePRoWFhYwMDBAmzZt8OrVq69q5969e+Hq6goDAwMYGhrCxcUFK1euBJB5nnbq1AkA0KBBA+l5mtUxo8g5+KXPnKJt/tLxyM0ff/yB6tWrQ1dXFyYmJqhXrx7++ecf6fqbN2+iWbNmMDc3h46ODuzt7dG3b18AeT+GRN+CuTsTc/fXs7OzQ1JSElJTU6XL5M3r3b59ewBAQEBAnsqvX78+ypcvj1u3bqFevXrQ1dWVXosVvZ5v374dDRs2hKWlJcRiMZydnbF+/fo8tlS+3K7nWRT57lC+fHk0aNAgW/kSiQRFixZFx44dZZatWLEC5cqVg7a2NqysrDBo0CDExMTIbCsIAubNm4dixYpBV1cXDRo0wMOHD7+qnbnlxAsXLqBatWoAgD59+kjP0x07dgAA/vvvP3Tq1AklSpSQHqfRo0fL3FXQu3dvrF27FgCk2396rivaZkWOR05OnjwJd3d36feTatWqYc+ePdL1T548QYcOHWBtbQ1tbW0UK1YMXbt2RVxcHIC8HUMiIiIiytlPM5K8c+fOsLe3h5eXF/z8/LBlyxZYWlpi0aJFAID+/ftj586d6NixI8aOHYvr16/Dy8sLAQEBOHz4sExZgYGB6NatGwYNGoQBAwagdOnS0nVeXl7Q0dHBpEmT8PTpU6xevRqamppQU1NDTEwMZs2ahWvXrmHHjh2wt7fHjBkzFG7Dw4cPUbt2bRQtWhSTJk2Cnp4e9u/fj3bt2uHgwYNo3749LC0tsX79enTq1AmrV6/GiBEjIJFI0Lt3bxgYGGDdunUAgKlTpyIuLg6vXr3C8uXLAQD6+vpf/f5u2rQJgwcPxpQpUzBv3jwAwLNnz3DkyBF06tQJ9vb2CA8Px8aNG+Hu7g5/f3/Y2NigXr162LVrF3r27IkmTZqgV69eOe4jKioKTZo0QXR0NC5evAgHBwcAmX+s6+vrY8yYMdDX18f58+cxY8YMxMfHY/HixV/dptycO3cObm5uWLVqFebNm4e3b9/C2toaU6dOxW+//Zbn8uSdU0lJSXB3d8fr168xaNAglChRAleuXMHkyZPx5s0bmdvtV65ciTZt2uDXX39Famoq9u7di06dOuH48ePw8PD46nY+fPgQrVq1QoUKFTBnzhyIxWI8ffoUly9flsbEx8djy5Yt6NatGwYMGICEhARs3boVzZo1w40bN1CpUiVoamqiffv2OHToEDZu3AgtLS3p9keOHEFKSgq6du0KIPOPtjZt2uDSpUsYOHAgypYti/v372P58uV4/Pgxjhw5It22f//++OOPP9C9e3fpfPBf094zZ86gW7duaNSokfSaEBAQgMuXL2PkyJGoV68eRowYgVWrVmHKlCkoW7YsAEj/q8g5mNtnTtE2K3I8cjJ79mzMmjULbm5umDNnDrS0tHD9+nWcP38eTZs2RUREBJo2bQoLCwtMmjQJxsbGCAkJwaFDhwAgT8eQKL8wdzN3K+r9+/dITEzEu3fvcPHiRWzfvh21atX64t0CYWFhAABzc/M87/Pt27do0aIFunbtih49esDKyipPOWz9+vUoV64c2rRpAw0NDRw7dgxDhw6FRCLBsGHD8lyfLF+6nmdR5LtDly5dMGvWLISFhcHa2lq67aVLlxAaGipz3R80aBB27NiBPn36YMSIEQgODsaaNWtw+/ZtXL58GZqamgCAGTNmYN68eWjZsiVatmwJPz8/NG3aVOYHDUV8KSeWLVsWc+bMwYwZMzBw4EDUrVsXAODm5gYA8Pb2RlJSEoYMGQIzMzPcuHEDq1evxqtXr+Dt7S1tU2hoKM6cOYNdu3Zlq4MibVb0eMizY8cO9O3bF+XKlcPkyZNhbGyM27dv49SpU+jevTtSU1PRrFkzpKSkYPjw4bC2tsbr169x/PhxxMbGwsjIKE/HkIiIiIhyIRRwM2fOFAAIffv2lVnevn17wczMTBAEQbhz544AQOjfv79MzLhx4wQAwvnz56XLbG1tBQDCqVOnZGJ9fHwEAEL58uWF1NRU6fJu3boJIpFIaNGihUx8rVq1BFtb2zy1pVGjRoKLi4uQnJwsXSaRSAQ3NzehVKlSMrHdunUTdHV1hcePHwuLFy8WAAhHjhyRifHw8MhzHbLY2toKHh4egiAIwsqVKwWRSCTMnTtXJiY5OVnIyMiQWRYcHCyIxWJhzpw5MssBCMOGDZNZtn37dgGA4OvrK7x580YoV66cULJkSSEkJEQmLikpKVv9Bg0aJOjq6sq8V3kRGRkpABBmzpyZbV10dLQAQDAzMxP09fWFxYsXC/v27ROaN28uABA2bNiQp33ldE7NnTtX0NPTEx4/fiyzfNKkSYK6urrw4sUL6bLP34PU1FShfPnyQsOGDbPty9PTU+G6LV++XAAgREZG5hiTnp4upKSkyCyLiYkRrKysZD53p0+fFgAIx44dk4lt2bKlULJkSem/d+3aJaipqQn//fefTNyGDRsEAMLly5cFQfj4uR06dKhMXPfu3XM8djkZOXKkYGhoKKSnp+cY4+3tLQAQfHx8sq1T9BzM6TOnaJsVOR7yPHnyRFBTUxPat2+f7TMpkUgEQRCEw4cPSz9vOVH0GBJ9K+Zu5u688vLyEgBIX40aNZLJkznp16+foK6uni3Xfom7u7vcnK/o9VwQ5L8HzZo1y3Y9dXd3F9zd3RWumyLXc3n7l/fdITAwUAAgrF69WiZ26NChgr6+vrSM//77TwAg7N69Wybu1KlTMssjIiIELS0twcPDQ5p/BEEQpkyZIgDI9+8ovr6+AgBh+/bt2dbJe/+9vLwEkUgkPH/+XLps2LBhgrw/iRRts6LH43OxsbGCgYGBUKNGDeH9+/cy67Leu9u3bwsABG9v7xzLUfQYEhEREVHuCvx0K1kGDx4s8++6devi7du3iI+Px99//w0AGDNmjEzM2LFjAQAnTpyQWW5vb49mzZrJ3U+vXr2kI2UAoEaNGhAEIdstlTVq1MDLly+Rnp6uUP2jo6Nx/vx5dO7cGQkJCYiKikJUVBTevn2LZs2a4cmTJzIPjFyzZg2MjIzQsWNHTJ8+HT179kTbtm0V2lde/P777xg5ciQWLVqEadOmyawTi8VQU8s8hTIyMvD27VvprbB+fn4K7+PVq1dwd3dHWloa/v33X9ja2sqs/3SUWNZ7U7duXSQlJeHRo0ff0Dr5sqZWefv2LbZs2YJx48ahc+fOOHHiBJydnaWj8fJC3jnl7e2NunXrwsTERHq8o6Ki0LhxY2RkZODff/+Vxn76HsTExCAuLg5169bN0/ssT9Zcs3/99Ve2KV6yqKurS0cVSyQSREdHIz09HVWrVpXZf8OGDWFubo59+/bJ1PXMmTPSqQSy2l22bFmUKVNGpt0NGzYEAOk0Llmf2xEjRsjUZ9SoUV/VzsTERJw5cybP2wLffg4q2mZFjoc8R44cgUQiwYwZM6SfySxZt41nlX38+HGkpaXJLUfRY0iUX5i7mbsV1a1bN5w5cwZ79uxB9+7dAeCLD+Pcs2cPtm7dirFjx6JUqVJ53qdYLM42BZWi13NA9j2Ii4tDVFQU3N3d8ezZM+lUGV9Dkev55/vP6buDk5MTKlWqJHPdz8jIwIEDB9C6dWtpGd7e3jAyMkKTJk1k2u3q6gp9fX1pu8+ePYvU1FQMHz5cZtqSr83dQN5zYpZP25+YmIioqCi4ublBEATcvn37i9sr2mZFj8fnzpw5g4SEBEyaNAna2toy67LeOyMjIwDA6dOnZaai+pSix5CIiIiIvkDFnfTfLGs0WlhYmMzyrJFOISEhwqBBgwQ1NTWZUWRZjI2NhY4dO0r/bWtrm210riB8HI22d+9eufu5du2a3HpFRUUp1I7r16/LjJCS9/Lz85PZJmvkq5WVlRATE5OtzG8djaavry8AECZOnCg3JiMjQ1i2bJng6OgoqKury9S1QYMGMrHIZTSavr6+YGxsLLx580bufh48eCC0a9dOMDQ0zPaeXLx48aval9tI8qx1mpqa2UYez549WwAgMwLpS3I6p3R0dHI93suWLZPGHjt2TKhRo4YgFotlYkQiUbZ95WWUVlJSklC7dm0BgGBubi506dJF2LdvX7ZRhjt27BBcXFwETU1Nmf3b29vLxA0aNEgwMDCQjhLcsmWLAEC4c+eONKZs2bK5tnvEiBHSstTU1IS0tDSZfcTFxeV5JHl4eLh0v0WLFhX69OkjnDx5UiYmt5Hkip6DOX3mFG2zosfjc4MHDxbU1NSyjfj/lEQiETp06CAAEAwNDYU2bdoI27ZtyzaiU5FjSPStmLuZu7/VgAEDhOLFi+c4Svbff/8VtLW1hWbNmmXLI4pwd3eXeweNotdzQRCES5cuCY0aNRJ0dXWzxX36PSKvI8kVvZ4r+t0ha3T1q1evBEEQhLNnzwr47C6HFi1a5NruNm3aSMsCIAQFBWWrt4mJSb5/R8ltJPnz588FT09PwcTEJFt9d+7cKY3LaSS5om1W9Hh8buHChQIA4cmTJ7nGjRkzRgAg6OjoCE2bNhXWrFkjxMbGysQocgyJiIiIKHc/zZzk6urqcpcLnzwgK7eHTn0qtxEXOe1Hkf3nJmuEzLhx43IcCefo6Cjz79OnTwPIHB306tUr6UiW/FKuXDnExsZi165dGDRoEOzt7WXWL1iwANOnT0ffvn0xd+5cmJqaQk1NDaNGjcrTiJ9ffvkF//vf/7By5Up4eXnJrIuNjYW7uzsMDQ0xZ84cODg4QFtbG35+fpg4ceJXjSz6kqwHrxkbG2c7rpaWlgAy3/MSJUooXKa8c0oikaBJkyaYMGGC3G2cnJwAZD54qk2bNqhXrx7WrVuHIkWKQFNTE9u3b5d5sNPX0NHRwb///gsfHx+cOHECp06dwr59+9CwYUP8888/UFdXxx9//IHevXujXbt2GD9+PCwtLaGurg4vLy8EBQXJlNe1a1ds3LgRJ0+eRLt27bB//36UKVMGFStWlGm3i4sLli1bJrdOxYsX/6Y2yWNpaYk7d+7g9OnTOHnyJE6ePInt27ejV69e2LlzZ67b5sc5qGibFTkeX0skEuHAgQO4du0ajh07htOnT6Nv375YunQprl27Jp33WJFjSJRfmLuZu79Wx44dsXnzZvz777/Z3vu7d++iTZs2KF++PA4cOAANja/7uptT7lbkeh4UFIRGjRqhTJkyWLZsGYoXLw4tLS38/fffWL58+Te9B4pcz/Py3aFLly6YPHkyvL29MWrUKOzfvx9GRkZo3ry5TLstLS2xe/duuXWysLD46vbk5FtyYkZGhnSu/IkTJ6JMmTLQ09PD69ev0bt3b4VztyJtVjS/fq2lS5eid+/e+Ouvv/DPP/9gxIgR8PLywrVr11CsWDEAih1DIiIiIsrdT9NJnhtbW1tIJBI8efJE+iA+AAgPD0dsbGy2W4RVoWTJkgAyH57XuHHjL8afOnUKW7ZswYQJE7B79254enri+vXrMn8IKtqxkBNzc3McOHAAderUQaNGjXDp0iXY2NhI1x84cAANGjTA1q1bZbaLjY3N0wOyhg8fDkdHR8yYMQNGRkaYNGmSdN2FCxfw9u1bHDp0CPXq1ZMuDw4O/oaW5U5NTQ2VKlWCr68vUlNTZR5gGBoaCiB//hh0cHDAu3fvvni8Dx48CG1tbZw+fRpisVi6fPv27d9cByCzvY0aNUKjRo2wbNkyLFiwAFOnToWPjw8aN26MAwcOoGTJkjh06JDMOTVz5sxsZdWrVw9FihTBvn37UKdOHZw/fx5Tp06ViXFwcMDdu3fRqFGjXM/RrM9tUFCQzAP4AgMDv6qdWlpaaN26NVq3bg2JRIKhQ4di48aNmD59OhwdHXOsS17OwZzKULTNwJePR07lSyQS+Pv7o1KlSrmWX7NmTdSsWRPz58/Hnj178Ouvv2Lv3r3o378/AMWOIdH3wNz9dQpL7s6aauXzaUuCgoLQvHlzWFpa4u+///7mDsrPKXo9P3bsGFJSUnD06FGZH9U/nY7lW+V2Pc/Ldwd7e3tUr14d+/btw2+//YZDhw6hXbt2Mts5ODjg7NmzqF27dq4/SGV9Lp88eSL9fABAZGQkYmJi8tzGL+XEnI7B/fv38fjxY+zcuVPmwbPypl3LLXcr0uYsX8qv8soHgAcPHmT7Me1zLi4ucHFxwbRp03DlyhXUrl0bGzZskE4BqMgxJCIiIqLc/TRzkuemZcuWAIAVK1bILM8aBeTh4fG9q5SNpaUl6tevj40bN+LNmzfZ1kdGRkr/PzY2Fv3790f16tWxYMECbNmyBX5+fliwYIHMNnp6et805yUAFCtWDGfPnsX79+/RpEkTvH37VrpOXV0922g7b29vmflXFTV9+nSMGzcOkydPxvr162X2AciO6ktNTcW6devyvI+86NKlCzIyMmRGGScnJ2P37t1wdnaW6XD4Wp07d8bVq1elowo/FRsbK50TV11dHSKRCBkZGdL1ISEhOHLkyDfXITo6OtuyrE7WlJQU6f4B2WNw/fp1XL16Ndu2ampq6NixI44dO4Zdu3YhPT0921zWnTt3xuvXr7F58+Zs279//x6JiYkAgBYtWgAAVq1aJRPz+edYEZ+et1n1rFChAoCP7dTT0wOQ+d5/Ki/nYE6fOUXbrMjxAIBHjx7hxYsX0n+3a9cOampqmDNnTrbRcVn1jomJyfZ5lVe2IseQ6Htg7v56P1Pu/vQ9/NTWrVshEolQpUoV6bKwsDA0bdoUampqOH36tFJGNyt6PZf3HsTFxeXLD9yKXM/z+t2hS5cuuHbtGrZt24aoqCi5uTsjIwNz587Ntm16ero0dzZu3BiamppYvXq1TB2/JncrkhPzkrsFQcDKlSuzlZlTGYq2WdH8GhQUJHMHXtOmTWFgYAAvLy8kJyfLbJ9VXnx8fLZnJLi4uEBNTU2mbODLx5CIiIiIclcoRpJXrFgRnp6e2LRpk/QW4Bs3bmDnzp1o164dGjRooOoqAgDWrl2LOnXqwMXFBQMGDEDJkiURHh6Oq1ev4tWrV7h79y4AYOTIkXj79i3Onj0LdXV1NG/eHP3798e8efPQtm1b6bQIrq6u2LdvH8aMGYNq1apBX18frVu3znO9HB0d8c8//6B+/fpo1qwZzp8/D0NDQ7Rq1Qpz5sxBnz594Obmhvv372P37t0yI4fyYvHixYiLi8OwYcNgYGCAHj16wM3NDSYmJvD09MSIESMgEomwa9cuhW+F/9yuXbvw/Plz6cOP/v33X+konJ49e0pHQA0aNAhbtmzBsGHD8PjxY5QoUUK67bFjx75q358bP348jh49ilatWqF3795wdXVFYmIi7t+/jwMHDiAkJATm5ubw8PDAsmXL0Lx5c3Tv3h0RERFYu3YtHB0dce/evW+qw5w5c/Dvv//Cw8MDtra2iIiIwLp161CsWDHUqVMHANCqVSscOnQI7du3h4eHB4KDg7FhwwY4OztLH3L6qS5dumD16tWYOXMmXFxcZEaAApnv8/79+zF48GD4+Pigdu3ayMjIwKNHj7B//36cPn0aVatWRaVKldCtWzesW7cOcXFxcHNzw7lz5/D06dM8t7N///6Ijo5Gw4YNUaxYMTx//hyrV69GpUqVpPWrVKkS1NXVsWjRIsTFxUEsFqNhw4Z5Ogdz+swp2mZFjgcAlC1bFu7u7rhw4QKAzM/o1KlTMXfuXNStWxe//PILxGIxfH19YWNjAy8vL+zcuRPr1q1D+/bt4eDggISEBGzevBmGhobSzkhFjyHR98DczdwNAPPnz8fly5fRvHlzlChRAtHR0Th48CB8fX2lo9mzNG/eHM+ePcOECRNw6dIlXLp0SbrOysoKTZo0+ao2fkrR63nTpk2ldzANGjQI7969w+bNm2FpaSn3B5W8UOR6ntfvDp07d8a4ceMwbtw4mJqaZrszwt3dHYMGDYKXlxfu3LmDpk2bQlNTE0+ePIG3tzdWrlyJjh07wsLCAuPGjYOXlxdatWqFli1b4vbt2zh58mSe7lQAFPuO4uDgAGNjY2zYsAEGBgbQ09NDjRo1UKZMGTg4OGDcuHF4/fo1DA0NcfDgQbmj2V1dXQFkPii8WbNmUFdXR9euXRVus6L5tVGjRgAyf6wAAENDQyxfvhz9+/dHtWrV0L17d5iYmODu3btISkrCzp07cf78efz222/o1KkTnJyckJ6ejl27dkFdXR0dOnTI0zEkIiIioi/4nhOgK0PWQ7YiIyNllmc9WCo4OFgQBEFIS0sTZs+eLdjb2wuamppC8eLFhcmTJ2d7qI6tra3g4eGRbT9ZD//y9vaWux9fX1+F6vUlQUFBQq9evQRra2tBU1NTKFq0qNCqVSvhwIEDgiAIwl9//SUAEJYuXSqzXXx8vGBraytUrFhR+pCzd+/eCd27dxeMjY0FAHl6EJi89+H69euCgYGBUK9ePSEpKUlITk4Wxo4dKxQpUkTQ0dERateuLVy9elXuA6iQy8O/Pn3vMjIyhG7dugkaGhrShw1dvnxZqFmzpqCjoyPY2NgIEyZMEE6fPi0gh4cs5sbd3T3HBzB9XlZ4eLjg6ekpmJqaCmKxWKhRo4Zw6tSpPO1PEHI+pwRBEBISEoTJkycLjo6OgpaWlmBubi64ubkJS5YskXlY3datW4VSpUoJYrFYKFOmjLB9+3bpOfb5vvLyUKxz584Jbdu2FWxsbAQtLS3BxsZG6Natm/D48WNpjEQiERYsWCDY2toKYrFYqFy5snD8+HHB09NT7jklkUiE4sWLCwCEefPmyd1vamqqsGjRIqFcuXKCWCwWTExMBFdXV2H27NlCXFycNO79+/fCiBEjBDMzM0FPT09o3bq18PLlSwF5fHDngQMHhKZNmwqWlpaClpaWUKJECWHQoEHZHji3efNmoWTJktKH2WWdE4qeg7l95hRpsyLHQxAyP0/yHvK2bds2oXLlytLy3d3dhTNnzgiCIAh+fn5Ct27dhBIlSghisViwtLQUWrVqJdy8eTNbOYocQ6Jvwdydibn7y/755x+hVatWgo2NjaCpqSkYGBgItWvXFrZv3y5IJJJs9c3plZcHYwpC5veFcuXKyV2naA47evSoUKFCBUFbW1uws7MTFi1aJGzbtk3mHM/aV17qp+j1XNHvDlmyHpLZv3//HPe9adMmwdXVVdDR0REMDAwEFxcXYcKECUJoaKg0JiMjQ5g9e7b0HKtfv77w4MEDpXxHEYTMz5ezs7OgoaEh8xBPf39/oXHjxoK+vr5gbm4uDBgwQLh79262B32mp6cLw4cPFywsLASRSJTt/flSmxU9Hra2tnI/z0ePHhXc3NwEHR0dwdDQUKhevbrw559/CoIgCM+ePRP69u0rODg4CNra2oKpqanQoEED4ezZs3LfM0WOIRERERHJJxKErxySS0RERERERERERERUwBWKOcmJiIiIiIiIiIiIiOQpFHOSq1pcXBzev3+fa4y1tfV3qUtkZKTMQ5w+p6WlBVNT0+9Sl/zy/v37Lz7kzNTUFFpaWvm63x/9vQwLC8t1vY6ODoyMjL5TbZQjIyMjx4e6ZdHX14e+vv53qhER/SyYu5VLVbk7OjoaqampOa5XV1dXygM/FfUzHmt5CsN3FCIiIiIqWDjdynfQu3dv7Ny5M9eY73UY7Ozs8Pz58xzXf/owwIJix44d6NOnT64xPj4+qF+/fr7u90d/L0UiUa7rPT09sWPHju9TGSUJCQmBvb19rjEzZ87ErFmzvk+FiOinwdytXKrK3fXr18fFixdzXG9rayt9sKIq/IzHWp7C8B2FiIiIiAoWdpJ/B/7+/ggNDc015ns9gf7y5cu5jowzMTGBq6vrd6lLfnnz5g0ePnyYa4yrqytMTEzydb8/+nt59uzZXNfb2NjA2dn5O9VGOZKTk3Hp0qVcY0qWLImSJUt+pxoR0c+CuVu5VJW7b926hZiYmBzX6+jooHbt2vm6z7z4GY+1PIXhOwoRERERFSzsJCciIiIiIiIiIiKiQosP7iQiIiIiIiIiIiKiQoud5ERERERERERERERUaGmougLKoKNjq+oqKJWbWWlVV0Hpymnk7xykP5pHGXGqroJSvZekqboKSqX+hQeOFXQXXuU+V+zXSIt6lu9lappzrvmfiW/R9qquglJdVNdTdRWUrmxKhqqroFTO1lGqroJSaRukq7oKSmW2f42qq6BUWjbl8r1M5m4iIiIqTH7KTnIiIvrBSH7uzjMiIqKfDnM3ERERFSKcboWIiIiIiIh+OGvXroWdnR20tbVRo0YN3LhxI9d4b29vlClTBtra2nBxccHff/8ts/7QoUNo2rQpzMzMIBKJcOfOnWxlDBo0CA4ODtDR0YGFhQXatm2LR48e5WeziIiI6AfETnIiIlI+QZL/LyIiIlIeFefuffv2YcyYMZg5cyb8/PxQsWJFNGvWDBEREXLjr1y5gm7duqFfv364ffs22rVrh3bt2uHBgwfSmMTERNSpUweLFi3Kcb+urq7Yvn07AgICcPr0aQiCgKZNmyIjgyPriYiIfmYiQRAEVVciv3FO8oKPc5IXbJyTvGBTypzk4YH5Xqam1c9/LSxMOCd5wcc5yQs2zklesCllTnIV5+4aNWqgWrVqWLMm89hJJBIUL14cw4cPx6RJk7LFd+nSBYmJiTh+/Lh0Wc2aNVGpUiVs2LBBJjYkJAT29va4ffs2KlWqlGs97t27h4oVK+Lp06dwcHBQuP5ERERUsHAkORERKZ9Ekv8vIiIiUh4V5u7U1FTcunULjRs3li5TU1ND48aNcfXqVbnbXL16VSYeAJo1a5ZjvCISExOxfft22Nvbo3jx4l9dDhEREf34+OBOIiJSOoHToxARERUoysjdKSkpSElJkVkmFoshFotllkVFRSEjIwNWVlYyy62srHKcHzwsLExufFhYWJ7ruW7dOkyYMAGJiYkoXbo0zpw5Ay0trTyXQ0RERAUHR5ITERERERGR0nl5ecHIyEjm5eXlpepqZfPrr7/i9u3buHjxIpycnNC5c2ckJyerulpERESkRBxJTkREysfpUYiIiAoWJeTuyZMnY8yYMTLLPh9FDgDm5uZQV1dHeHi4zPLw8HBYW1vLLdva2jpP8bnJ6sAvVaoUatasCRMTExw+fBjdunXLc1lERERUMHAkORERKZ8gyf8XERERKY8ScrdYLIahoaHMS14nuZaWFlxdXXHu3DnpMolEgnPnzqFWrVpyq1urVi2ZeAA4c+ZMjvEKvw2CAEEQsk0TQ0RERD8XjiQnIiIiIiKiH8qYMWPg6emJqlWronr16lixYgUSExPRp08fAECvXr1QtGhR6XQtI0eOhLu7O5YuXQoPDw/s3bsXN2/exKZNm6RlRkdH48WLFwgNDQUABAYGAsgchW5tbY1nz55h3759aNq0KSwsLPDq1SssXLgQOjo6aNmy5Xd+B4iIiOh7Yic5EREpnyRD1TUgIiKivFBx7u7SpQsiIyMxY8YMhIWFoVKlSjh16pT04ZwvXryAmtrHG6Pd3NywZ88eTJs2DVOmTEGpUqVw5MgRlC9fXhpz9OhRaSc7AHTt2hUAMHPmTMyaNQva2tr477//sGLFCsTExMDKygr16tXDlStXYGlp+Z1aTkRERKogEgRBUHUl8puOjq2qq6BUbmalVV0FpSunYaLqKijVo4w4VVdBqd5L0lRdBaVSF4lUXQWluvDqbL6XmfrcL9/L1LKtku9lkur4Fm2v6ioo1UV1PVVXQenKpvzcP4Y5W0epugpKpW2QruoqKJXZ/jWqroJSadmUy/cymbuJiIioMOFIciIiUj7OIU5ERFSwMHcTERFRIcJOciIiUj4J/9AmIiIqUJi7iYiIqBBR+3IIEREREREREREREdHPiSPJiYhI6QTesk1ERFSgMHcTERFRYcKR5ERERERERERERERUaHEkORERKR/nNSUiIipYmLuJiIioEGEnORERKR9v2SYiIipYmLuJiIioEOF0K0RERERERERERERUaHEkORERKZ8kQ9U1ICIiorxg7iYiIqJChJ3kRESkfLxlm4iIqGBh7iYiIqJChNOtEBEREREREREREVGhxZHkRESkfBKORiMiIipQmLuJiIioEOFIciIiIiIiIiIiIiIqtDiSnIiIlI/zmhIRERUszN1ERERUiLCTnIiIlI+3bBMRERUszN1ERERUiBT6TvJBg3ph9OiBsLKywP37ARgzZiZu3rybY/wvv7TEjBljYWtbDE+fhmDatIU4fdpHJmb69DHo06cbjI0NcfXqTYwYMRVBQSHS9ZUqlce8eZPg6loBGRkSHDlyEhMnzkViYpJS2tjWszU6D+4EUwtTBAU8w+rpaxF4JzDH+HoeddFnfG9YF7PCq5DX2LxgC26c95Wur9OiNlr3aAWnCqVgaGKIgU0HI8j/mUwZHr+2RMN2DVCqvCP0DPTQxrk9EuMTldK+uj2bouGg1jC0MMbrgOc4MHM7XtwNyjG+Usua8BjbGabFLBAZHIajC3fD/8Id6foKzaqjzq+NUdylJPRMDLCo5QS89n8uU0aXBQNQunZ5GFqZIjUxGcF+gfhr4R5EBIXme/tae7ZGp0EdYWphgmcBz7B2xjoE3nmcY3xdj7roPa4XrIpZ4XXIa2xZsA2+Ph+PX+3mtdGqZ0uUcsk8foObDcWzz45fy+4t0KBdAziWd4CegR7al+ugtOPX3rMtug3pnHl++gdhxfTVCMjl/Kzfqh76j+8D62LWeBX8ChsWbMa18zek6+u1qIO2PVujdAUnGJkYok/TgXj6UPZ8aP2rB5q0awgnl1LQM9BDi7Jt8E5J7Wvn2QZdB2e272lAEFZNX4NHubTP3aMe+o3vndm+kNfYuGAzrn/Svrot6qBNj1Zw+tC+/k0H4am/bPta/eqBxu0aSj9/rZzbKq19RKpg6dkC1kPaQdPCGEn+IXgxfQsS7zzJMd6klRuKju8GcTFLJAe/wasF/0Pceb+P61vUhEXPZtCr4AANEwM8aDoa7x+GyJQhEmui+Iw+MGtbByItDcRduIPnUzYiPSpOKW2s1Ksxqg3ygJ6FESIDXuDcjP8h7O6zHOOdPKqj9tiOMCpmjpiQcPzrtRfBPh+/z5RqXhUVezSClYsddEwMsLP5FET6v5ApQ12sifrTuqNMm5pQ19JEyMV7ODttB5Ki4vO9fbZ9mqDk0NYQWxoh3v8FHk7ZgbjbOedu69Y1UHpiJ+gUt0BicBgezf0TkefufFzfshpKeDaGUQV7aJka4L+GkxD/UDZ3q4k1UXZWD9i0qwU1sSYife7iwaTtSI3M/2No0KUNjDw7Qd3cFKmPg/B24VqkPsj52q/bpB5MhnlCw8Ya6S9eI3rFFry/9PHar9uoDgw7tYJW2VJQNzbE686DkRoo+34ZdGgJvRYNIS7rCDV9PTyv0w6SBOVc+3V/aQe9bl2gbmqKtKAgxC9fhbSARznGazdwh0H/vlC3tkb6q1dIWL8JKdeuf1xfry5027WGZmknqBkZIbJ3f6Q/lW2fTptW0GnSCJpOpaCmp4ew5q0gvFNO+/48fBI79h1BVHQsSjvYYfKI/nApWyrH+NMXrmDNtj8RGhaBEsWKYPTAnqhX01W6/uy/17D/2Gn4Pw5CXPw7eG9eijKO9jJlzF66Htf87iEyKga6OtqoWK40Rg/qiZIliimljUREREQkS6Vzkr969QpRUVHSf//333/49ddfUbduXfTo0QNXr15V6v47dmyFRYumYf78lahVqxXu3QvA0aO7YGFhJje+Zk1X7Ny5Gjt37kfNmh44duwf7N+/Cc7OTtKYsWMHY+jQ3hgxYgrq1WuLxMQkHDu2C2KxGABQpIglTpzYjaCgENSr1w5t2/aCs7MTNm9eqpQ21m/tjsEzBuF/y//A4BZDEeT/DIv+WABjM2O58c6uzpi2dgpO7j2FQc2H4PKpK5izZRbsSttJY7R1tfHA9wE2L9iS437F2mL4XriJPWv25nOLZFVuVQvtp/XCqZUHsdhjEl77P8fQ/02Bvpmh3Hj7Kk7wXDUCV/f54PeWk3DvH1/03zQeRZyKf6y7rhjPbgbi6MI9Oe735f1n2D1+AxY0HoN1vRYAEGHo/6ZCpCbK1/a5t66HQdMH4I8Vf2Boy9/wzP8ZFuyaD2MzI7nxzq5lMWXNJJzaexpDWgzDldNXMWvLDNiVtpXGaOtq48GNh9iyYFuO+xXriHHzwk3sXbMvX9vzuYZt6uO3mYOxY9n/0L/5YDz1D8LS3YtyPD/LV3XGzLXTcOLPk+jXbBD+O30ZC7bOgf0n56eOrjbu33iADfM357hfbR0xrl/wxa7VOR/j/NCgdX0MnTEYO5bvwoAWmT8mLf5jYY7tK+fqjBlrp+LE3lPo33wwLp26jHlbZsu0T1tXG/d9H2DTglzapy3GjQu+2L3mz3xu0dcThIx8f5FqqDp3m7apjeIz+yB02T48bD4WSf4hcNo9Axo5XBf1q5aGw9oxiPrzHB42G4vY09fhuHUSdEqXkMao6Yrx7kYAXs7/X477LTGrL4ybVMXTQYvxqMM0aFmbwnHLxHxvHwCUbl0D9af/iqsrDmOXxzREBLxAxz8mQjeH3GbjWgqtVg/Dg30X8b+W0/D09C202zwa5k4fO9c0dcV47RuIf71yvq43mPErHBpXxtEhq7Gv8zzoW5mg7aZR+d08FGlbE2Vn98STpQdxqckUJDx8jhp7J0HLXH77TKqWQuUNw/FyzwVcajwZ4SdvouqOsdAv87F96rpiRF8PxKN5OV/3nOf0hFXTKvAbsBJX282BtrUJXLeNzvf26TVzh9m4QYjd+AdCuw5BauAzWK/3gpqpsdx4cUVnWC6cgneHTyG0yxAk+lyG1YpZ0HS0k8ao6Wgj+fYDRK/I+buXSFuM91d8EbtVudd+7YYNYPjbELzbvhNR/QYi/WkQTJf9DjVjY7nxmuXLwXjmdCQd/xtRfQcg+b9LMPGaCw17u49119FG6r0HiF+/Kcf9isRipFy/gXe7dudzi2SdOn8Ji9dvx2DPzti/aQmcHOwwaMIcvI2JlRt/58EjTJy7DL+0bATvzUvRsE51jJy+CE+CP/5I8z45GZXLl8XogT1z3K+zkwPmTvgNf+1chQ2/TwcgYND4OcjIUF2+Y+4mIiKiwkSlneQdOnTAtWvXAAB//fUX6tevj3fv3qF27dpISkqCu7s7jh8/rrT9jxjRH9u378WuXd549OgJhg+fgvfv38PTs7Pc+GHD+uCffy5i+fKNCAx8ijlzluLOnQcYPNjzk5h+WLRoDY4fP4MHDx6hf/8xKFLEEm3aNAUAtGjRCGlpaRg1ajqePHmGW7fuYfjwKWjfviVKlrSVu99v0XFgB/z950mc3v8Pnj95gRWTViIlOQXNuzaTG/9Lv3bwveCL/Ru88eLpS+xYshNPHjxFu95tpDFnD57DrhW7ceu/2znu99DWw9i7dh8C/ALyvU2fatDfA1f2nsN17wsIe/oa+6duQer7VNTs3EBuvHvfFgi4eAfnNx1DeNBr/L1sP149DEZdz4/vh+/h/3Bq1UEEXr6f436v/HkOQTcCEP0qEq8eBuPE0n0wLWoOs2KW+dq+DgN+wck/T+Gf/Wfw4skLrJy8GinJKWjWRf7xa9evHXwv3IT3xgN4+fQldi75H54+eIo2nh+P37lD57B75R7cvpTz8Tu89Qj2rduPAL+cR4Xlhy4DOuLYnr/x9/7TCHnyHEsmrUDy+xR4dG0uN75jv19w44Iv/tywH8+fvsDWxTvw+MET/NKnnTTm9MGz2LFiF27+dyvH/XpvOYTda/fioZLPz04DO+DEn3/j1P7TeP7kBZZNWoHk5BS0zKF9HT60b9+G/Xjx9AW2LdmBJw+eon3vttKYMwfP4n8r/sCt//zklgEAB7Yewp61e+Gv5PbliSDJ/xephKpzt9WANojccwZR+88j+ckrPJ+0AZL3KTDv2kh+fL9WiLtwG2EbjiD56Su8Xvwnkh48g2WfltKYtwcvInTFfsT/J/9OMnUDXZh3bYSXs7cj4fJ9JN1/huDRq2FQrSz0qjjJ3eZbVO3fAvf/9MED73/x9kkozkzejrT3KSjfxV1ufJW+zRB88R58N55A9NNQXF56AOEPQlCpdxNpjP+hy7i68gieX3ogtwwtAx24dKmPC3N34+UVf4TfD8GpcZtQtKoTilR2yNf22Q/2wMs/zuPV3ot49/g17o/fioz3qSjerb7ceLuBLRDpcxfP1h3HuyeheLzIG3H3g2HX92MufH3gEp4uO4Sof+Xnbg0DHRTv3gD+M3fh7aWHiL8XjLsjN8K0emkYuzrma/sMe3ZAwqGTePfXaaQ9e4G381ZCSE6BQTv5udvw1/Z4f8UXcTu9kRb8ArFrdyIl4CkMu3689r87fhaxG/9A8vWcr/3xuw8jbts+pNxT7rVfr2snJB07gfd/n0J6yHPELV4GITkZOq1ayI/v1AEp128g8c99SH/+Au+2bEfa4yfQ7dBeGvP+9Bm82/E/pN7MOXcneR9E4h9/Iu2hf7636VP/8z6GDh5N0L5FIzjYFceMMYOgoy3G4ZPn5cb/cfA4alevjD5d26GkbTEM79sdzqXs8efhk9KY1k3rY4hnZ9R0rZjjfju1boqqFcuhqLUlnJ0c8Fvf7giLiEJoWGS+t1FhzN1ERERUiKi0k/zhw4coV64cAMDLywsLFizAX3/9hYULF+LQoUNYtmwZZsyYoZR9a2pqonJlF5w/f0m6TBAEnD9/CdWrV5G7TY0aVeDjc0lm2Zkz/6JGjcx4O7viKFLEUqbM+PgE+PrekcaIxWKkpaVBEARpzPv3yQAAN7dq+dO4DzQ0NeDkUgp+n3RmC4IAv/9uw7lKWbnbOLs6Z+v8vnnxJpxd5cerkrqmOoqXLynTmS0IAgIv34d9Ffm3xNpVdsLjy7IdBAH/3oX9N3RyaOmIUaNTfUS9CEfMm6gvb6AgDU0NlHIpJdOZLQgCbv93G2VzOB7OVcpm6/y+efFWjvGqpKGpAacKTjKdvYIg4OYlP5RzdZa7TXlX52yd3zcu3ET5HOJVSUNTA6Vdsrfv1n9+cK4iv77lXJ2zdX7fuOgL5x+wfVR4qTJ3izQ1oFfBQbYzWxAQf+ke9F1Ly91Gz7V0ts7vuAt3oO+q+HVft4ID1LQ0ZcpJDnqNlFcROe73a6lpqsPKxR7PLz38uFAQ8OLSQ9hUkd+Za1PFMVvnd8i/93KMl8fKxR7qWhoy+40OeoP4V1GwySGnfg2RpjqMKtgj6r9P6isIiPr3AYyryt+PiWspRP0r275In3swySFeHqOKJaGmpSFTTuLTUCS9jMxTOV+koQFxWSe8v/bJtVwQ8P6aH8QV5F/LtSs4y8YDeH/lJsQVfrzcDQ0NaDo5IeXTzmxBQMpNP2h9uC58Tqu8s2w8gJTrvtAqLz9eldLS0uD/OAg1XStIl6mpqaFmlQq4+1D+dDl3/R/LxAOAW4t2+8EAAQAASURBVLXKOcYrIul9Mo6cOo+iRaxgbSn/DlciIiIiyl8q7STX0NBAQkICACA4OBgtWsiOQGnRogUCA7/+C2ZuzM1NoKGhgYgI2U7NiIgoWFtbyN3GyspCbryVVWa8tbWldFlOMRcuXIaVlQVGjx4ETU1NGBsbYt68STLb5xcjU0Ooa6gjJjJGZnlMVAxMLU3lbmNqYYKYqM/iI2NhaiE/XpX0TDLbl/DZfLAJkXEwsDCWu42hhTHio2Kzx5vLv00/N3V6NMXihzuxJOB/cK5fCet6zEdGWv7dRmooPX6xMstjomJhamEidxsTCxPEfNa+2FziVcnI1AgaGuqIzna+xcAsh/PN1MIU0Z+dz9FRMT/k+WlkagR1DfVs9c38/Mk/HqYWJnLejx/z85dnEkn+v0glVJm7NUwNINJQR9pn1/20yFho5nDd17QwRtpn19G0qFho5uG6qGlhDElKGjLiZZ8dkhYZl+N+v5aOqQHUNNSR+FkbE6PioGchP1fpWRgjKVJ23vCkyHjo5aFuehZGSE9JQ8pnbUyMioOeZd5zZE60TA2hpqGOlM/mAU+JjIPY0ljuNmJL42zzhqfmEi+/DCNkpKQh/bP2pUbFQZyPx1DdxAgiDXVkvJW9lme8jYG6ufxzTt3cBBlvY7PFa5j/eNd+NaPM9kmiZdsniY6Bmpn8+qqZmkIS81l8TAzUTH+87yYxcQnIkEhgZmIss9zMxBhvo2PlbhMVHSsn3ghROUzPkpu9R06ieovuqNGyOy5dv43Ni2dCU1Mzz+XkG+ZuIiIiKkRU2knu7u6OP//MnDexcuXKuHDhgsx6Hx8fFC1aNNcyUlJSEB8fL/P6dJT2jyYg4AkGDBiLESP6Izr6EUJCbiIk5CXCwiIg8BbEAuXmX//hd4+JWNl5FiKevUGftaOgIVbhHzJERN+BsnJ3KueqJaJCzqNxPXhvXoLtK+bCrngRjJ29BCmpqaquFhEREVGhoKHKnS9cuBB169ZFaGgo6tSpg6lTp8LX1xdly5ZFYGAg9u3bhw0bNuRahpeXF2bPni2zTF3dEJqaxrluFxUVg/T0dFhamssst7Q0R1gOc/+Fh0fKjQ8Pz4wPC4v4pIwImZh79z7On7hv31/Yt+8vWFqaIzExCYIgYMSI/ggOfpFrnfMqLjoeGekZMPlstJyJuQmiI6LlbhMdGQOTz0Y6mVgYIzpSfrwqJcZktu/zUeAGFkZI+GzUYJb4yFgYmhtnj/9sxJ4ikhPeIznhPSJDwhBy+zEW3t2GCs2qwe/olTyXJbeu0uMnW18Tc+Nso5OzxETGwOSz9hnnEq9KcdFxSE/PgGm2880Eb3M436Ijo7ONijc1N/khz8+46DhkpGdkq2/m50/+8YiOjJHzfvyYn78844+APw1l5e7++qUx0DD36SXSoxMgpGdA87PrvrzR4lnkjTLXNDdGWh6ui2mRsVATa0LdUFdmNLmmhVGO+/1a76MTIEnPgN5nbdQzN0JipPxclRgZC10L2Yde6loYIjEPdUuMjIOGWBNiQ12Z0eR65kZIjMh7jsxJanQ8JOkZEH82Kl5sYYSUiFi526RExELrs3itXOLllxEHdbEmNAx1ZUaTa5kbISUfj2FGTByE9Ayom8ley9XNTJARJf+cy4iKgfpnD3RWNzNBetSPd+2XxGW27/NR4GqmJpC8lV9fSXQ01Ew+izcxyTYa/UdgYmQAdTW1bA/pfBsTC7McHrxqbmosJz4O5iby43NjoK8HA3092BazQUVnJ9Ru0wvn/ruOlo3q5rmsfMHcTURERIWISkeSly1bFtevX0dqaip+//13JCYmYvfu3Zg1axaePn2KvXv3onfv3rmWMXnyZMTFxcm8NDS+fFtwWloabt++jwYNakuXiUQiNGhQGzduyH8o0vXrfqhfv7bMskaN6uL6h4cohYS8xJs3ETJlGhjoo1q1StKYT0VERCExMQkdO7ZGcnIKzp27lC3mW6SnpePx/SeoXKeSdJlIJELlOpVyfKCf/y1/VKlTWWaZa90q8L/1Az0A8IOMtAy8fPAMTm4u0mUikQil3coj2O+J3G1Cbj+Gk1t5mWVl6rgg2O/xN9VFJBJBJBJBQyv/RpKnp6Xjyf0nqFS7ksx+KtWphIAcjoe/XwAqfxIPAFXqVskxXpXS09Lx+N5juH5yvolEIrjWqYyHt+Q/lOvBLX+41pF9ZkDVeq54kEO8KqWnpSPw/mNU+aS+We3z95Nf34dyPn9V67rC/wdsX55JMvL/RSqhrNzd2+DLc4QLaelIvBcEwzqfzP8rEsGwjgve3ZI/xUvirUDZeABG9Sri3S3Fr/tJ94IgSU2TKUfbwQbiYpY57vdrSdIyEH4/GCVqfzJfs0iEErXLIdTvqdxtQv2ewra27PzOtnXK5xgvT/j9YGSkpsvs16RkERgWM0doDjn1awhpGYi7Fwzzup/kYpEIZnXLIfam/P3E3HoC87qy7bNwd0FMDvHyxN19Bklqusx+9RyKQLe4RZ7K+aL0dKQEPIZ2jU+u5SIRdGpURso9+dfy5Hv+0Kkhe+3XqVlF6Q/g/Crp6Uh7/Bhi109ysUgEsWsVpD58KHeT1Af+EFeVzd3iaq5IfSA/XpU0NTXh7OSA6373pMskEgmu+d1DxXLynz9Q0dkJ1/1kHxh79dbdHOMVJQiZzzJJTUv7pnK+CXM3ERERFSIqHUkOAA4ODvjzzz8hCAIiIiIgkUhgbm6u8Px7YrEYYrFYZplIJFJo21WrtmDz5qW4desebt68i99+6wtdXV3873/eAIAtW5YhNDQMM2b8DgBYu3Y7/vlnH0aOHICTJ8+jU6fWqFLFBcOGTZKWuXbtVkycOBxPnwYjJOQlZs4cizdvInD06D/SmMGDPXHt2i28e5eIRo3qYsGCKZg+fSHi4mTnE80PBzYdxMTl4/H47hM8uvMIHfr/Am0dbZzedxoAMHHFeESFvcXWhdsAAIe2HsHyA0vQaWAHXDt3Aw3a1odTBScsm7hSWqaBsQEsbSxgZp35IKHiDsUBZI6CzZr/3MTCBKYWJihqZwMAKFnGHknvkhARGomE2IR8a5/PlhPosXQoXt4PwvM7QajfryW0dMW47n0BANBj6TDEhUfj2O+ZUwNc3HYSI/bNRIP+rfDQxw+urd1Q3MUBeydvlpapa6QHk6LmMPowb7Rlycw2xEfGIiEyDmbFLVGltRse/XsX76LjYWxthsZD2iItORX+PrIPzfxWBzcfwvhl4/Dk3hM8uhOIX/q1zzx++zPPp/HLx+Ft2FtsW7QdAHBk6xEs8V6MDgN/wY1zN1C/TX04VSiFlZM+PX76sLCxhJlV1vErBiBzFPqnx8/EwgQ2H46ffRk7JL17j8jQCCTEvsu39u3bfABTlk/Eo3uPEXD7EToN6AAdHW38/eH8nLpyIqLeRGHjwq0AgANbD2H1geXoMqgTrp69hkZtG6BMBScsnrDsk/YZwKqoJcw/tK9E1vkZES0dUW9qYQJTS1MUs8ucEqJkmZJISkxC+OuIfD0/vTcdxOTlExB4NxABdwLR8cPn7+S+UwCAySsmIiosCps/tO/g1kNYeWAZOg/siGvnrqNh2wYoXcEJSycul22fjaWcz99n7bMwlX7+7MvY4/279wgPzd/2UeGljNytJVJXaNvwzUdhv3wEEu8FIfH2E1gNaAU1HW1E7TsHALBfOQJpb6LxauEfmfFbj6P0gXmwGtQGcWdvwbRtHehWcEDIhPXSMtWN9aFV1BxaVplzKus4ZF4b0iJikR4Zi4yEJETtPYfiM/sgPfYdMhKSYDtvAN7dfITEb/yRVZ6bW06ixdJBCL8fjDd3guDarzk0dcV4sP8iAKDF8kF4FxaD/xbtBwD4bTuNLvunouqAFnh2/g7KtKkF6wolcWbSNmmZ2kZ6MChqBn2rzNxm6lAEQOYI8qTIOKQmvMf9fRfQYPqvSI59h9R379Fwdi+8vvkYb24H5Wv7gjecQMVVQxB75xnibj+F3cAW0NAV4+XezPZVXD0EyWExCJy/FwAQsukkah6ZAfvBHog4exs27WrBqGJJ3Bv3MXdrGutBp6g5xNaZ7dNzzGxfSkQsUiLjkJ7wHi/3+KDs7B5Ii32HtIT3KL+gN2J8HyP2luI/JigiftdBmM+dgNSHj5HyIBCGPdpDpKONhCOZuc183gRkREQhZlXm8YnffRhFti6FYa+OeP/vdeg1rw9xOSdEzV0hLVPN0AAaRSyhbpF57de0y8zdGVHR0vnP1c1MoG5uCo3imeevpqM9hKT3SH8TAUl8/l37E/d6w3jqJKQ9eoy0gADodu4IkY423p/IzG1G0yZDEhmJhI1bMuO9D8JszQrode2E5CvXoNO4ITTLlEbc70ulZYoMDKBuZQl188w7NjVKlACQOQo9a8S5mqkJ1ExNof5hOieNkiUhJCUhIzwCQkL+ta9Xp9aYunA1yjk5wqVsKew6cAzvk1PQrnlDAMCUBSthaWGGUQN6AAB6dGiFPqOmY+f+v1C3pitOnb+Eh4FBmDl2sLTMuPgEvImIQsSHuwNCXrwGkDkK3dzUBC9Dw3Da5zJqVa0EU2NDhEe+xdY/D0Es1kLdGlVARERERMonEn7gCbxfvnyJmTNnYtu2bV8O/oSOjq3CsYMHe2L06IGwsrLAvXv+GDt2Fnx97wAATp/ei+fPX2HgwHHS+F9+aYmZM8fB1rYYnj4NwdSpXjh92kemzOnTx6Bv324wNjbElSs3MXLkNDx9Gixdv2XLMjRv3hD6+roIDAzCihWb8OefhxWus5tZ3kamtO3dBl0Gd4KJhQmC/J9hzYx1eHT7EQBgqfdihL8Mx+9jlkjj63nURd8JvWFVzAqvg0OxacFm3DjvK13frFMTTFg+Ptt+di7bhf8t2wUA6DWmJzzH9MwW8/voxTjtfeaLdS6nofjDnOr2aoZGA1vD0MIYrwJCcHDWDjy/k/kH7/C9MxD9KhK7x33sDKnUsiY8xnaBWTELRISE4ajXH/C/cEe6vnpHd/RYMjTbfk6u8MbJFQdgaGmCbosGoXh5e+ga6SMhKhZBNx7h1KoDiHj2RqE6P8pQ/Nb1Np6t0WlwR5hYmOCZ/zOsm7Eej+5kjlxcvP93hL8Kx5IxH//QrOtRF73He8KqmCVCQ0Kxef5W+Pp8PH5NOjXB+GVjs+1n17I/sGt5ZqdSz9E90HNMj2wxi8csxRkFjt97ieKjnn7p3RbdhnSBqYUJnj4MwsoZa+D/4fxc5b0UYa/CsWD079L4+q3qYcCEvrAuZoVXwa+xfv4mXDt/Q7q+RedmmLJ8Qrb9bFu6E9uX/Q8A0GdML/Qd65ktZsHo33Fy/+kv1lldwR/iAKB977boMrhzZvv8g7B6xloEfGjfCu+lCHsZhoVjFkvj3T3qod+EPrAuZoXXwa+xYcFmXP+kfc07NcUkOe3bsex/2PGhfb3H9ELvMb2yxSwc/TtOef+TbfnnLrw6q3D7FJV8wzvfy9Su3infy6Rv97W527doe4VjLXu3gPWQdtC0MEHSw2C8mLEFibczRwOX9p6L1FcRCB69Whpv0soNRSd0h7iYJZKD3+DV/J2IO//xDi+zzg1QcvmIbPt5vXQvQpftAwCIxJooPqMPzNrWgUisifgLdxAyZSPSFZyq46K6nsLtA4DKnk1QbZAHdC2MEOn/HOdm7kLYnczO6i77piLuVSROjd0kjXfyqI464zrBsJg5YkPCcHHBXgT73JWuL9exLlosG5RtP1eWH8KV5YcAAOpiTdSf1h1l2taChpYGgi/ex9lpO5CUwzQvnyubovgoUdu+TVFyaCuILY0R//A5/KfuQKxfZvtqHpqOpJeRuDfy47Q91q1roPSkztApboGk4DAEzNmDyHN3pOuLdamHiquGZNvP48UH8GTJQQCAmlgTZWf1gE17N6iJNRDlcw8PJm7L9hDRnDhbR3056AODrm1h7NkJ6uYmSAkMQvSidUi5n3ntt96yBOmh4Yia8fHar9ukHkx+6w1NGyukvXiN6OVb8P7Sx2u/fpumsJib/btXzPr/IXZD5ncv48E9YTIk+7U/cvpivDv65Wu/tkG6wu3T/aUd9Lp3gbqpKdKeBiF+xWqk+WeOfDddvRwZb8IQt2DRx7IbuMNgQF+oW1sj/dVrJKzbiJRr16XrdVo0g/HUSdn2k7BtB95t2wkA0O/rCYO+vbPFxM5fiPcnv5y7zfavUbh9ew7/jR37jiAqOhZlHOwxaXg/VHDOvNulz6jpsLG2xPxJw6Xxpy9cwZpte/A6LAK2RYtg9KBeqFfTVbr+yKnzmL4o+/6HeHbG0N5dEREVjZlL1sH/cRDiExJhZmIE1wrOGNyrM+xL5P6MhyxaNuW+HJRHzN1ERERUmPzQneR3795FlSpVkJGRt1vz8tJJXhDltZO8IMpLJ3lBlJdO8oIoL53kBVFeOskLIqV0kl/bl+9latfsku9l0rf72tydl07ygiivneQFUV46yQuivHSSF0R56SQviPLSSV4QKaWTnLmbiIiIChGVTrdy9OjRXNc/e/bsO9WEiIiIFMHcTURERERERD8blXaSt2vXDiKRCLkNZld0fnEiIvqBCRJV14DyCXM3EVEhwdxNREREhYiaKndepEgRHDp0CBKJRO7Lz8/vy4UQERHRd8PcTURERERERD8blXaSu7q64tatWzmu/9JINSIiKiAkkvx/kUowdxMRFRLM3URERFSIqLSTfPz48XBzc8txvaOjI3x8fL5jjYiISCl+gD+0165dCzs7O2hra6NGjRq4ceNGrvHe3t4oU6YMtLW14eLigr///lu6Li0tDRMnToSLiwv09PRgY2ODXr16ITQ0VBoTEhKCfv36wd7eHjo6OnBwcMDMmTORmpqa57r/SJi7iYgKiR8gdxMRERF9LyrtJK9bty6aN2+e43o9PT24u7t/xxoREdHPaN++fRgzZgxmzpwJPz8/VKxYEc2aNUNERITc+CtXrqBbt27o168fbt++jXbt2qFdu3Z48OABACApKQl+fn6YPn06/Pz8cOjQIQQGBqJNmzbSMh49egSJRIKNGzfi4cOHWL58OTZs2IApU6Z8lzYrC3M3ERERERER/WxEwk94T7SOjq2qq6BUbmalVV0FpSunYaLqKijVo4w4VVdBqd5L0lRdBaVS/8kfSnjh1dl8L/P9vzvyvUyder0Vjq1RowaqVauGNWvWAAAkEgmKFy+O4cOHY9KkSdniu3TpgsTERBw/fly6rGbNmqhUqRI2bNggdx++vr6oXr06nj9/jhIlSsiNWbx4MdavX49nz54pXPfCwrdoe1VXQakuquupugpKVzYlQ9VVUCpn6yhVV0GptA3SVV0FpTLbv0bVVVAqLZty+V6mqnM3ERER0fek0pHkRERUSKjwlu3U1FTcunULjRs3li5TU1ND48aNcfXqVbnbXL16VSYeAJo1a5ZjPADExcVBJBLB2Ng41xhTU1OF605ERKQynG6FiIiIChENVVeAiIjoa6SkpCAlJUVmmVgshlgsllkWFRWFjIwMWFlZySy3srLCo0eP5JYdFhYmNz4sLExufHJyMiZOnIhu3brB0NBQbszTp0+xevVqLFmyJNd2EREREREREdH3xZHkRESkfIIk319eXl4wMjKSeXl5eX33pqWlpaFz584QBAHr16+XG/P69Ws0b94cnTp1woABA75zDYmIiL6CEnI3ERER0Y+KI8mJiKhAmjx5MsaMGSOz7PNR5ABgbm4OdXV1hIeHyywPDw+HtbW13LKtra0Vis/qIH/+/DnOnz8vdxR5aGgoGjRoADc3N2zatEmhthERERERERHR98OR5EREpHxKmNdULBbD0NBQ5iWvk1xLSwuurq44d+7cJ9WR4Ny5c6hVq5bc6taqVUsmHgDOnDkjE5/VQf7kyROcPXsWZmZm2cp5/fo16tevD1dXV2zfvh1qaky7RERUQHBOciIiIipEOJKciIiUT8W3WI8ZMwaenp6oWrUqqlevjhUrViAxMRF9+vQBAPTq1QtFixaVTtcycuRIuLu7Y+nSpfDw8MDevXtx8+ZN6UjwtLQ0dOzYEX5+fjh+/DgyMjKk85WbmppCS0tL2kFua2uLJUuWIDIyUlqfnEawExER/TA4PQoREREVIuwkJyKin16XLl0QGRmJGTNmICwsDJUqVcKpU6ekD+d88eKFzChvNzc37NmzB9OmTcOUKVNQqlQpHDlyBOXLlweQOUL86NGjAIBKlSrJ7MvHxwf169fHmTNn8PTpUzx9+hTFihWTiREEQYmtJSIiIiIiIqK8EAk/4V/qOjq2qq6CUrmZlVZ1FZSunIaJqqugVI8y4lRdBaV6L0lTdRWUSl0kUnUVlOrCq7P5Xub7f9ble5k6TYfme5mkOr5F26u6Ckp1UV1P1VVQurIpGaquglI5W0epugpKpW2QruoqKJXZ/jWqroJSadmUy/cymbuJiIioMOHkqERERERERERERERUaHG6FSIiUj7Oa0pERFSwMHcTERFRIcJOciIiUj4J/9AmIiIqUJi7iYiIqBDhdCtEREREREREREREVGhxJDkRESkfR6MREREVLMzdREREVIiwk5yIiJSP85oSEREVLMzdREREVIhwuhUiIiIiIiIiIiIiKrQ4kpyIiJSPt2wTEREVLMzdREREVIhwJDkRERERERERERERFVocSU5ERMrHeU2JiIgKFuZuIiIiKkTYSU5ERMrHW7aJiIgKFuZuIiIiKkQ43QoRERERERERERERFVocSU5ERMrHW7aJiIgKFuZuIiIiKkTYSU5ERMrHW7aJiIgKFuZuIiIiKkR+yk7ySqYlVV0FpaqvbqHqKijd7NALqq6CUhU1MFN1FZTKVNNA1VVQKi+huKqrQPTT+V3j5+6MOfzGR9VVULqrFtVVXQWlsupeTNVVUCoh/p2qq6BUiSOHqboKSqXlfUHVVSAiIiIq0H7KTnIiIvrBcDQaERFRwcLcTURERIUIH9xJRERERERERERERIUWR5ITEZHyCYKqa0BERER5wdxNREREhQg7yYmISPl4yzYREVHBwtxNREREhQinWyEiIiIiIiIiIiKiQosjyYmISPk4Go2IiKhgYe4mIiKiQoSd5EREpHwC/9AmIiIqUJi7iYiIqBDhdCtEREREREREREREVGhxJDkRESkfb9kmIiIqWJi7iYiIqBDhSHIiIiIiIiIiIiIiKrTYSU5ERMonCPn/IiIiIuX5AXL32rVrYWdnB21tbdSoUQM3btzINd7b2xtlypSBtrY2XFxc8Pfff8usP3ToEJo2bQozMzOIRCLcuXNHZn10dDSGDx+O0qVLQ0dHByVKlMCIESMQFxeX57oTERFRwcJOciIiUj6JJP9fREREpDwqzt379u3DmDFjMHPmTPj5+aFixYpo1qwZIiIi5MZfuXIF3bp1Q79+/XD79m20a9cO7dq1w4MHD6QxiYmJqFOnDhYtWiS3jNDQUISGhmLJkiV48OABduzYgVOnTqFfv355qjsREREVPJyTnIiIiIiIiH4oy5Ytw4ABA9CnTx8AwIYNG3DixAls27YNkyZNyha/cuVKNG/eHOPHjwcAzJ07F2fOnMGaNWuwYcMGAEDPnj0BACEhIXL3Wb58eRw8eFD6bwcHB8yfPx89evRAeno6NDT45zMREdHPiiPJiYhI+TiSnIiIqGBRYe5OTU3FrVu30LhxY+kyNTU1NG7cGFevXpW7zdWrV2XiAaBZs2Y5xisqLi4OhoaG7CAnIiL6yTHTExGR8gns1CYiIipQlJC7U1JSkJKSIrNMLBZDLBbLLIuKikJGRgasrKxklltZWeHRo0dyyw4LC5MbHxYW9tX1jYqKwty5czFw4MCvLoOIiIgKBo4kJyIiIiIiIqXz8vKCkZGRzMvLy0vV1ZIrPj4eHh4ecHZ2xqxZs1RdHSIiIlIyjiQnIiKlEySCqqtAREREeaCM3D158mSMGTNGZtnno8gBwNzcHOrq6ggPD5dZHh4eDmtra7llW1tb5yk+NwkJCWjevDkMDAxw+PBhaGpq5rkMIiIiKlg4kpyIiIiIiIiUTiwWw9DQUOYlr5NcS0sLrq6uOHfunHSZRCLBuXPnUKtWLbll16pVSyYeAM6cOZNjfE7i4+PRtGlTaGlp4ejRo9DW1s7T9kRERFQwcSQ5EREpHx+0SUREVLCoOHePGTMGnp6eqFq1KqpXr44VK1YgMTERffr0AQD0+j97dx3e1PUGcPyburuhw12Ku7sMug3dGAxnG/xw9wFjwHD3wYAhQwZsQ8Zwb0uBIi0tlGJ1g7rk90dZStoE2i5dkffzPNmz3rw59xzuTd6bk3PP6d2bQoUKqaZrGT58OE2aNGHhwoV06NCBnTt34u7uzrp161RlRkREEBgYyNOnTwHw8fEB0kehu7i4qDrI4+Li2LZtGzExMcTExADg6OiIvr7+f/lPIIQQQoj/kHSSCyGEyHuycKcQQgjxbsnn3N29e3dCQ0OZNm0aQUFBuLq6cuTIEdXinIGBgejpZdwYXb9+fXbs2MGUKVOYNGkSpUuX5sCBA1SqVEkVc/DgQVUnO0CPHj0AmD59OjNmzMDT05PLly8DUKpUKbX6PHjwgGLFiuVVc4UQQgiRz6STXAghhBBCCCHEW2fo0KEMHTpU43OnTp3Ksq1r16507dpVa3lfffUVX331ldbnmzZtilIp66gIIYQQHyLpJBdCCJH3ZOFOIYQQ4t0iuVsIIYQQHxBZuFMIIYQQQgghhBBCCCHEB0tGkgshhMh7snCnEEII8W6R3C2EEEKID4h0kgshhMh78kVbCCGEeLdI7hZCCCHEB0SmWxFCCCGEEEIIIYQQQgjxwZKR5EIIIfKeUhb/EkIIId4pkruFEEII8QGRTnIhhBB5T27ZFkIIId4tkruFEEII8QH54Kdb+ayPG/su/cIp/6NsOLSKCq7lXhvfvGMTdp7ewin/o2z7ayP1mtdRe75Ju0Ys2TGfI94HuPjkJKUrlsxSRucvOrJyz2L+unuYi09OYmFlrtM2ZVazdyuGnVvCRJ/N9Dswk4JVS7w2vnz72nx9YgETfTYz+OgPlGpWVe35cm1r8vnPExjttYapD7fjXOGj15bXc8s4pj7cTtnWNf51WzT5ekgf/Hwv8SLGnwvnDlGrputr4z/7rCPeN0/zIsafa55/0a5t8ywxM6aP4dFDT55H+3H0z52UKlVc7flqrpU48scvhIXcJviZN6tXzcPc3EyXzVLp3b875679ic+Tqxw4tp2q1Su9Nr59p1acuPQbPk+ucvTsXpq1bKj2fNuOLfj51zV43TvDw/AbVKhUNksZxsZGzJo/Ca97Z7j98BJrflqEg6OdTtv1j259P+X3q79yKeBvtv6xjorVyr82vuXHzdh3dgeXAv5m98mtNGxRT+355u2bsGrnYk7e/oNrQecpU7F0ljI+7dWJ9fuWc/beMa4FncfCykKnbXpV0b6taXJ1Oa0ebqXun7Oxrpb1M+FVzh/XoeG5hbR6uJUGp+bj0MJV/fn2tai5axLN76ynbfBOLCtqfv/Z1CxNrb1TaPngJ1r6baL2genomRjqqllC5Ks2vduz8tw6tvvs4fsDCyhVNev7/FV129dnyYmVbPfZw8KjS6nWLGs+6j7qc9Zd3cx2n91M3f4dLsUKqD1fvFIJpm6byU83trPJ62cGz/0GEzMTnbbrVfmR20qXLsG+vZsIenqTiLC7nD65n6ZN6uuyWSpOfdpR5dJaavjvovyheZi7vv4Y2nasT6XTy6nhv4uKfy3Bunl19efb1aXMjulU895KrSf7Ma1YLEsZCmNDis4ZRDXvrVT33UHJdeMwcLDWZbNUDKo1x2TIAkxHr8P4yynoFSj+2nj9sjUxGfA9pqPXYdJvFnolqqg/X6YGxt1GY/q/5ZiN34zCqYh6ASbmGLb8Ir2MUWsx+fpHDFt8Dkamum4aAAZ12mA6ZiVmM7ZjMuR79AqXem28fqW6mI5YgtmM7ZgOW4h+mWrqz1eojclXUzCbvAnzOXvQK1BMvQBTC4w69sN0xNL0MsauxqhDXzDOm2sv4zZuWK3cic32Y1h+vwr9Uq//fmBYtwlWS7Zis/0YVgs3YVBN/fuBYe1GWExZgPWm37Ddcwr9Yln/vYxadsRixhJstvyO7Z5TKMzy7tpECCGEEEJkle+d5OHh4Zw8eZKIiAgAwsLCmDdvHt999x137tzJ03236NSM/03/mo2LtvBV20Hcu+3P4u3zsbW30RhfuWZFZq6cyqFf/qBPm4GcOXqOeRtnUaJsMVWMqZkJN654s3LOOq37NTE15tKpK2xZvl3HLcqqQse6tJryBWeW7mN9xykE3wnk858nYGZvpTG+cI3SfLp8KF67T7G+w2R8jrnTbd0oHMsUVsUYmprw6KoPJ37Y+cb91+nfFmUe3qrZtWsnflwwnVmzF1GrTluu37jNH79vx9HRXmN8vbo12f7zSjZv/oWatdtw8OBR9v66kYoVMzqKx475hqHf9uOboROo3/BjYuPi+OPwdoyNjQEoUMCZo0d24ucfQP2GH9Oh4xdUrFCWTRuX6Lx9Hd3aMGXWWJYuWEPH5t254+3Dz3vWYO+gucO6Rq2qLF8/j93b9tOhWTeO/fE3635eSplyGV/GTM1MuXrpGj/M1F7fqXPG0aJNE77pN4Zunfri7OLI2i2Ldd08WnduwegZw1i7cBOft+6H7y0/Vv2yCFsHG43xVWtWYu7qGRz45TA9W/Xl1J9nWbR5LiXLZXQ+mJqZ4HXlBstmr9a6XxNTEy78fZlNS7fquklqXDrXo9zML/Fb+CsXWk3k+a2H1Nw5ESMHze8/m5plqLrmfzzecZILLScQ/Kc71X8ag0W5jPefvpkJkZfv4jt7h9b92tQsTY1fJhJ26gaX2k7hYpvJBG46ijItH2+bTlPq/pFDK1eupFixYpiYmFCnTh2uXLny2vg9e/ZQrlw5TExMqFy5Mn/88YfqueTkZMaPH0/lypUxNzenYMGC9O7dm6dPn6qVERERwRdffIGVlRU2Njb079+fFy9e5Ljub5v8zN31Ozakz5R+7Fm6i/EdR/HwzgMm/zwDK3vNnZ1lapRjxPIx/L37L8Z1GMmVY5cZt24iRcoUVcV0HvIp7b7qwLpJq5nYeSyJcQlM+XkGhsbpPyzZOtkxbft3BAU8Y5LbOOb0nknhMkX5duHwPGljfuQ2gN8ObMFA34BWbbpRu247rt+4zW8HtuDs7KjT9tl1akCR6X15umgXt9qOJu52AGW2T8NAyzG0qFmWkitHEfbLCW61GU3U0cuU2jgB07IZx1DPzJgXV+7waI72z/WiM/ph06omfoMXcPezKRi52FFqw3idtg1Av1xtDJv3IPn8byT8NANlyCOMu40GM0uN8XqFSmHUaQgpN86Q8NN0Uu95YvzpMBQOhTKCDI1IfXyPpFN7NJahsLBBYWFD8sldJGyaQtLvG9EvURmj9n11377K9TFq34fkv/cQv3I8aUEPMflqMphrzm16Rctg3G0EKe5/E79yHCl3rmD8xTi1jn6FkQmpD++SdHSb5vZZ2qKwtCXpyFbil40ice9K9Mu4Yvzp1zpvn2H9Zpj2+YaEPT8RM34gqQ/9sZi8AIWVjcZ4/TIVMR8xjcS/fydm3ACSrpzDYtxs9IpkXJsoTExIuXuT+G3avx8ojExI9rpC/P68/36QbW9B7hZCCCGE+K/kayf5lStXKFmyJC1atKBUqVJ4eHhQu3ZtNm7cyNatW6lRowaenp55tv+eA7tycMfv/L77CAH3HjJ/wiIS4xPo2KOdxvhu/T/j8qkrbF+zi4d+gaxbsBkf73t06fuJKubI3uNsWrKVq2c9tO5314a9/LzyF7w9b+u8TZnVHdCOaztPcn3PGcLuPeH3SZtIjk/EtVsTjfG1+7bF7/QNLq79nTC/p5xa+CvPvAOo1ae1Kubm/nOcXbafB+e8X7tv5wofUXdgBw6N1f6F4N8aOXwgGzbuYMvW3dy5c49vvp1AXFw8fb/qoTF+2LD+HD16ioWL1nD3rh/TZyzg2jVvvvk640vk/4YN4Pu5Szl06Bg3b97hq77DKVjQmc6d2wDQoX1LkpNTGPa/Sfj6+uPucZ1vhk7gs087ULJkMZ22b8A3vdn581727PiNez73mTR6FvHx8XT7wk1jfN/BX3D6xHnWrvgJP98HLJy7Eu8bd+gzIOPfY//uwyz7cS3nTl/SWIalpQXdv/iE2VN+5MLZK3hfv8OYYVOpWaca1WpW0fia3Oo1uDv7th/i4M4/uO8bwJxxC0iIT8StR0eN8T0HduPCyctsXbWDB/cesmr+eu7c9KVH3y6qmN9/Pcq6RZu5dPaq1v3uWL+bzSu2ccPzlk7bk1mxIR14tO1vnuw8TazvE26N3UBqfBKFejbVGP/RoHaEnbxOwKrDxN57it+83cTcfEDRfm1UMU9/PYv/on2En9H+/iv3XW8ebjjCg+UHeeHzmFj/ZwQdvIQyKUXXTXxn7Nq1i1GjRjF9+nQ8PT2pWrUqbdq0ISQkRGP8hQsX6NmzJ/379+fatWu4ubnh5uaGt3f6v3tcXByenp5MnToVT09P9u3bh4+PD506dVIr54svvuDWrVscP36cw4cPc+bMGQYNGpTn7c1L+Z27Ow7ozImdxzi15wSP7z1i3aTVJMUn0rxbS43xHfp+jNdpTw6u3c8Tv8fsWriD+973adunQ0ZM/4/Zu2IP7sevEHj3IStGLcHWyY5aresCUKNFTVKSU9kwdS1P7z/B/4Yf6yetpm77+rh85KLzNuZHbrO3t6VM6RLMX7CCmzfv4Of3gEmTv8fc3IxKFV8/ijannAd2InTHccJ2/03Cvcc8nLCGtPhEHHq00BzfvyPRp64RtOYACX6PebLgF+K87+PUt70qJnzvaZ4u2U3M2esay9C3NMOhRwsezdzM8/M3ibt5nwcjl2NZqzzm1cvotH0GtVqTcv0MqTfPoQx/StLRrSiTkzCo3EhzfI1WpN2/ScqVIyjDn5F8dj9pwQ8xqJ7x75F66yIpFw6SFqA5bynDnpB0YCWp/tdRRoWSFniH5DN70S/pCgrdXu4bNuhIivsJUjxPoQx9TNJv61AmJ2FYI+vdCwCG9TqQes+L5HMHUYY+IfmvXaQ9vY9hvbaqmBSvMySf/JVUv5ua2xfyiMRfFpJ61wNlRDBp971JOv4L+uVqgJ5u22fSsSuJJ34n6dQR0h4/JG7dIkhKwKh5e83xHT4j2esKiQd3kfYkkIRdm0i9fw+TthnfD5LOHCfh162k3NT+/SDxj19JPLCDVN+8/34ghBBCCCGyytdO8smTJ9O1a1eio6OZNGkSbm5utGjRAl9fX/z8/OjRowezZs3Kk30bGBpQtkoZtc5spVLJ1XOeVKpRUeNrKtWokKXz+/Kpq1rj85ueoT4FKhdX78xWKnlwzpvC1TXf1ly4eqksnd/3z9ygcPXX30abmYGJEZ8s+5Y/p/5EbGh0juueHYaGhlSvXoUTf59VbVMqlZz4+xx162qe2qVunRpq8QDHjp9SxRcvXpQCBZw58fc51fMxMc+5cuUadeukxxgbG5GUlKw2Qj4+PgGABvVr66ZxgKGhAZWrllfrzFYqlZw7fZnqtapqfE31WlU5d/qy2rYzf1/QGq9JZdcKGBkZqu3X/14Ajx89pboOO8kNDA0oX6Usl89kdGYrlUoun3WnSk3NU8pUqVGRy2fc1bZdPHWZKjXfvvegwlAfqyrFCT/7yhd+pZLwMzexqam5Q8amRmnCz6h3EISdvK41XhMjBytsapQmKSyaOoe/o5n3Gmrvn4ZN7azT6vynlGm6f+TAokWLGDhwIH379qVChQqsWbMGMzMzNm3apDF+6dKltG3blrFjx1K+fHlmzZpF9erVWbFiBQDW1tYcP36cbt26UbZsWerWrcuKFSvw8PAgMDAQgDt37nDkyBE2bNhAnTp1aNiwIcuXL2fnzp1ZRpy/S/I7d5eoXJIb5zI6QpVKJTfOXadMdc3neJnqZdXiAa6fuaaKdyrijK2THTdfiYl7Hoefly9lX8YYGBuSkpyi9rmflJAIQLlaFXTTuJfyK7eFh0dy18ePXr26YGZmir6+PoMG9iI4OBQPzxs6a5/C0ADzKiXVO7OVSmLO3cCihuZjaF6jbJbO7+hTXljUyP5no1mVkugZGaqVk+D/hMTHIVr3myt6+ui5FCPt4aud2UrSAm6jV0jztZReoZKkPlTvGE174I1+oddPz/VGxmaQlJDjz8vX0jdAr2AJUv1eOSeUSlL9bqBXVPPx0CtahlR/9XMo1e86ekX+3Y8TChMzSIzX7bzZBgbolyhLyo1XrveVSpJveGBQRvN73aBMRfV4IPn6FfS1xL9T8jl3CyGEEEL8l/K1k9zDw4NRo0ZhaWnJ8OHDefr0KQMHDlQ9P3ToUK5e1T4a9N+wsbPGwECfiLBIte0RoZHYa5l72d7RjojQTPFhkdg72uZJHf8tM1tL9Az0eRGm3kkdGxaDhaOWW5odbYjNFP8iLBpzR5sc7bv1tF489vDF97j2ETP/loODHQYGBoQEh6ltDwkJxUXLreEuLo4Eh4SqbQsODlPFuzg7vdyWKSYkDBeX9OdOnjqPi4sjo0cNwdDQEBsba76fMwmAAgWc/n3DXrK1t8XAwICwkHC17WEh4Tg6OWh8jaOTA2GhmeJDtcdrKyMxMYmYmOdZy3HOfjlvYmtng4GBARGhEWrbw0MjsHfS/B50cLLXEq95CoL8ZGRnhZ6BPkmZfiRKDI3G2MlG42uMnWy0xGd/zlzTj9LPwVJjuvB42wnce/xAzM0Aav86BbPiuh/xmm35eMt2UlISHh4etGyZMdJYT0+Pli1bcvHiRY2vuXjxolo8QJs2bbTGA0RHR6NQKLCxsVGVYWNjQ82aNVUxLVu2RE9Pj8uXL2sp5e2Xn7nb0tYKfQN9osOi1LZHh0VhoyUX2zjaZImPeiXexslWtU1bjPf5G9g42tBp8CcYGBpgbmXOFxP6qL1eV/IrtwG0adsDV9dKREX4Evv8PiOGD6LDx18QFaW7H7sN7CxRGOiTnOlaIzk0CkMt1xqGjjYkh0apx4dFYZiD6y9DRxvSEpNJjYnLtN9orfvNDYWZJQo9fZSxMWrblXHRKLRMR6Iwt84aHxuNwvxfzJduaoFh/Y9J8TqV+zI0UJhZotDXR/lC/fgpX0SjsLDR/BoLGw3xUehZao7PFjNLDJt2IfnqX7kvQwOFpTUKfX3SotWvNZTRkejZaL42UdjYZY2P0h7/TpHpVoQQQgjxAcnXTvKkpCRMTdMXFDI0NMTMzAwHh4xOOAcHB8LDw7W9HIDExERiYmLUHmkySiFflWlZnWL1K3J05s/5XZU8cfu2L337j2DkiME8j/bjyaNrBDwIJCgohDRdjmYSIhcUL2+rf/TzCZ7sPM1z7wDuTttKrP9TCn/eNH8rp2OaPv8TExOzxIWFhZGamoqzs7PadmdnZ4KCgjSWHRQUlKP4hIQExo8fT8+ePbGyslKV4eSk/sOZgYEBdnZ2Wst5F+RV7k5VpuZpvf+Nx/cesXL0Uj4e0Jltd3ez3n0LIY+CiQqJzN+5/nVs+bI5hIaE0bTZJ9Sr34HfDh7lwL4tah3p4h1gZIJxlxEow5+SfP63/K6N7hmbYtJ7Immhj0k+sTu/ayOEEEIIId4T+dpJXqRIEe7fv6/6e+fOnRQoUED197Nnz9S+eGsyd+5crK2t1R5Pnj98476jIqJJSUnFzkF9FJKdoy3hmUaq/iM8NAK7TKOW7BxsCc80uvxtERf5nLSUVCwc1EcimTtY8ULLFCgvQqMwzxRv4WBNbKYRXK9TrH4F7D5yYtzN9Uz238pk//RFtLqsGcGXOyfnrBGvERYWQUpKCk6ZRjc7OTkSlGm03D+CgkJxdlIfiefs7KCKDwoOebktU4yTA0FBGXMX79x5gMJFq1G0WA2cXCoxc9ZCHB3tuf8g8F+36x+R4ZGkpKTgkGmUtIOTPaEhYRpfExoShkOmhd0cHLXHayvD2NgIKyv1BcYcHO0JDc5+OW8SGRFFSkoKdpnu3LB3tCM8RPN7MCwkXEv86zvk8kNSRAxpKakYZbprw9jRmsSQKI2vSQyJ0hKf/VGciSHpn0cvfB6rbX9x7ykmhXR3J0BOKdPSdP7Q9Pk/d+7c/7xtycnJdOvWDaVSyerV2heMfV/kVe6+G33vjft+HhlDakoq1pkW97V2sCFKSy6OCo3KEm/zSnzUy/eMzWtiAM79doaBtb5icJ2+9HPtxe7Fv2Blb0VwoG5/8Miv3Na8WUM6tG/J572+4cJFd655eTPsf5OIj0+g95ddddI2gJSI5yhTUjHMdK2habT4PzSNMjd0sCE5B9dfyaFR6Bkbom9llmm/1lr3mxvKuOco01KzjBpXmGUdLa56TWzWUebpo8tzMYLfyCR9kdCkBBL3LYc03f74pIx7jjI1FYWF+vFTWFijfBGl+TUvojTE25D2XHP8axmZYNJnMiTGk7h9ge7b9zwaZWoqetbq1xoKa1vSojRfmyijIrLG22iPf5fkRe4WQgghhHhb5WsneY8ePdQWTevQoYNqdBrAwYMHqV379XM8T5w4kejoaLVHIcuP3rjvlOQUfG74UrNhddU2hUJBzYbV8fbQvCiSt8dttXiA2o1raI3Pb2nJqTy7+YBiDV6Zr1mhoHiDSjz21NwZ8djTj+IN1Od3Lt6oEo89/bK93/OrD7G2zUTWtZukegAc+26bThfxTE5OxtPzBs2bNVRtUygUNG/WkEuXNE/zcumyB82bN1Tb1rJFY1X8gweBPHsWrFampaUFtWtX49LlrGWGhIQRGxtHt66dSEhI5K+/zuiiaQAkJ6dw8/odGjSuo9qmUCho0LgOnlc1L0zmefW6WjxAo6Z1tcZrctPrNklJyTRoklFOiVLFKFykIJ7uupuXNiU5hTs3fKjTKGMqCoVCQe2GNbjhrnlRyhset6jdSH1O3rqNa3HD/e17DyqTU4m58QD7Rq/Mr65QYN+oElHuvhpfE+VxTz0esG9SRWu8JvGBoSQ8i8C8VEG17eYlXIh/rLsfOXIsD27Z1vT5P3HixCy7dnBwQF9fn+DgYLXtwcHBuLhonoLGxcUlW/H/dJA/fPiQ48ePq0aR/1NG5oVBU1JSiIiI0Lrfd0Fe5e5y1prXynhVSnIK92/6U7lBxvoICoWCyg2q4Ovpo/E1vp4+avEAVRq5quJDHgUTGRJBpVdiTC1MKeVaBh8NZUaHRZMQl0D9jxuSlJicZb7zfyu/cpuZWfoxzHxHVJoyDT0dLoyoTE4h9oY/Vg1fOSYKBVYNK/PCQ/MxjPXwUY8HrBtX5YVH9j8b4274k5aUrFaOScmCGBd20rrfXElLJS0oAL2PXp2PWoFesfKkPdF8LZX2xB/9j9Tnr9YrVpHUJ/452/c/HeSpKSTuXQapebBYc2oKaU/vo1+ycsY2hQL9kpVJC9R8PNICfdXjAf2SVUh7lP3jB6SPIO87FVJTSNg2D1KSc1r7N0tJIfW+DwaVX7neVygwrFyDFC0Laqb43lKPBwyr1Hw/FuCU6VaEEEII8QExyM+dT58+/bXPT548GX19/dfGGBsbY2xsrLZNT5G9L3O/rN/D1MUTuHvDl1vX7tBjYBdMTE04vOsIANOWTiT0WSirf9gAwO6Ne1n16xJ6Du7Khb8u0bJzc8pVKcsP4xaqyrSyscS5kBMOL0eAFS1ZFIDwkAjVfOZ2jrbYO9lRuFghAEqWK0FcbBzBT0KIiVKfB/rfurThTzovHMyzGw94et2f2v3aYmhmzPU9pwHovGgIz4Mi+Xv+LgCubD5C711TqDuwPff+vkbFj+tRsHIJfp+wUVWmibU51oUcsHS2AcC+RPoIwhehUcSGRqsemcU8DSPqkeZRcLm1eOl6Nm9cjIfnDa5evcb/hg3E3NyUn7akt2fzpqU8ffqMyVN+AGD58o38feJXRo4YzB9//kX3bp2pUaMKQ74Zpypz2fINTJr4P+753Scg4BEzZ4zl6dNgfvvtqCrmm6+/4uJFd17ExtGyRSPm/TCVSZO/Jzpa8yix3NqwaisLV87mhtdtrnvepN/gXpiZmbJnxwEAFq2aQ9CzYObPWpbe3rXb2XVoEwO/6c3fx8/w8SftqOxakQkjv1OVaW1jRaHCBXB2SR9RWKJUMSB9BHloSDjPn79g1/b9TJk1hqjIaJ4/f8F3P0zE44oX13TYSQ6wbe0uvls6mdvX7+J97TafD+yGqZkJv+38HYBZy6cQ8iyM5d+vAeCX9btZv38lXw7pwdm/LtDGrSUVqpZj1th5qjKtbCxxKeSCk0v6e7BYqX/eg+Gqu0TsHe2wd7KnaLHCAJQuX5LYF3EEPQnS6XswYM3vVF72NdFe94m+5kexQe3RNzPmyc7091/l5d+QGBSB75ydADxc9ye1D0yj2JAOhP51jQJu9bGuWoJbYzJ+XDK0McekkAPGLul3tfzTGZ4YEqWaz/zBqkOUGtuV57ce8tw7gILdm2BeqhDX+i/RWdveBpo+/zUxMjKiRo0anDhxAjc3NyC9I/DEiRMMHTpU42vq1avHiRMnGDFihGrb8ePHqVevnurvfzrI7927x8mTJ7G3t89SRlRUFB4eHtSokf7jzt9//01aWhp16qj/mPUuyavcra94/Wv+cXjDb3y7cDj+N/zwu36PDv0+xtjMhJN70ucmHrpoBBFB4eyYnz7l1++bDzFz1xw6DuyM59/uNPi4ESUrl2TthJWqMn/feIjPhnUj6MEzQh4F033050SGRHD1WMYCxm37tMfH4y4JsQlUaeTKl5O+YvsPW4mLic1WvXMiP3LbxUvuREZGs3nTEmbPWUJ8fAID+n1O8WJF+OPPEzptX/D6gxRf/D9ib/gTe+0ezgM7omdqQtiu9P0UX/o/kp9F8PiHbenxGw9T9tfZOA/uRPRfHth1bohZlZIEjMu4c0PfxgKjQg4YOaeP6DUtmX6NlRwSRUpoFKnP4wjbeYIi0/uSEvWC1OdxfDR7IC/c7xLrmcPO2jdIuXoMow4DSAsKIO3ZfQxqtkZhaEzKzfSFU406DED5PIrkM7+mx3scx7jneAxqtSHV/zoG5eug51KMpCM/ZRRqYo7Cyg6FRfpnv55dAdJIH4VObEx6B3n3MSgMjEg8vA6MTdIfAHHPQam7zsnk84cx/uxb0p74k/rYD8P6HVAYGZPscTK9fV2GooyJIPnYjvT4i79jMmAmBg06kurjiUGVBugVKknigbUZhZpaoGfjgMIyvX0Kh4LoAcrnUekj1I1NMflqCgojYxL2LENhbJa+MCmkj9DX4VSLCYf3YP7tRFL9fUjxu4NJhy5gbELSyT8BMBs6kbSIMBJ2rE+P/30vljOXYtyxG8melzBq0Bz9kmWJXZvx/UBhYYmegzMK2/Q8oVewCABpUREoX444V9jYoWdjh55L+rmrX7Q4yoR40sKCUb7Q7fcDIYQQQgiRVb52kr9JeHg406dPZ9OmTXlS/omDJ7G1s2bAmK+wd7Tj3i1/RvYaT+TLxTydCzqpjai66X6L6UNnM2hcP4aMH8CjB08Y338q930CVDENW9dn6uIJqr9nr54GwIaFP7Fx0RYAPvmyEwNGf6WKWbM/vYNz1sgf+GN3RkesLtw+fAkze0uajOqChaM1wbcfsqP3PGLD0jtzrQraq82n+tjjHvv/t5JmY7rSbGw3IgKC2D1oEaG+GVM3lGlVg84LB6v+/mzlMABOL97LmSX7dFr/N9mz5yCODnbMmDYGFxdHrl+/RYeOvQh5Ob1I0SIF1Y7hxUvu9Oo9lO9mjmP2rPHc83vAZ136c+tWxiiyBT+uwtzcjDWr5mNjY8X581fp8HEvtbmOa9WqxvRpY7CwMOOujz9ffzue7dv36rx9hw8cxd7BllETvsHRyYHb3j707vY1YS87ewsWclFrn8fV6/xv0ATGTB7G2Cn/I+B+IIO+HI7v3YzRa63aNWXhitmqv1duXADA4nmrWTI/vcNh1uT5KNPSWPPTIoyMjDhz8jxTxs7RefuO/XYCW3sbvh43AHtHO3xu3ePbnqNVC+q6FHIm7ZXz87q7N5O+mcG34wcxdOJgAh88ZlTfifjffaCKadKmEd8tzZjWZ97a9B8I1vy4kbU/pn+WdOnjxpAx/VUxm35bBcC04XM4tOsPnbUv6LeLGNlbUXpcV4ydbIi59RD3nj+oOrNNCzmojaqKcvfl+tfLKTOhO2Um9SD2QRCeX/3Ii7sZ7z+nNjWpvOxr1d+u64YD4LfgV/x+TO9webjuT/SMDSn3XW8Mbc15fiuQq93mEP9QfWT0fyqf14oYNWoUffr0oWbNmtSuXZslS5YQGxtL3759AejduzeFChVSTdcyfPhwmjRpwsKFC+nQoQM7d+7E3d2ddevSf7BITk6mS5cueHp6cvjwYVJTU1XzjNvZ2WFkZET58uVp27YtAwcOZM2aNSQnJzN06FB69OhBwYIFNVf0PZDXufvC4XNY2VvRfdTn2DjaEnD7AXN6zyT65UKQDgUd1G7p9/W4y9L/LaTnmF58PvZLngU8Zf6guTzyzZge67c1+zAxM2Hw3G8wszLnrvsd5vSeSXJixkjVUlXL0G1kT0zMTHni/5h1E1dxZv+pPGljfuS28PBIOnT8glnfjef40d0YGhpw+7Yvn37Wjxs3dDsiNuLgeQzsrCg0pgeGjrbE3XqAb6/vSHl5DI0KOqp9Nr5w9+H+0MUUGvc5hcf3IuHBM/z6/0C8T8YxtGldixKL/6f6u+TqMQA8WbiTp4vSf1wInLGJImlKSq0bh8LYkJhTXgRMeqWjVkdS714h2cwSw4ZuKMytSQsJJHH3IohLv/ZSWNmrdVqnPfEj6dBaDBt9imHjz1BGBpO4bznKsCeqGP1Srhh3GKD627hzeh5IPneA5PO/oef8EfoFSwJgOni+Wn3iV49BGaO7aclSb14gydwKwxbdMbK0Ie1ZAAk/zYGX08PoWTuQ9mr7An1J3L0Uo5Y9MWr9OcrwZyRun48y5JEqxqBcTYy7fKv626THSACSTuwm+e896BUsjn7RMgCYjV6hVp+4Bd+gjNLdIIzkCyeJt7LBpHtf9GzsSA3w48WccSij069N9Byc1Y5fqu8tYpfOwrRnf0w/H0Dasye8mD+FtEcZ1yaGNRtg/m3G9wOLkek/Nsbv/omEPT8BYNyqE6bdvlLFWM5aDkDsyh9IOnVEZ+3LEVnnSQghhBAfEIVSqcOhJTp2/fp1qlevTmpqzuYbrFeoWR7V6O3Q3uD97Vz5x8xnp/K7CnmqkKX9m4PeYXaGlm8OeofNVRbJ7yrkqbbBO3VeZuzsXjov03zKthzFr1ixggULFhAUFISrqyvLli1Tjehu2rQpxYoV46efflLF79mzhylTphAQEEDp0qWZP38+7du3ByAgIIDixYtr3M/Jkydp2rQpABEREQwdOpRDhw6hp6fHZ599xrJly7CwsMh5g98Ruc3dXT/qnEc1ejvsf+ae31XIcxcdXz/Nzruu4v9s8rsKeUoZ8yK/q5Cnknx1ezfj28Z2zymdl/k25G4hhBBCiP9Kvo4kP3jw4Guff3VhMCGEEO+wt2Ae0qFDh2qdXuXUqVNZtnXt2pWuXTUvWFisWDGy8xuznZ0dO3bsyFE933aSu4UQ4gPxFuRuIYQQQoj/Sr52kru5uaFQKF7b0aBQKP7DGgkhhMgTaXLL9vtCcrcQQnwgJHcLIYQQ4gOSvRUu80iBAgXYt28faWlpGh+enp75WT0hhBBCZCK5WwghhBBCCCHE+yZfO8lr1KiBh4eH1uffNFJNCCHEOyJNqfuHyBeSu4UQ4gMhuVsIIYQQH5B8nW5l7NixxMbGan2+VKlSnDx58j+skRBCiDyhlFu23xeSu4UQ4gMhuVsIIYQQH5B87SRv1KjRa583NzenSZMm/1FthBBCCPEmkruFEEIIIYQQQrxv8rWTXAghxAdCbrEWQggh3i2Su4UQQgjxAcnXOcmFEEIIIYQQQgghhBBCiPwkI8mFEELkOWWazGsqhBBCvEskdwshhBDiQyKd5EIIIfKe3LIthBBCvFskdwshhBDiAyLTrQghhBBCCCGEEEIIIYT4YMlIciGEEHlPRqMJIYQQ7xbJ3UIIIYT4gMhIciGEEEIIIYQQQgghhBAfLBlJLoQQIu8pZfEvIYQQ4p0iuVsIIYQQHxDpJBdCCJH35JZtIYQQ4t0iuVsIIYQQHxCZbkUIIYQQQgghhBBCCCHEB0tGkgshhMhzShmNJoQQQrxTJHcLIYQQ4kMineRCCCHynnzRFkIIId4tkruFEEII8QGR6VaEEEIIIYQQQgghhBBCfLBkJLkQQoi8l5aW3zUQQgghRE5I7hZCCCHEB0RGkgshhBBCCCGEEEIIIYT4YMlIciGEEHlP5jUVQggh3i2Su4UQQgjxAZFOciGEEHlPvmgLIYQQ7xbJ3UIIIYT4gGS7k/zgwYPZLrRTp065qowQQgghdEdytxBCCCGEEEII8WbZ7iR3c3NT+1uhUKBUKtX+/kdqauq/r5kQQoj3xqv5Qvx3JHcLIYTILcndQgghhPiQZHvhzrS0NNXj2LFjuLq68ueffxIVFUVUVBR//PEH1atX58iRI3lZXyGEEO+iNKXuH+KNJHcLIYTINcndQgghhPiA5GpO8hEjRrBmzRoaNmyo2tamTRvMzMwYNGgQd+7c0VkFhRBCCPHvSe4WQgghhBBCCCE0y1Unub+/PzY2Nlm2W1tbExAQ8C+rJIQQ4r0jo8fyneRuIYQQOSK5WwghhBAfkGxPt/KqWrVqMWrUKIKDg1XbgoODGTt2LLVr19ZZ5YQQQgihG5K7hRBCCCGEEEIIzXI1knzTpk188sknFC1alCJFigDw6NEjSpcuzYEDB3RZv1zxe/E0v6uQpwJtHfK7CnmulXOV/K5CnvKND35z0DvM2sA0v6uQp7brJ+V3FfJU2zwoUymj0fLd2567J6bldw3y1gi7evldhTy3wVDx5qB3mPPq9/uz/ynv9+f0avdN+V2Fd47kbiGEEEJ8SHLVSV6qVClu3LjB8ePHuXv3LgDly5enZcuWKBTv9xckIYQQuSBftPOd5G4hhBA5IrlbCCGEEB+QXHWSAygUClq3bk3r1q11WR8hhBBC5BHJ3UIIIYQQQgghRFbZ7iRftmxZtgv93//+l6vKCCGEeE+951NpvK0kdwshhMg1yd1CCCGE+IBku5N88eLF2YpTKBTyRVsIIYQamdc0f0juFkIIkVuSu4UQQgjxIcl2J/mDBw/ysh5CCCGE0DHJ3UIIIYQQQgghxJvlek7yfyiV6SMMZNEvIYQQWslotLeK5G4hhBBvJLlbCCGEEB8Qvdy+cOvWrVSuXBlTU1NMTU2pUqUKP//8sy7rJoQQQggdktwthBBCCCGEEEJklauR5IsWLWLq1KkMHTqUBg0aAHDu3DmGDBlCWFgYI0eO1GklhRBCvONk8a98J7lbCCFEjkjuFkIIIcQHJFed5MuXL2f16tX07t1bta1Tp05UrFiRGTNmyBdtIYQQamTxr/wnuVsIIUROSO4WQgghxIckV9OtPHv2jPr162fZXr9+fZ49e/avKyWEEEII3ZLcLYQQQgghhBBCaJarTvJSpUqxe/fuLNt37dpF6dKl/3WlhBBCvGfS8uAhckRytxBCiByR3C2EEEKID0iupluZOXMm3bt358yZM6p5Tc+fP8+JEyc0fgEXQgjxYZNbtvOf5G4hhBA5IblbCCGEEB+SXI0k/+yzz7h8+TIODg4cOHCAAwcO4ODgwJUrV/jkk090XUchhBBC/EuSu4UQQgghhBBCCM1yNZIcoEaNGmzbtk2XdRFCCPG+klus3wqSu4UQQmSb5G4hhBBCfEBy3UmelpaGn58fISEhpKWpX0E1btz4X1dMCCGEELoluVsIIYQQQgghhMgqV9OtXLp0iVKlSlG+fHkaN25M06ZNVY9mzZrpuo5CCCHecco03T9yauXKlRQrVgwTExPq1KnDlStXXhu/Z88eypUrh4mJCZUrV+aPP/5Qe37fvn20bt0ae3t7FAoFXl5eWcoICgriyy+/xMXFBXNzc6pXr87evXtzXnkdkNwthBAiJ96G3C2EEEII8V/JVSf5kCFDqFmzJt7e3kRERBAZGal6RERE6LqOQggh3nVpefDIgV27djFq1CimT5+Op6cnVatWpU2bNoSEhGiMv3DhAj179qR///5cu3YNNzc33Nzc8Pb2VsXExsbSsGFD5s2bp3W/vXv3xsfHh4MHD3Lz5k0+/fRTunXrxrVr13LWAB2Q3C2EECJH8jl3CyGEEEL8lxRKpTLHy5abm5tz/fp1SpUqlRd1+tccrcvmdxXylJttlfyuQp57nPoiv6uQp3zjg/O7CnmqiIldflchTxXRt8rvKuSpnx/u03mZ4R2a6LxM+99PZzu2Tp061KpVixUrVgDp044UKVKEYcOGMWHChCzx3bt3JzY2lsOHD6u21a1bF1dXV9asWaMWGxAQQPHixbl27Rqurq5qz1lYWLB69Wq+/PLLjHrb2zNv3jwGDBiQ7frrwtueuz2LdM7vKuSp+GTD/K5CnttqosjvKuQpZ4zyuwp56imJ+V2FPLXafX5+VyFPGTqU0HmZ+Z27hRBCCCH+S7kaSV6nTh38/Px0XRchhBDvqfy8ZTspKQkPDw9atmyp2qanp0fLli25ePGixtdcvHhRLR6gTZs2WuO1qV+/Prt27SIiIoK0tDR27txJQkICTZs2zVE5uiC5WwghRE7IdCtCCCGE+JBke+HOGzduqP5/2LBhjB49mqCgICpXroyhofroqCpV3v+RzkIIIfJXYmIiiYnqIx+NjY0xNjZW2xYWFkZqairOzs5q252dnbl7967GsoOCgjTGBwUF5aiOu3fvpnv37tjb22NgYICZmRn79+//z0ZzS+4WQgjxLlu5ciULFiwgKCiIqlWrsnz5cmrXrq01fs+ePUydOpWAgABKly7NvHnzaN++ver5ffv2sWbNGjw8PIiIiNB4F9i6devYsWMHnp6ePH/+nMjISGxsbPKohUIIIYR4W2S7k9zV1RWFQsGrs7P069dP9f//PKdQKEhNTdVtLYUQQrzb8mD02Ny5c5k5c6batunTpzNjxgzd7yyXpk6dSlRUFH/99RcODg4cOHCAbt26cfbsWSpXrpzn+5fcLYQQItfyeeT3P+uJrFmzhjp16rBkyRLatGmDj48PTk5OWeL/WU9k7ty5dOzYkR07duDm5oanpyeVKlUCMtYT6datGwMHDtS437i4ONq2bUvbtm2ZOHFinrZRCCGEEG+PbHeSP3jwIC/rIYQQ4j2WF7dYT5w4kVGjRqltyzyKHMDBwQF9fX2Cg9XXAggODsbFxUVj2S4uLjmK18Tf358VK1bg7e1NxYoVAahatSpnz55l5cqVWeY2zwuSu4UQQuRWfk+PsmjRIgYOHEjfvn0BWLNmDb///jubNm3SuJ7I0qVLadu2LWPHjgVg1qxZHD9+nBUrVqhy7j9rhAQEBGjd74gRIwA4deqU7hojhBBCiLdetjvJP/roo7yshxBCCJEjmqZW0cTIyIgaNWpw4sQJ3NzcgPSFO0+cOMHQoUM1vqZevXqcOHFC9UUZ4Pjx49SrVy/b9YuLiwPS5z9/lb6+Pmlp/03Pg+RuIYQQb5PsTpX2z3oir47kzs56Ipl/PG/Tpg0HDhzQTeWFEEII8V7L1cKdW7Zs4ffff1f9PW7cOGxsbKhfvz4PHz7UWeWEEEK8H/J78a9Ro0axfv16tmzZwp07d/j666+JjY1VjU7r3bu32hfx4cOHc+TIERYuXMjdu3eZMWMG7u7uap3qEREReHl5cfv2bQB8fHzw8vJSzVterlw5SpUqxeDBg7ly5Qr+/v4sXLiQ48ePqzrr/0uSu4UQQuREXuTuuXPnYm1trfaYO3duln2/bj0RbeuD6Go9ESGEEEJ8mHLVSf79999jamoKpP9iv2LFCubPn4+DgwMjR47UaQWFEEK8+/K7k7x79+78+OOPTJs2DVdXV7y8vDhy5Ijqy3RgYCDPnj1TxdevX58dO3awbt06qlatyq+//sqBAwdUc5oCHDx4kGrVqtGhQwcAevToQbVq1VS3dBsaGvLHH3/g6OjIxx9/TJUqVdi6dStbtmxRW0TsvyK5WwghRE7kRe6eOHEi0dHRag+Z91sIIYQQb4NsT7fyqkePHlGqVCkADhw4QJcuXRg0aBANGjSgadOmuqyfEEIIoRNDhw7VOr2KpnlHu3btSteuXbWW99VXX/HVV1+9dp+lS5dm7969OalmnpHcLYQQIr9ld6q0/FpPRAghhBAfrlyNJLewsCA8PByAY8eO0apVKwBMTEyIj4/XXe2EEEK8H5QK3T9EjkjuFkIIkSP5mLtfXU/kH/+sJ6JtfZB/1hN5VU7XExFCCCHEhytXI8lbtWrFgAEDqFatGr6+vqrbxm/dukWxYsV0Wb8812/A53z7v/44OTtyy/suE8fO4prnTa3xndzaMmHycIoULcR9/wBmTf+Rv46fUT3f4eNW9OnXg6quFbGzs6VZw85437yrVoaxsRHfzZmA22ftMTYy4uTf5xg3aiahoeF50samX7ahzeBOWDva8OjOQ36ZvomA635a42u0r0vn0T1wKOxI8IMg9v6wDe9T11TPV2tTmyZftOajyiWwsLXku/ZjeXQ7QK2MXt8PonyDytg425EYm4C/pw97f9hGkP9TnbevY5+OdBncBVtHW+7fuc/qaavx9fLVGt+wQ0N6j+mNc2FnngQ8YfP3m7l68qrq+fpt69Phyw6UqlwKK1srvm3zLfdv31c9b2FjwZejvqR64+o4FnIkOjyai0cvsvXHrcQ9j9N5+3r168bAob1xdLLnzi1fZk6Yz41rt7TGt+vUkpETv6ZwkYIE3A9k/nfLOPXXedXzrTs05/OvPqNS1fLY2tnQsWkP7nir/3sZGRsx6btRdPykNUZGRpw9eZFp4+YSHhqh8/a59elEjyHdsHO0w++OP8umruCul4/W+CYdGtN/7Fe4FHbhccAT1n6/nst/X1E936hdQzr16kiZKmWwtrViQOvB+N32Vyuj4xcdaOnWnNKVSmFuaU7HCp15EROr87YBtOzdlvaD3F6+/wLYOn0D91/z/qvdvh6fje6JQ2EnggOeseuHn7l+0lP1fM22dWj+RRuKVS6Jpa0lk9uNIvCV95+5tQWfjupB5UZVsS/kQEx4DJ7HrvDrwl+Iz4PzU7w73qfc7dCnPc6D3TB0tCX+TgCPpq0jzuue1nibDvUpOOYLjAo7kRjwlCffbyXmpEfG823r4vBlW8wql8TA1oo7bUYQf/uBWhkKY0MKT+2HbaeGKIwMiTl9jUeT15ASFp0nbXTp25ZC33TCyNGG2NsPuT95Iy+uaf/ssP+4HkXH9cCkiCPxD57xcPY2Ik9k5G679nVw6d0aiyolMLSzxKvFGGJvBWRpY/EZfXDo3AA9YwMiT17n/oT1JOdBG5t+2YZWL69NHt95yM43XJtUf3ltYl/YkZAHQezLdG0C8PHI7jTq2QJTK3P83e+yY8p6QgIy5iIuUrE4n07oRbGqJUlLTePan5fZM3sLiXEJOm9f7S9b0WBwBywcrQm+E8jv07fw5Pp9rfEV29em+eiu2BR2IOJBMMd++IV7p66rxTQf+Rk1ejbDxMqcQHdfDk3ZRERAxqjZAhWL0XpCDwpWLYEyNY3bf17lyOxtJMUlZt7dv9bsy7aZri038uC115b1cFNdWz5j7w/buJnp+HUe2Z1GPVtiZmWGn7sP26asUzt+RSsWp8uEXhSrWoq01DQ8/rzE7jw6fr/sPcTmHb8SFhFJ2VIlmDTyaypXKKs1/ujfZ1mxfitPgoL5qHAhRn7dl8b1a6ueP37qPLsP/M5tHz+iY57z6+YVlCtTUq2MmfOXcfHqNULDIjAzM8G1UgVGftOPEh8V0Xn73hWjRo2iT58+1KxZk9q1a7NkyZIs64kUKlRINaf58OHDadKkCQsXLqRDhw7s3LkTd3d31q1bpyozIiKCwMBAnj5N/07i45N+zeni4qIacR4UFERQUBB+funn9M2bN7G0tKRo0aLY2dn9Z+0XQgghxH8rVyPJV65cSb169QgNDWXv3r3Y29sD4OHhQc+ePXNUVlJSErt372bkyJH07NmTnj17MnLkSPbs2UNSUlJuqpdtbp+247vvJ/LjvJW0aPwJt7zvsnv/RhwcNF/81KpdjbUbF7L9519p3siNP38/wZYdKylXvrQqxszMjMsXPZk1/Uet+501dxKt2zajf58RdOrwJc4uTvy0bYXO2wdQs2N9uk3pw6Gle5jVYTyPbz9kxNbJWNpbaYwvWb0MA5eN4Nyuv/mu/Ti8jl3h23XjKFgm4wLd2MwEP/e77P1hm9b9Prx5n5/GrmJayxEs6T0bUDBi61QUerk65bRq/HFjBk0dxPYl2xnWfhgPbj9g9s+zsba31hhfvkZ5JqyYwNGdRxnabigXj15k6oapfFT2I1WMiZkJt67cYtP3mzSWYe9sj52zHRtmb+Drll+zaNQiajStwcgFup/Tt4NbaybNGsWyBevo1Pxz7t66x097VmLvYKsxvnqtKixZ9z17tv/Gx80+5/gfp1i9dRFlymV8ETMzM8X9shfzv1umdb9TZo+mRZtGDOs/ns87D8TJxZHVP2k/p3Or2cdN+WbaEH5a/DMD2w3B//Z9Fmz7ARt7G43xFWtUYNrKyfy+8wgD2g7h3JHzzN4wk+Jli6liTMxMuHnVm3Xfr9e6XxMTY66cusr2Fb/ouEXq6nRswOdT+rJ/6W6mdhxD4J0Axv08DSst52fpGmX5ZvkoTu8+wdQOo/E4doUR68ZTuExRVYyxqQm+V++w64efNZZh62yHrbMtv8zZwsRWI1g/ZjmVm1RjwPxv86SN2ZXfc5KL9yd3237ckMJT+/FsyS7uth9F/O0HlPp5BgZa3lfmNcpRfMUYwnb+xd12I4k6epkSGyZiUjbjfaVnZsKLK3d48v1WrfstPL0/1i1rcX/IfHy7TsbQ2Y4S6/JmHl2HzvUpPqMPjxbuwav1OGJvBVDxlykYOmjO3ZY1y1J29QhCfjmBV6uxRPx5lXKbx2FWLiN365sZ8/zKHR7O1p67i3/3FXatauAzcCE3P5mOkYst5TaN1Xn7anasT5cpffh96R7mvLw2+d9rrk1KVC/DgGUjOL/rb2a/vDb5OtO1SZshnWnetx3bJ6/jB7eJJMYn8r+tUzAwNgTA2smWkdunEfowiB/cJrGszxwKlClMnx91/9lYqWNd2k75glNL97GmwxSCbgfSe+sEzLW0r0j10nRZNhTPXadY3X4yd46503PdKJzKFFbFNBzSkTp923Bo8mbWuU0jKT6R3lsnqNpn6WRDn+0TCX8YzDq36WztMx+nMoX55MchOm9frVeuLb/rMI5HtwMYsXXKa64tyzJo2QjO7TrBd+3Hcu3Y1SzXlm2HuNGib3u2TV7H926TSIxPZOTWqWrHb/T2aYQ8DGKO20SW9JlNoTJF6JsHx+/Pv04zf/k6vu73BXs2LadsqeIMHjWF8MgojfHXbt5m3Iwf+KRjG/ZsXkHzRvX438RZ3LsfoIqJT0igepWKjPy6n9b9VihbitmTR3FwxzrWLpqDUqlk0MjJpKam6riF2ZffuTs/1hMBWLNmDdWqVWPgwIEANG7cmGrVqnHw4MHc/lMKIYQQ4h2gUCqVyvzauZ+fH23atOHp06fUqVNHdcETHBzM5cuXKVy4MH/++adqDtXscrTWPtLjVUdO7MbL8yYTxs4CQKFQcP32aTas+5lli7N2sK3fvBgzM1O+6J7xhePPv3bhffMuY0dOV4stUrQQnjf/zjKS3NLKgrv+FxkyYAyHfjsKQKnSJbjo/idtW3TDw1191JAmbrZVstU+gIkHvifguj+/TN+oauO8i2v4e8ufHFl9IEv8oBUjMTY1Znn/HzLK2D+HR7cD2DZZ/d/EvrAjP5xbpXEkeWaFyhVlxpGFTGo8lNDA4NfGAjxOffHmxgGLDy7G97ovq6euBtLbt/XKVg5uPsieVXuyxE9YNQETUxNm9J2RUcZvi/G/5c+KSeo/VDgVdmLLxS1ZRpJr0rBDQ8YtHYdbWTfSUt/8DcA3/s3/BgB7j27hxrXbzJwwD0hv37kbf7J1/U7WLvspS/yyDT9gambKwM+Hq7b9emQLd7x9mDrme7XYQkUKcOba71lGkltYWnDV5wQjB0/iyKH0W1ZLlCrG8Uv7+KxNH7w8tN9p8Y8iJtkbZbPq0HJ8rvuwdMoKVft2X/2F/ZsPsGPlzizx01ZNwdTMhIlfTcko4+By/G75sWjiUrVYl8LO7Ly0XeNI8n+41qvKkj0LczySvIi+5o6AzGYc+IH7N/zYOm0DkN6+JZfWcfynPzi8en+W+G9XjMbYzJhF/TKO1fT9P/Dw9gN+mrxWLdahsCOLz6/NMpJck9rt6zFkyQgGlO+ZrfPz54f7stG6nHnWsJnOyyxw7qTOyxRvlle527NI52zFlT24gNjr93g89eXIQIWCSlc2Err5d4JXZZ3/vfiqseiZGuPfd3ZGGb/NJ+7WAx5NWq0Wa1TYiUoX12cZSa5naUYVr60EDFtE1B8XADAuWYiKp1Zxt9NY4q5pv3vpH/HJhtlqH0CVP+bywsuP+5M2qtpY03MNzzb+yZMVB7LEl107Ej0zE+58OTejjN+/J9Y7AP/x69RijYs4UvPq6iwjyfUtzah9ayO+3ywl/PAlAExLFaT6uWVcbz+RF57aR+r/Y6tJ9qZSmPDy2mTnK9cmcy+u4eSWPzmq4dpk4IqRGJkas/KVa5PxL69Ndry8Npl/ZR3H1x/i+PpDAJhYmvGj+3p+GrMS90MXaNSzJZ1GdWdc7UH8c+lbsGxRph9dyJQmwwh9GJRlv5k5Y5St9g06MJMn1+/z+/QtqvaNvriMy1uOcXb1oSzxXVcMw8jUmO39M36MHrh/JkG3H3JocvoP9mOvrODC+j84v/4PAIwtTRnnvor9Y9bifegSNXo2o8Woriyo/a2qfU5lizD06A8saTKKiIdvvu54SvZGnE86MJeA637seOX4zX95bfmnhuM3eMVIjExNWN4/4/ycuP/7l9eW6efnj1fWc2z9IY6tT++ENLU0Y5H7BjaNWcnVQ+dp3LMlbqN6MLr2QFX7CpUtysyji5jUZCgh2Th+q93nZ6t9PQeOoFK5Mkwe/Q2QPsVHy09683mXTgz4sluW+NFT5xKfkMCqBTNV2z4fOIKypUsyfdwwtdgnz4Jp0+UrjSPJM/Pxe8Bnfb7hj10bKVq44BvrbehQIjvNyxHJ3UIIIYT4kOR6WO/Zs2fp1asX9evX58mTJwD8/PPPnDt3LttlfP3111SuXJng4GBOnTrFrl272LVrF6dOnSI4OJiKFSvy7bd5M/rR0NCQqq4VOX3qgmqbUqnkzKkL1KxVTeNratZy5cypi2rbTp44R81artneb1XXShgZGant1+/efR4FPqFm7eyXkx36hgZ8VKkEd87fUG1TKpXcOX+DktXLaHxNiWpluP1KPMCtM9cpoSU+O4xMjWnQtRmhgcFEPNPdlDIGhgaUrlwar3Neqm1KpRKvs16Ur1Fe42vKVy+vFg/gcdpDa3x2mVuaE/ciLlsdkNllaGhAparluXD6smqbUqnkwunLVKul+YeSajUrc/6VeICzJy9SrWb2f1ip7FoeIyNDtXLu+wXw5NEzrfvNDQNDA8pWLoPH2YypRJRKJR5nPalQvYLG11SsUUEtHuDK6atUqKE5Pj/pGxpQrHJJbp1Tf//dOneDUtU1/5BXqnoZtXiAm2euUVpLfHaZWpkTr+PzU7yb3vXcrTA0wKxySZ6fe+UHZaWS52evY15D8/vEvHpZYs6p/wAdc/qa1nhNzCqXRM/IUG2/if5PSHwcgkWNcjlrxBsoDA2wqFKCqDOvfBYolUSfvYllTc11tqxRRj0eiDzlhWXN7Oduiyol0DMyVCsn3u8pCY9DsdKy39zQNzSgqIZrk7vnb2i91ihRrQx3M12b3H7l2sShiBPWTrbcOZ/xI27C8zgeePlR4uXnp4GRASnJKbw6NiQ5If2uh1K1dHcM9Q31KVCpOP7nvVXblEol/ue9KVy9tMbXFKlWivuvxAP4nblBkerpPzTZFnHE0skW//MZU60lPo/niZc/RV6WaWBkSGqm9qW8bF/RWro9fh9VKqF2rZh+bXlT9W+dWYlqZdSON8CtM16qa1GHIk7YONmqxcQ/j+O+1z1VjIGR4X9y/JKTk7ntc4+6r1zb6+npUbemK9e972h8zfVbd6hX01VtW/06Nbh+S3N8dsTFJ3Dg92MULuhCAWfHXJcjhBBCCCGyL1ed5Hv37qVNmzaYmpri6elJYmL6yJPo6Gi+//77N7w6w/nz55k9ezZWVllHZVpZWTFr1izOnj2bmyq+kZ29LQYGBoSGqHfahoSG4+TsoPE1Ts4OhISEqW0LfU28xjKcHEhMTCIm+rmGcnR7EWxha4m+gT4xmeYSjQmNxsrRRuNrrB1teJ4lPgprB83xr9O0V2uW3/qZlXe2UalpNRb3mkVqckqOy9HGys4KfQN9IkMj1bZHhkVi66h5OhJbR1siw7Ifn6162FrRc3hP/tzxZ67L0MTW3gYDAwPCMs0DHhYagaOTvcbXODg5EJ5pbvuwkHCt8ZrLsCcxMYnnMeqj+cNCc1bOm1jbWaNvoE+EhuNn56T5eNg52hKR+fiFRmHn+PbND2n58v0XHRaltj0mLAobLe8/G0ebLPHRYdFYa4nPDgtbS9yGdeXkL8dzXYYu5Pct2+L9yN0GdlYoDPRJCY1S254SFoWhls9xA0cbUjK9r5JfE6+JoZMtaYnJpGa64yQlLAqDf/H+1LgvO0sUBvokh6rn4qTQKIycNO/L0MmG5Ez/Jsmh0RhqiddWRnob1dcuSA6NylE5b/LPtUnWaw3tn3VWjjYarmUyrk3+uaaJyfRvEBMapSrz7gVvrB1taD2oE/qGBphZmfPJ+C8AsNZh+8xeti82U31jQ2OwdNQ8JZCFow0vMsW/CI3G4mX7LF624UWohpiXz92/cAsLR2saDOqAvqE+JlZmtBrfA0ifikVXtF9bRmk9ftaONsRkzoWh0arjZ/3yvZj1+EW/cvxuYuVoQ5tXjt+nquOX+2u4zCKjYkhNTcPeTr1MeztbwiIiNb4mLDwyS7yDnS1h4ZrjX2fnvsPUavkJtVt+wrlL7qxbPAdDw+zfhaJrkruFEEII8SHJVSf57NmzWbNmDevXr1e7cGvQoAGenp6veaU6GxsbAgICtD4fEBCAjY3Na8tITEwkJiZG7aGUK7C3wuXfzjGrw1jmd5tG8P1nDF45SjW35PvCzMKMmVtmEngvkG2LtM/zKkR+MLEwZczmyTzxe8T+xbvytS5KpULnD5Ezb3vuTlLm37y74v337N5jNo9eScuBH7P8zjbmX11P+KMQokOjUKbl28yDOhN67wn7Rq+l/sD2TLmzmXFXVxH5KITnoVEo09796+Kn9x6zafQKWg/8mFV3trPw6gbCHoUQHRr5Xhy/f3Ro3YxfN6/gp5Xz+ahIIcZMm0tiYt6u8/A6kruFEEII8SExyM2LfHx8aNy4cZbt1tbWREVFZbucAQMG0Lt3b6ZOnUqLFi3U5jU9ceIEs2fPZtiwYa8tY+7cucycOVNtm6mRHeYmrx/dHREeSUpKSpaRsU6O9oQEh2l8TUhwGE5O6uU6viZeYxkhYRgbG2Flbak2mjy9nNBsl5MdLyKfk5qSipWD+sglK0frLKN1/hEdGoVllviso1uzI/55HPHP4wgJCOL+tXssvb6Z6m1qc+Xg+RyXpUlMRAypKalZRoHbOthmGV3+j8jQSGwdsh//Oqbmpsz6eRbxL+KZNXAWqSm67eCJDI8iJSUFh0yjpB0c7bLcAfGPsJAw7B3Vz2kHJ3ut8ZrLCMfY2AhLKwu10eQOjjkr502iI6JJTUnFTsPxiwjRfDwiQiOxy3z8HG2IyDTa/m3w/OX7L/NdGFYONkRpef9Fabhrw9rBmmgt8a9jYm7CuK1TiY+NZ+mgeTo/P8W7523P3YMsyzDY+vXTJqRExKBMSc0yetvAwYZkLZ/jKaFRGGR6Xxm+Jl6T5JBI9IwN0bcyVxtNbuBgk2VU+7+VHPEcZUoqhplGHRs52pAUonlfySFRGGb6NzF0tCZZS7y2MtLbaKY2mtzQ0SZH5bzJP9cmWa81tH/WxYRGabiWybg2+eeaxsrRRu36xsrRRm3NlKsHz3H14DksHaxJiktEqVTSckDHbK2Vkl1xL9tnnqm+5o5WPM80EvwfL0KjsMgUb+FozYuX7Xvxsk0Wjtaq///n72e3H6r+vnnwAjcPXsDcwYrkuESUSqg/oD2RgSH/vmH/1FXrtaWN1uMXHRqFVeZc6GitOn7RL9+LmcuwcrRWO35XDp7jysFzWDlYk/jy+LXW8fGztbFCX1+P8EyjxsMjInGw0zxi3cHeNkt8WEQkDvY5H+FuaWGOpYU5HxUpRNWK5ajftisnzlygfaumOS5LCCGEEELkTK5Gkru4uODn55dl+7lz5yhRIvuLxnz33XeMHz+eBQsW4OrqSsGCBSlYsCCurq4sWLCA8ePHM2PGjNeWMXHiRKKjo9UeZsZvnnohOTmZ6163aNyknmqbQqGgUZN6uF+9pvE17le9aNSkrtq2Js3q437V6437+8d1L2+SkpLU9luyVHGKFC2E+5Xsl5MdqckpPPS+T/n6lVXbFAoF5etXxt9T8yJj96/5qsUDlG9Yhfta4rNLoUj/j4GR7kaSpySncO/mPVwbuL6yHwWuDV2546F5Hsg7nnfU4gGqNaqmNV4bMwsz5myfQ0pyCjP7zSQ5MTmn1X+j5OQUvK/foX7j2qptCoWCeo1rc+3qDY2vueZ+Uy0eoGGTOlxz1xyvyU2vOyQlJauVU7zURxQqUkDrfnMjJTkFn5u+VG9YXbVNoVBQo2E1bnve1viaWx63qd5Qfc2Amo1qcNtDc3x+Sk1OIeCmPxUaZMzjrlAoqNigCn6ePhpf4+fpS8UG6u+/So2qck9LvDYmFqaM2zadlKQUFvefmyfnZ07JLdv5723P3X2tNM/X/CplcgpxN/2xfOV9hUKBZcMqxHpofp/Eevpg9Wo8YNnIVWu8JnE3/UlLSlbbr3GJQhgXduKFx93XvDLnlMkpvLhxH+tGr3wWKBRYN6zMc3fNdX7u4YtNI/XPDpvGVXnunv3c/eLGfdKSktXKMS1ZEJPCjsRo2W9upCanEKjh2qRc/cparzXuX/Ol3GuuTcIehRAdEkm5+pVUz5tYmFLctRT3NXx+Pg+LJjEugZod65OcmMSdc7rLbanJqTzzfkCJ+hVV2xQKBSXqV+KxlsVPH13zU4sHKNmwEo8809+vkY9CeR4SqRZjbGFKIdeSPNJQZmxYDElxiVTqWJeUxCT8z3lnicktbdeW6cdP83mi6dqyQsOqqmvRsEchRIVEqsWYWJhSwrW0xuvVmJfHr1bHBiQnJnM705oD/4ahoSEVypbmsruXaltaWhqXPbyoWknz+jVVK5bnkoeX2raLV69RteK/W+9GqVSiVEJSUv7lcMndQgghhPiQ5Gok+cCBAxk+fDibNm1CoVDw9OlTLl68yJgxY5g6dWqOyho/fjzjx4/nwYMHBAWlr0zv4uJC8eLFs/V6Y2NjjI2N1bYpFNnr+1+zcjPLV8/D65o3nh43GPxNH8zMTfll2z4AVqyZR9CzYGbPXATAutVb+e2Pn/l6aF+OHz3NJ5+1x7VaJUYPn6Yq08bWmsKFC+Di4gRAqdLp7QgJDiMkJIznMS/Y/vNevpszgcjIaJ4/f8Hc+VO4ctkTD3fdXeT/4/iGw/Rb+C0BN/154OVHy/4dMDIz5vye9JXl+y0cSmRwBPvn7wDgxKbfGbNrJq0GdOTmSU9qfdyAYpVL8vPEtaoyzawtsC/koJoD0rlEQSB9pFBMaBQORZyo9XF9bp25wYuIGGxd7Gj79SckJyRx82T2b+nPjv3r9zN60Wju3biHj5cPbv3dMDY15vju9PmXRy8eTXhQOD/N+wmA3zb+xvw98/l00KdcOXGFJp2aULpKaZZNWKYq08LGAqeCTtg7p4/ILlyyMJA+Cj0yNFLVQW5sasyC4QswszTDzNIs/d8gPJo0Hd7WvGn1dhasmMlNr9tc97xF3yGfY2Zmyq+/HATgx5XfEfQshB9nrwDgp7U72HFwPf2/6cXJY+fo+GkbKrlWYPKo2aoyrW2sKFjYBWeX9DnwS5QqBkBoSDhhIeG8eP6CPdsPMHnWaKKjYnjxPJbpc8fheeU6Xh430aU96/YycfE4fK77cMfLhy4DPsXE1IQ/dx0BYOKS8YQFhbH+h40A7N24j6W/LqLboC5cOnGZ5p2bUbZKGRaOX6wq09LGEueCTti7pB+/IiWLABARGqGa/9zO0RY7RzsKFUs/d4uXK078i3iCn4bwPEp9vYB/488Nhxi0cBgPbvhx//o92vT7GGMzY87s+RuAwYv+R2RQOLvnbwfg2ObDTNo1i3YDO+H1twd1P25I8col2TRhjapM85fvP1vn9B8DC5QoBKS//6JDozCxMGX8z9MxMjVizfAlmFqaYfry/IwJj3kvbrsXufO2524jhX62Xhuy/jc+WjScuBt+xHndw7H/x+iZmhC++y8APlo8guSgcJ7O+zk9fuMhyuyZg9OgzkSfcMeuUyPMqpQkcMJKVZn6NhYYFXTE8OX7yqRk+vsqOTSSlNAo0p7HEb7rLwpN60dK1AtSX8RR5LtBvHC/S9y1f/cjsiZP1x6i9NKhvLjuz4trfhQc2AF9M2NCdqbn7tLLh5H0LJyH36fn7qfr/6DS/pkUHPIxkX954ODWEIuqJfAfm/HZYWBjgXEhB4xc0nO3aan0z7+kkCiSQ6NIfR5H8C9/U2zmV6REvSDleTwl5vQn5qoPL7R07ubWXxsO89XLa5MALz9avLw2ufDy2uSrhUOJCo7gQKZrk5avXJt8VLkk2165Njmx6XfaD/uMkIAgwh6F0Hl0d6KCI/E6dlUV07R3W/w9fEiMS6BCwyp8NulL9s3bTnymedj/rQsb/uSThYN5evMBj738qde/LUZmxnjuOQ3ApwuHEBMcyV/z06fBurTpCP12TaH+gPb4nrxG5Y/rUbByCQ5O3Kgq8+KmIzQZ5kZ4QBCRj0JpMboLz4OjuHvMQxVTu3crHnncIykugZINK9N6Uk+Oz9tFgo7bd3zDIfotHMrDV64tjdWuLYcRFRzOvpfH769NfzB210xaD/iYGyc9qP1xQ4pVLsHWiRnn51+bfqfDsM8IDnhG2KMQ3Eb3ICo4kmvHrqhimqkdv6p0yaPj17v7J0yes5CK5UpTqUJZtu0+QHxCIm4dWgEwcdaPODnYM/LrvgD06taZvt+O46df9tK4fm3+/Os0t+7eY8b4/6nKjI55zrOgEELC0u/IexD4GEgfhe5gb8ejJ884cuIM9WtXx87GmqDQMDb+vBtjYyMa1a+l0/YJIYQQQgjNctVJPmHCBNLS0mjRogVxcXE0btwYY2NjxowZ88ZbrLUpXrx4li/Xjx49Yvr06WzatClXZb7JgX1/Ym9vx/hJ/8PJ2RHvm3fo/ukAQl8ufFi4cAG1DqWrV64xZMAYJk4ZweRpo7jvH0Cfz7/l7p2ML49t2zVn+eofVH+v37wEgPlzl7Pgh/SOzKkTv0eZlsbmn5dhZGTEyb/PMX6U+m3nuuJ++AKWdlZ0Htk9/bbjOwEs7TNHtWCWXSEHlMqMuRz9PX3ZMHwpbqN78snYzwkJeMbKQfN56vtIFePaqiZ9f/xW9ffgFSMBOLhkN4eW7CE5MZnStcrTsm8HzKwtiAmL4t6VO/zw2RSeh8fotH1nDp3B2s6aXqN7Yedoh/9tf6Z+OZWol7fwOhVyUmvfHY87zBs2jz5j+/DVuK94EvCEWQNm8dAn43bluq3qMnrRaNXfE1dNBGDbom1sX7ydkpVKUq56+pQAm86pn5t96vUh5LHubmv+/cAx7OxtGTHhaxyc7Lnj7UPfbkMJfzm9SIHCLmqd8p5XbzBy8GRGTfqG0ZOH8vB+IF/3HoXvXX9VTMu2TZi/IuN8W7Yh/XxdOn8ty+andzjMnrKQtDQlKzcvwMjIiLMnLzJt3FydtesfJw+dwsbemr5jvsLO0Ra/2/6M+3IikS+Pn3MhJ7X34C2P28wa+j39x/VlwPh+PHnwhCkDpvPAJ0AV06BVPSYsHqf6e/rqKQD8tGgrPy3aCkCnLz/mq1G9VTHL9y0B4IeR8zmy55jO2nf58Hks7a34bFRPrB1tCLz9gAW9Z6kWPLMv6KDWvnsePqz+32K6jPmcrmO/IDjgGUsGzeOxb6AqpnqrWgxamPE5O3Rl+rm6b/Eu9i/ZRbFKJShVvQwAC8+uVqvPyAaDCXus22mdskuZJvOQ5rf3JXdHHjqHgZ0VBUZ/jqGjLfG3H+D35UxSXr6vjAo5qA1XjPW4y4NhCyk4thcFx31JYsBT7g+YS4JPxvvKulVtii0antGuVWMBeLboF54t3gnA45kbKZympMS68SiMDHl++hqBkzM6+XQp7LcLGNhbUXRcD4wcbYi9FcCtnnNIftlG40Lqnx3P3X3w/WYpH43vwUcTPyf+wTPu9p1P3N2M3G3Xpiallw5V/V127SgAAn/czaMfdwPwYNpPkKak7IYx6BkbEnXyOv4T1uu8fe6HL2BhZ0Wnl9cmj+8EsOw11yb3X16bdB7dE7eX1yarM12bHF3zG0amJvSaOxgzKzP8rt5lWZ85pLxyJ02xqqX4eGQ3jM1MCLr/hG2T1nF5/xmdt8/78CXM7CxpPrILFo7WBN15yM995hEbln4NZF3IXq19jzzv8evwlbQY3ZWWY7sRHhDEL4MWEeL7WBVzbs1hjEyN6TS3PyZWZgRe9eXnPvPU2le4akmaj/wMIzMTwu4/5dCkTVzff07n7bv68vh1HtlDdW25pM+cjNxWyEFtfSB/Tx/WD1/KJ6N7aL22PLLmAMamxvSeOxgzK3PuXb3Lkj6z1dpXvGppOo/srjp+P09ay6U8OH7tWjYhMiqaFRu2ERYRQbnSJVmzcJZqupVnwSHoKTJyWrXKFZg3YzzL121h6dqf+KhwIZbNnUrpEsVUMSfPXmLK94tUf4+dnn7t9XW/L/i2fy+MjYzwvO7Nz7sPEPP8BfZ2NtSsWoltaxZhb2uj8zZml+RuIYQQQnxIFMpXr9KzITU1lfPnz1OlShXMzMzw8/PjxYsXVKhQAQsLC51W7vr161SvXp3U1JzNpetoXVan9XjbuNlWeXPQO+5x6os3B73DfON1N3/m26iIyZunPHqXFdG3yu8q5KmfH+7TeZmBNVvovMyi7id0Xub76l3I3Z5FOuu0Hm+b+OT3a+FqTbaavN8das4Y5XcV8tRTEvO7Cnlqtfv8/K5CnjJ0yP60WdkluVsIIYQQH5IcjyTX19endevW3LlzBxsbGypUqJDrnR88ePC1z9+/fz/XZQshhBAineRuIYQQQgghhBBCu1xNt1KpUiXu37+f7blHtXFzc0OhUPC6wewKxfs9KkkIIT4Ecst2/pPcLYQQIickdwshhBDiQ5K9FS4zmT17NmPGjOHw4cM8e/aMmJgYtUd2FShQgH379pGWlqbx4emp20UehRBC5A9lmkLnD5EzkruFEELkhORuIYQQQnxIcjWSvH379gB06tRJbbSYUqlEoVBkex7SGjVq4OHhQefOmuchfdNINSGEEEJkj+RuIYQQQgghhBBCs1x1kp88eVInOx87diyxsbFany9VqpTO9iWEECL/SJ9p/pPcLYQQIickdwshhBDiQ5KrTvImTZroZOeNGjV67fPm5uY625cQQgjxIZPcLYQQQgghhBBCaJarTnKAqKgorly5QkhICGlpaWrP9e7d+19XTAghxPtD5iF9O0juFkIIkV2Su4UQQgjxIclVJ/mhQ4f44osvePHiBVZWVmpzmyoUCvmiLYQQQo1SKV+085vkbiGEEDkhuVsIIYQQHxK93Lxo9OjR9OvXjxcvXhAVFUVkZKTqERERoes6CiGEEOJfktwthBBCCCGEEEJolquR5E+ePOF///sfZmZmuq6PEEKI95Ay7c0xIm9J7hZCCJETkruFEEII8SHJ1UjyNm3a4O7uruu6CCGEeE+lKRU6f4ickdwthBAiJyR3CyGEEOJDku2R5AcPHlT9f4cOHRg7diy3b9+mcuXKGBoaqsV26tRJdzUUQgghRK5I7hZCCCGEEEIIId4s253kbm5uWbZ99913WbYpFApSU1P/VaWEEEK8X2Txr/whuVsIIURuSe4WQgghxIck253kaWkyKZ0QQgjxLpHcLYQQQgghhBBCvFmO5iRv3rw5UVFReVQVIYQQ7ytlmkLnD5E9kruFEELkhuRuIYQQQnxIsj2SHODUqVMkJSXlVV2EEEK8p5TK/K7Bh0tytxBCiNyQ3C2EEEKID0mORpILIYQQQgghhBBCCCGEEO+THI0kB7h9+zZBQUGvjalSpUquKySEEOL9I7dY5y/J3UIIIXJKcrcQQgghPiQ57iRv0aIFSg333ikUCpRKJQqFgtTUVJ1UTgghhBD/nuRuIYQQQgghhBBCuxx3kl++fBlHR8e8qIsQQoj3VJpSRqPlJ8ndQgghckpytxBCCCE+JDnuJC9atChOTk55URchhBDvKaV80c5XkruFEELklORuIYQQQnxIZOFOIYQQQgghhBBCCCGEEB+sHI0kb9KkCUZGRnlVFyGEEO8pDdNhi/+I5G4hhBC5IblbCCGEEB+SHHWSnzx5Mq/qIYQQ4j0m85rmH8ndQgghckNytxBCCCE+JDmekxzA1tYWhSLrRZNCocDExIRSpUrx1Vdf0bdv339dQSGEEEL8e5K7hRBCCCGEEEIIzXLVST5t2jTmzJlDu3btqF27NgBXrlzhyJEjfPvttzx48ICvv/6alJQUBg4cqNMKCyGEePfI4l/5T3K3EEKInJDcLYQQQogPSa46yc+dO8fs2bMZMmSI2va1a9dy7Ngx9u7dS5UqVVi2bJl80RZCCCHeApK7hRBCCCGEEEIIzfRy86KjR4/SsmXLLNtbtGjB0aNHAWjfvj3379//d7UTQgjxXlAqdf8QOSO5WwghRE5I7hZCCCHEhyRXneR2dnYcOnQoy/ZDhw5hZ2cHQGxsLJaWlv+udkIIId4LaUqFzh8iZyR3CyGEyAnJ3UIIIYT4kORqupWpU6fy9ddfc/LkSdW8plevXuWPP/5gzZo1ABw/fpwmTZrorqZCCCGEyDXJ3UIIIYQQQgghhGYKpTJ3N76dP3+eFStW4OPjA0DZsmUZNmwY9evX12kFc6NmgUb5XYU8pafI1Q0A75S41MT8rkKeehoXnt9VyFNVrYvldxXyVGxaUn5XIU9deXpa52VeLfSJzsus9WS/zst8373NuXtVkV75XYU81VA/Or+rkOesbBLyuwp56mqwU35XIU81q/I4v6uQpyICTfO7CnmqzJ0jOi9TcrcQQgghPiS5GkkO0KBBAxo0aKDLugghhHhPyS3WbwfJ3UIIIbJLcrcQQgghPiS57iRPS0vDz8+PkJAQ0tLS1J5r3Ljxv66YEEIIIXRLcrcQQgghhBBCCJFVrubtuHTpEqVKlaJ8+fI0btyYpk2bqh7NmjXTdR2FEEK845R58MiplStXUqxYMUxMTKhTpw5Xrlx5bfyePXsoV64cJiYmVK5cmT/++EPt+X379tG6dWvs7e1RKBR4eXlpLOfixYs0b94cc3NzrKysaNy4MfHx8blowb8juVsIIUROvA25WwghhBDiv5KrTvIhQ4ZQs2ZNvL29iYiIIDIyUvWIiIjQdR2FEEKIf2XXrl2MGjWK6dOn4+npSdWqVWnTpg0hISEa4y9cuEDPnj3p378/165dw83NDTc3N7y9vVUxsbGxNGzYkHnz5mnd78WLF2nbti2tW7fmypUrXL16laFDh6Kn99+vLSG5WwghhBBCCCGE0CxXC3eam5tz/fp1SpUqlRd1+tdk4c53nyzc+W6ThTvfbXmxcOeFAp/pvMz6z/ZmO7ZOnTrUqlWLFStWAOnTjhQpUoRhw4YxYcKELPHdu3cnNjaWw4cPq7bVrVsXV1dX1qxZoxYbEBBA8eLFuXbtGq6urmrP1a1bl1atWjFr1qwctCxvvO25WxbufPfJwp3vNlm4892WFwt35nfuFkIIIYT4L+Wqt7VOnTr4+fnpui5CCCHeU0qlQuePxMREYmJi1B6JiVl/YEtKSsLDw4OWLVuqtunp6dGyZUsuXryosb4XL15Uiwdo06aN1nhNQkJCuHz5Mk5OTtSvXx9nZ2eaNGnCuXPnsl2GLknuFkIIkRN5kbuFEEIIId5WuVq4c9iwYYwePZqgoCAqV66MoaGh2vNVqlTRSeWEEEIIbebOncvMmTPVtk2fPp0ZM2aobQsLCyM1NRVnZ2e17c7Ozty9e1dj2UFBQRrjg4KCsl2/+/fvAzBjxgx+/PFHXF1d2bp1Ky1atMDb25vSpUtnuyxdkNwthBBCCCGEEEJolqtO8s8+S7/1rl+/fqptCoUCpVKJQqEgNTVVN7UTQgjxXkjLgzInTpzIqFGj1LYZGxvnwZ5yJy0tvdWDBw+mb9++AFSrVo0TJ06wadMm5s6d+5/WR3K3EEKInMiL3C2EEEII8bbKVSf5gwcPdF0PIYQQ7zElur/F2tjYOFud4g4ODujr6xMcHKy2PTg4GBcXF42vcXFxyVG8JgUKFACgQoUKatvLly9PYGBgtsvRFcndQgghciIvcrcQQgghxNsqV53kH330ka7rIYQQQuQJIyMjatSowYkTJ3BzcwPSR3mfOHGCoUOHanxNvXr1OHHiBCNGjFBtO378OPXq1cv2fosVK0bBggXx8fFR2+7r60u7du1y3I5/S3K3EEIIIYQQQgihWbY7yQ8ePEi7du0wNDTk4MGDr43t1KnTv66YEEKI90eaMn/3P2rUKPr06UPNmjWpXbs2S5YsITY2VjUNSu/evSlUqJBqCpThw4fTpEkTFi5cSIcOHdi5cyfu7u6sW7dOVWZERASBgYE8ffoUQNUZ7uLigouLCwqFgrFjxzJ9+nSqVq2Kq6srW7Zs4e7du/z666//SbsldwshhMit/M7dQgghhBD/pWx3kru5uREUFISTk5NqJJ4mMq+pEEKIt0337t0JDQ1l2rRpBAUF4erqypEjR1SLcwYGBqKnp6eKr1+/Pjt27GDKlClMmjSJ0qVLc+DAASpVqqSKOXjwoKqTHaBHjx6A+uKhI0aMICEhgZEjRxIREUHVqlU5fvw4JUuW/A9aLblbCCGEEEIIIYTIDoVSqXzvxgjULNAov6uQp/QUem8OesfFpSbmdxXy1NO48PyuQp6qal0sv6uQp2LTkvK7CnnqytPTOi/zb+duOi+zefBunZcp8s+qIr3yuwp5qqF+dH5XIc9Z2STkdxXy1NVgp/yuQp5qVuVxflchT0UEmuZ3FfJUmTtHdF6m5G4hhBBCfEhy3NuanJxMixYtuHfvXl7URwghxHtIiULnD5F9kruFEELklORuIYQQQnxIctxJbmhoyI0bN/KiLkIIIYTIA5K7hRBCCCGEEEII7XI1b0evXr3YuHGjrusihBDiPZWWBw+RM5K7hRBC5ITkbiGEEEJ8SLK9cOerUlJS2LRpE3/99Rc1atTA3Nxc7flFixbppHJCCCHeD3KLdf6T3C2EECInJHcLIYQQ4kOSq05yb29vqlevDoCvr6/acwqFXEwJIYQQbxvJ3UIIIYQQQgghhGa56iQ/efKkrushhBDiPSa3WOc/yd1CCCFyQnK3EEIIIT4kuZqTXAghhBBCCCGEEEIIIYR4H+RqJHmzZs1ee2v233//nesKCSGEeP/IaLT8J7lbCCFETkjuFkIIIcSHJFed5K6urmp/Jycn4+Xlhbe3N3369NFFvYQQQrxHZPGv/Ce5WwghRE5I7hZCCCHEhyRXneSLFy/WuH3GjBm8ePHiX1VICCGEELonuVsIIYQQQgghhNBMp3OS9+rVi02bNumySCGEEO+BNIXuH0I3JHcLIYTQRHK3EEIIIT4kOu0kv3jxIiYmJrosUgghhBB5SHK3EEIIIYQQQogPXa6mW/n000/V/lYqlTx79gx3d3emTp2qk4oJIYR4f6TJvKb5TnK3EEKInJDcLYQQQogPSa46ya2trdX+1tPTo2zZsnz33Xe0bt1aJxUTQgjx/lDmdwWE5G4hhBA5IrlbCCGEEB+SXHWSb968Wdf1yDddv/qEL7/pib2jHfdu+7Ng8hJued3RGt+iY1O+Hj+AAoVdePTgMctnr+H835dUzzdr35jPenemXOWy2NhZ83nLvvje8lMr45NeH9P2k1aUrVwGC0tzmpZtx4uYvFs0rctXbvT6uoeqjT9OWcptr7uvbePgcf1etvEJK+as4cLfl1XPN23XiE97d6Z85TJY21nzRav+3MvURrcvPqbNJy1UbWxerkOetbFH38/o+00vHJzs8Lntx/eTFuJ97bbW+NYfN2fo+EEUKlKAhw8esXjWSs6euKh6vmX7pnTr8wkVqpTDxs6az5p/ic+te2pldPmyMx0+aUP5KmWxsDSnXumWPM+j9vUf+AXDhg/AydmRWzfvMn7sd3h63NAa39mtLROnjqBo0cLc9w9gxrQF/HXstFrMxMnD+fKrblhbW3H5kgdjRk7nvv9D1fNVqlZgxnfjqFa9MqlpqRz67ShTJs4lNjZO5+1z69OJ7kO6Yudoh/8df5ZNXcldLx+t8U06NKbf2D64FHbhccAT1n2/gct/X1E936hdQz7u1ZEyVUpjbWvFgNZD8L/tr1ZGxy/a08KtOaUrlcLc0pyOFdyIjYnVedvg/X//iXfH+5S7K/VpievgDpg5WhN+J5Cz07YS4nVfa3zJDrWpPaYLloUdiA4I5uL3Owk8eV31fIm2Nan4ZQscKxfDxNaSXW0mEX47UK0MfWND6k/9nNKd6qJvZEjg6RucmfwT8WExedJG+y/b4zj4UwwcbUm484An09cSf/2e1njr9g1wHt0Lo8JOJD54StAPP/H8lIfqeas29bD/oh2mlUtiYGuFb/v/kXD7gVoZdj3bYNO5CaYVS6JvaYZ3lR6k5dFno2X3Tlj36Yq+vR1Jvv6Ez1tJkrf2z36zVo2x/aYPBgVdSA58QuTSDcSfy/jsN2veEMuuHTEqXxp9Gyuedh9Cko/6Z7/FZ+2xaNcco3Kl0LMwJ7CRG2nP86Z9Jb9qRdlvOmDiaE3U7UCuTd5C5GvO0cIda1NxfFfMCzvw4kEwN2b/QtDfGedoofY1KdG7JbaVi2FsZ8mxlpOIvvVQrQw9Y0OqTv+CIp3rom9sSNCpG3hO2ExiHpyjJh+7YdqlB3p2dqTc9yd21VJSfLTnNqNGTTHr0w99ZxdSnzwhduMakq9m5DajBo0w6dAZg9Jl0LOyJvLr/qTeV89txu0+xqRZC/RLlUHP3JzwTzugjM2b3Gb9+cfY9euCvoMtiXfvEzpnFQk3fbXGW7RphMP/emNQyJnkh08IW7iJ2DNXM55v1QDr7u0xqZh+fj785BsS76qfD9Zd22HZsRnGFUqib2GOX+3P8uz8fJesXLmSBQsWEBQURNWqVVm+fDm1a9fWGr9nzx6mTp1KQEAApUuXZt68ebRv3171/L59+1izZg0eHh5ERERw7do1XF1d1cpISEhg9OjR7Ny5k8TERNq0acOqVatwdnbOq2YKIYQQ4i3wr+YkT0pK4vHjxwQGBqo93hWtOjVn5IyhrF/4E73aDMD3th/Lf1mIrb2NxvgqNSsxZ/V0ftvxO1+07s+pI2f5cfP3lCxbXBVjamaK1+WbLJ+zRut+TUxNuHDyMpuX/azrJmXRslMzRkz/lg2LttC7zUDu3fZn2Y4ftbaxcs2KzFo1lYO//MGXrQdy+shZFmyaQ4lMbbx+5SYrvl+rdb8mpsZcPHWFn5Zv03WT1LTt3JJxM4ezeuEGurbqg8+te6zduQQ7B1uN8a41KzN/zXfs33GIri378PefZ1j203xKlSuhijE1M8Hz8nUWz16pdb8mpiacO3mR9Ut/0nWT1HzyaXtmz53E/B9W0KyhG97ed/h1/yYcHOw0xteuU431mxezfeuvNG3YmT8O/8W2X1ZRvnxpVcz/Rg5i0JDejB4xjVbNuhAXF8+v+zdjbGwEgIuLE/sPbuH+/Ye0at6Frp/0p1z50qxcM0/n7Wv2cRO+njaYLYu3Majd1/jfvs/8bXOx0XJ+VqxRgakrJ/HHziMMbPs1546cZ9aGGRQrW0wVY2JmgvdVb9Z9v0Hrfo1NjLly6irbV/yi4xape9/ffzmRlgcPkTvveu4u9XEdGkz9Avcl+9nTfgphtwPp+PN4TO2tNMa71ChNqxXfcmfnafa0m8KDox602zASu7KFVTEGZsY8u+LDxe93ad1vg+lfUKxlNY4OWc6BrrMxd7al7boRum4eANYdG1JgygCCl/7CvQ4jiL/9gOJbv0Pf3lpjvFn1chRdNpbIXce41344Mccu8dG6yRiXKaqK0TMzIdb9NkE/bNG6Xz1TY56f9iRk1R6dt0mtvq2bYDd6MFFrt/G059ck+d7HedVc9GxtNMYbV62A49xJPD9whKc9vibu5HmcFs/AsGQxVYzC1ISEa95ELtX+2a9nYkz8+atEb8zbz/7CnepSdcYX3F64j+NtphB9O5DGv0zAWMs5al+zNHVWD+XBjlMcbz2ZJ0fcabB5FFavnKP6ZiaEXfbh5pydWvfrOrMXBVtX4+KgZZz8dBamzrbU3zhS5+0zatIM80HfErd9C1HfDiT1vj9Wc35EYW2jMd6gQkUsJ04l8cgfRH0zkKQLZ7GaPgf9jzJym8LElORbN4ndqD23KUyMSXK/QvzOvM1tFu0a4zh+IOErtxH42VASfe5TaP0c9O00v/9MXMtT4McJRO89SuCn3/LixEUKLp+GUemPMupuakK85y1CF2pfJFlhakzsWXci1mr/HPqv5Xfu3rVrF6NGjWL69Ol4enpStWpV2rRpQ0hIiMb4Cxcu0LNnT/r378+1a9dwc3PDzc0Nb29vVUxsbCwNGzZk3jzt17UjR47k0KFD7Nmzh9OnT/P06dMsU5YJIYQQ4v2Tq05yX19fGjVqhKmpKR999BHFixenePHiFCtWjOLFi7+5gLfEF4O7c2D7IQ7t+oMHvgHMHfcjCfEJdOrZQWN8jwFduHjyCj+v/oWAew9ZM38jd2/60q1fxkXTH78eZcPin7hyxl3rfn9Zv4ctK7bj7XFL523K7PNB3Tiw4zCHd/3Jg3sP+WH8QhLiE/i4Z3uN8T0GdOHSyStsW72TAL+HrF2wKb2NfT9Rxfy59xgbF2/hyhkPjWUA7NzwK1tX7MDbQ/uIbl3oPaQnv277jQM7f+e+bwDfjZ1HQnwCn/TsqDG+16DunD95ic2rtnP/XgAr5q3j9k0fPu/XRRVz6NcjrFm0iYuvjADKbNu6XWxc/jM38vgYfjO0H1t/2sWObXvx8fFj1PBpxMXH80XvLhrjB3/dhxN/nWX50g34+vjz/ewl3Lh+mwGDv1TFDPmmDwsXrOLP309w+5YPXw8ai0sBJzp0bAVAm3bNSE5JYeyoGfjde8A1z5uMGj6NTm5tKV6iqMb95lbXQZ/x+y9/cmT3UR7eC2TRhKUkJCTSrkcbjfGf9f+EK6eusmvNHgL9Atn84xbuefvxyVedVTHH9/7F1iXb8DjrqXW/ezfu55eVu7jtqf2uEV14399/OZGmUOj8IXLmfcndVQe24/YvJ7m7+wyR955yeuJmUhISKde9icb4Kv3bEHjqBl5rfyfS7ylXfvyVUO8AKvdppYrx3Xce96UHeHzOW2MZRpamlO/elPPfbefJhduE3gzg79HrKFCrDM7VSuq8jY4D3IjYeZTIPSdI9HvEk8mrUMYnYtetlcZ4h36deH7ak9B1+0n0f0zwou3E3/LHoU9GLozaf5KQZTt5ft5L637DNh0kdPWvxF3TPiJYF6y//Izn+/7kxW9HSb4fSPjspSgTErF00/zZb/X5J8RfuErMlj0kPwgkatUWku74YdUj47M/9ve/iF63jYTL2j/7Y7bvJ3rzLhJv5u1nf5nB7Xiw/SQBu87w3PcJHuM2kRqfSLGems/R0gPaEnTyBr6rf+f5vafcmv8rkTcDKNUvYxqkwF/PcWfxfoLPaD5HDSxNKd6zKV7TtxN6/jZRNwK4OnItDrXLYFe9lE7bZ/ppNxKOHCbx2J+kBj7kxbKFKBMTMGmjObeZunUh2f0K8b/uJPXRQ+K2biLFzxeTzhm5LfHEMeK3byH5mvbclrD/V+J37yDlbt7mNts+nxKz5wgx+4+T5B9IyIzlKBMSsfpU8/lp29uN2HPuRG76laT7jwhftpWEO37YfN5JFfP84AkiVu0g7sI1rfuN2nqAyA27Sbiet++/nMjv3L1o0SIGDhxI3759qVChAmvWrMHMzIxNmzT/2LB06VLatm3L2LFjKV++PLNmzaJ69eqsWLFCFfPll18ybdo0WrZsqbGM6OhoNm7cyKJFi2jevDk1atRg8+bNXLhwgUuXLml8jRBCCCHeD7nqJO/bty96enocPnwYDw8PPD098fT05Nq1a3h6av9y8jYxMDSgXJUyXD6bcTGuVCq5ctadKjUqanxNlZqVuHJWvfP74qkrVK5RKU/rmlv/tPFqpjZePetBZS1trFyjIlfOqn9BuXT6qtb4/GRgaECFKmW5dDajM1upVHLpzFWq1qys8TVVa1TK0vl94eQlrfH5ydDQkKrVKnL61AXVNqVSyelTF6hVu5rG19SqXY3TJy+obfv7r7PUqu0KwEfFiuDi4sSpV2Kex7zAw/26qkwjIyOSk5JRKjNmokxISACgbr2aOmkbpB+/MpXLqHVmK5VKPM96UrF6BY2vqVCjQpbO76un3alYo7zO6qUr7/v7T7x73ofcrWeoj2Pl4jw+98oPlEolj8/ewqWG5o5A5+qlsnR+Pzp9A2ct8Zo4Vi6OvpGB2n6j/J/x/HEYzjVKv+aVOacwNMC0UilenM+YagOlkufnvTCrXlbja8yqleNFps7vF2euYVa9nE7rphMGBhiVL6Pema1UknDZE+Mqmj/7jatUyNL5HX/RHeMqb99nv8JQH9sqxQk++8o5p1QSfNYbey3nin3NUoScVT9Hg07dwD4H56htleLoGRmolfPc7xmxj8Owr6nDTnIDAwxKlyHZ85VcpVSSfM0Dgwqac5VB+YokZer8Tva4imH5tzC3GRpgUrE0sRdf6cxWKom9eA1TV83nm0nV8sRdVO/8jjvnoTX+Q5eYmEhMTIzaIzExMUtcUlISHh4eap3Zenp6tGzZkosXL2aJB7h48WKWzu82bdpojdfEw8OD5ORktXLKlStH0aJFc1SOEEIIId49ueok9/LyYu3atbRr1w5XV1eqVq2q9siuYcOGcfbs2dxU4V+zsbPGwMCAiNAIte0RoZHYO9lrfI29o52G+AjsnTRPfZHfMtoYqbY9IiwSe0fNdbZ3tCMiLFN8aCR2b2Ebbe1sMDAwIDzTMQkPjcRByzF0cLLPEh/2mvj8ZG9vi4GBAaEhYWrbQ0PCcXZy1PgaJ2cHQjLFh4SE4eScHu/s7PCyjMxlhuH08rmzpy/i5OzAsOEDMDQ0xNrGiukzx6a/3kXzfnPD2s4afQN9IjOdn5Fhkdg5aZ4ux87RlsiwKPX40EhstZzP+el9f//llDIPHiJn3ofcbWJniZ6BPnGh0Wrb48OiMXPUMhWJow1xmeZkjguLwczRJtv7NXOyJjUxmaQY9XUZ4l6z39zSt7VCYaBPSqbPgpTQKAwdNX82GjjakJLpszElNAoDBxud1k0X9G2tURjokxqu3r7U8Ej0tUyVpu9gS2p4lIb4t++z0fjlOZqQ6RxNCI3BxEnLdB2ONlniE0OjMXGyyfZ+TZxsSE1MJjnTOZoYGo1JDs71N9Gzskahb0BalPrxS4uMRM9W8/HQs7UjLTL78flJ38bq5fkZpbY9NTxK6/lp4GBLaub332vi3yV5kbvnzp2LtbW12mPu3LlZ9h0WFkZqamqWecCdnZ0JCgrSWN+goKAcxWsrw8jICBsbm39VjhBCCCHePbnqJK9QoQJhYWFvDnyDlStX0rRpU8qUKcO8efNydeGhaTRCmlJmqxUit+7e9eObweP5Zlg/noTc4K7fRR4+fExwcChpadI1KcS76m3P3cnK1H9dNyGEEG+3iRMnEh0drfaYOHFifldLCCGEECJ3neTz5s1j3LhxnDp1ivDw8CxfdHPi2LFjtG/fnh9//JGiRYvSuXNnDh8+TFpa9jq6NY1GCHrx6I2vi4qIJiUlBbtMIzrtHG0JDwnX+Jrw0AgN8XaEh0RojM9vGW1UH8li52CbZTT1P8JDI7IsemnnaEvEW9jGyIgoUlJSsozKtXe0JUzLMQwLCc8S7/Ca+PwUHh5JSkoKjk4OatsdnewJDgnV+JqQ4DCcMsU7OTkQEpweHxwc9rKMzGU6EBKc0Xm2d88hypeqT8UyDSn1US3mfb8MBwc7Hj7Q3eJ+0RHRpKakYpvp/LR1sCUiJFLjayJCI7HNNDLS1tGWSC3nc356399/OZXfi3+Jtz93H4t58xoPCRHPSUtJzTJ629TBOsvo8n/EhUZh5qC+YKKZgxVxoVHZqitAXEg0+saGGFmZZSpH+35zKzUyBmVKKgaZPgsMHG1IDtX82ahp1Lim0eVvg9TIaJQpqejbq7dP396W1DDN7UsNi0Q/04LH6fFv32dj4stz1CTTOWriaEVCiOZzJSE0Kku8saM1CSFR2d5vQkgU+saGGGY6R40drUnIwbn+Jmkx0ShTU9CzUT9+era2pEVqPh5pkRHo2WY/Pj+lRsW8PD9t1Lbr29toPT9TwiLRz/z+e038uyQvcrexsTFWVlZqD2Nj4yz7dnBwQF9fn+DgYLXtwcHBuLi4aKyvi4tLjuK1lZGUlERUVNS/KkcIIYQQ755cdZK3bNmSS5cu0aJFC5ycnLC1tcXW1hYbGxtsbXN2a2HlypVZsmQJT58+Zdu2bSQmJuLm5kaRIkWYPHkyfn5+r329ptEILhZF3rjflOQU7t7wpXbDGqptCoWCWg1raF2M8Ya7N7VeiQeo07gmNz00L6KU3/5pY61MbazZsDo3tbTxpsctajXS1Ma8X2Q0p1KSU7h9w4c6jWqptikUCuo0qsV195saX3Pdw5u6r8QD1GtSW2t8fkpOTub6tVs0blJPtU2hUNCkSX2uXtG88NPVK9do3LSe2ramzRtw9YoXAA8DHhEUFEKTV2IsLS2oUbOqxjJDQ8OJjY3jk886kJCQyMmT53XQsnQpySn43vSlesOM+dUVCgXVG1bjlqfmRblue9xWiweo0ag6tzzydhG23Hjf3385labQ/UPkzNueu1tbvXl+4rTkVEJvPqBQg1diFQoKN6xIkIfmfQZ7+lG4gXrZRRpVIlhLvCahNx+QmpSiVo5NiQJYFnYg2ONetsvJDmVyCvHefljUr5KxUaHAon5V4jx9NL4m7tpdLOqrT5lj0dCVOM+3ZwFAlZQUku74YvLq2hoKBSa1q5F4Q/Nnf+KN2+rxgEnd6iTeePs++5XJqUTeeIBTQ/Vz1KlhJcK1nCvh7n7q8YBz40qE5+AcjbzxgLSkFJwaZZRjUbIA5oUdCHfPfjlvlJJCyj1fDKu9kqsUCgxdq5NyW3OuSrlzCyNX9dxmWL0myXfewtyWnELCrXuY1XXN2KZQYFbXlXgvzedbwvU76vGAWf3qWuPfJfmZu42MjKhRowYnTpzIqE9aGidOnKBevXoaX1OvXj21eIDjx49rjdekRo0aGBoaqpXj4+NDYGBgjsoRQgghxLvHIDcvOnnypK7rgaGhId26daNbt24EBgayadMmfvrpJ3744QdSU7Xfgm1sbJxl9IGeInt9/9vX7mLG0kncvn6XW153+HxgV0zNTDm08w8AZi6bTEhQGCu/XwvAzg2/sm7fcr4Y3J1zJy7SpnMLKlQtx/djF6jKtLKxxKWQM44v53f+qGRRAMJDIlSjR+0d7bB3sqNw8cIAlCpfgrgXcQQ9CSYm6nm26p5dO9btZvqSidy5fpdb1+7SY2AXTM1MObzzTwBmLJ1ESFAoq+auV7Vx7d5lfD64G+dPXKJ15+aUr1KW78f+qNZG50LOODrbv2xj+o8SEZnaaOdkR5HihdLbWK4EsbFxBOu4jVvX/MKcZVO55XUH72u36TWoO6ZmJhzY+TsA3y+fRkhQKEvmrAZg27pdbD6wmj5DPufMX+dp59aKilXLM2PMD6+0z4oChZxxckk/hsVLfQSkj0J/tX0OTvYUfXkMS5cvSeyLOJ49CSYmKmcjMl9n1YpNrFw7H69r3nh63GDIN19hZmbKjp/3pj+/dj7PngUza8ZCANau3sKhP7fz7bB+HDt6ik8/64BrtUqMHDZFVeaaVVsYPfYb/P0DeBjwmElTRxD0LITfDx9XxQwY1Isrlz2JjY2jabMGzJw9nu+m/0hMtG7Pzz3r9jJh8Th8r/tyx8uHLgM+wcTUhCO7jgIwcck4QoPC2PDDJgD2btzPkl8X0nVQFy6duEzzzk0pW6UMC8cvUZVpaWOJU0EnHFzSz8+iJdOPUURohGr+c1tHW+wc7ShULP38LFGuOHEv4gl5GsJzHZ6f7/v7T7xb3vbcbajQz9Y+r6//k+aLBhN64wEhXv5U6d8WA1Nj7u4+DUCLxYOJDYrk0rzdANzYeJTOeyZTdVA7Hp7wonSnejhWKcGpCZsy6mNjjkVBe8yd038ssC1ZAIC40GjiQ6NJeh7PnV2naDDtCxKiXpD8Ip5G3/UmyN2X4Gv+2f8Hy6bQDQcosnAk8Tf9iPPyxaF/Z/TMTIjc8xcARRaOJDk4nKD5WwEI23SQkrvm4jDAjecn3bH5uBGmlUvxeOIKVZn61hYYFnLE8OUaB8Yl0j8fUkIjSXk50tjA0QYDR1uMPyoIgEnZj0iLjSf5SSip0S901r7on/fiOGscibd9SfL2weqLT1CYmvD8t/TPfodZ40gJCSNqefoxitmxH5cNC7H6sgvxZy9j3rYpxhXKEP7dElWZelaWGBRwQt8x/bPR4KP0z/7UsAjV/Of69rboO9hhUCS97YaliqOMiyflWQhpMbr7bPRd+ye1lw4m8voDIrz8KT2wLQZmxgTsTD9Hay0bQnxQJN7f7wLg3oYjNN03hTKD2/PsxDWKdK6HXdUSeIzdqCrT0MYcs0IOmDrbAGD58hxNCIkiMTSalOfxPPjlFFVn9CIpMpbkF3FUm92HsKu+RHjqsJMciN+3G8sxE0nxvUuKz11MPumCwsSUhGPpuc1i7CTSwkKJ25ye2+IP/Ir1gmWYftaNpCuXMG7SHIPSZXmxJCO3KSwt0XN0Rs8+/fjpF0nPbWmREShfjjhX2NqhZ2uHXsH046dfvATKuDjSQoNRPtfd8Yvcsg+XuWNI9L5Hwk0fbHp/gp6pCTH7jwHg8sMYUoLDCVu8OT1+6wGKbF2A7Vef8uL0FazaN8WkYmmCpy9VlalnbYFhAScMXq6BY/jy+jElLFI14lzfwRYDB1sMX77/jMsUS3//PQshTYfvv3fJqFGj6NOnDzVr1qR27dosWbKE2NhY+vbtC0Dv3r0pVKiQak7z4cOH06RJExYuXEiHDh3YuXMn7u7urFu3TlVmREQEgYGBPH36FEjvAIf0EeQuLi5YW1vTv39/Ro0ahZ2dHVZWVgwbNox69epRt27d//hfQAghhBD/JYVSqcy3SYb19PQICgrCyclJ4/NKpZK//vqLVq1a5ajcmgUaZTu2W99P/9/efYfHlLZhAL8nvfemhSBRQwhCdIsgSlbvvaxO9G7Xrli70XtnF9F92F27FrF6SAQpIolEkN6lt/n+CBMjMyTMGEnu315z2Zx5zjnvM+U8M++85z0YMWUIjE2N8NQ/BL8s3Qj/B4UjmXae2oTIF9H4ftZqUfw3PTtgyoIJqFTNAi/CXmLTqu24eeWO6P6eA7tj5cbFxfaz69d92OVe+GF64pwxmDh3bLGYlTNX48Lxvz7a5pL+CPDWgDHfYvjkwaIc3Zdtgv+DwtEt209uQNSLaPwwu6iT+JueHfDdgnGoVLUwx80/7sCtK3dF9zsP7IYVG4rPHbjbfT92ux8AAEyYMxoT5owpFvP9LDf8cfziR9uckV/8KvfSDBnbH2OmDIOJmTGe+AfDbck6PPYpHJ20//Q2vHoRhaUzV4niu/bqhOkLJ6FKtUp4HvYC637YguuXi65W32eQM37atKzYfrb9sgfbft0DAJgydzymzBtfLGbJjFX437E/PtrmyIyST+8yfuJwTJ85HmbmpvB7FIiF81fB+/5DAMC5P39HRMQrTPtuQVH7Xbph8fLZsLSsimeh4VixbC3+/eea2DYXLZmJkWMGQV9fD3du38c815UIDQkvynXnWnTt1gHa2toIfhqKLZv24rjH/0rc5sb6NUoc6zK6DwZ9NwBGpoYIDQjF5uXbEPigcPTj+hO/IvpFDH52Lfohqr1zO4ydPxoWVc3xKuwVdq7eg7tXvET3Ow3oioXr5xXbz4F1h3Bw3W8AgFGuIzDadWSxmDWzf8HfJ/75aJvTC3JKnF9ZfP95RV77aExpHa48XObbHBb5u8y3SR8nr9q9rVrJXyMNR3VBk++coWWqj/iA57i+/DfE+hZ2Vvc5vgSvX8bhimtRp0gt5xZoMW8A9KqaIDk8Grd/8kDE1Yei++sMaItv1k0qtp97607j3vrTAABldVU4LhsK6z6toKymghfXHuPakgPILOF0K22USzcti/FIZ5hO7AsVU0NkBT7Dq5W7kOn7FABQ02M1cl7G4uXcDaJ4/R6tYTFnOFSrmiMnPBJRbvvx2tNbdL9h/29Q7ddZxfYTs+EIYjYcBQCYzxoC81lDi8W8mLsBSScvF1v+Pj2DrBLnpzuoD/RHDYCyiSFygkKR8PM25PgVHvst9vyKvMgYxC8vOvZrdWkHw6mjoVLZHLkRr5C0YQ8ybxQd+3V6d4XJD8WP/ck7DiF5R+Gx3+C7ETD4rvixP375L0g79/Fj/70Yya95SWqN6YI6U3pCw1Qfyf7P4bv0EBLf/KDS/tQSZLyIx71ZO0XxVXu2QMMFA6BVzRRpYdF4tOoooq8UvUarD2yHFhuLv0b9fz2FAPfC16iSuioarxgGS5dWUFJXQbTnY/gs3I/sEr5GOzZ6WeL8NHp/C83+g6FkaIS8ZyFI37YJeUGFtU1/7Qbkx0Qjzb2otqm17QCtUeOgbG6B/MiXSN+zA7n3imqbepdu0J1bvLZl/LYfGb8fAABoDR8NrRHFa9vrX92QfenjtS0xQrPE+RkM7QXDcf2hbGKI7MBniFu9HVmPCjtTqx5ci9xXMYhZ7C6K13FqC5OZo6BSxQy5zyMR/+tepP93T3S/nksXWLjNKbafhC2/I2FrYS0znjocxtOKHwejF7kj9eylYsvfZxP48cegtL6G2r1lyxb88ssviI6Ohp2dHTZt2gQHBwcAQIcOHVCjRg0cOHBAFH/ixAksXboU4eHhsLa2xtq1a9GjRw/R/QcOHBB1sr9rxYoVWLlyJQAgKysLc+bMwdGjR5GdnQ0nJyds27aN060QERGVc5/cSX79+nXs3LkTz549w4kTJ1ClShX89ttvsLKyQps2bUq0DSsrK9y/fx/Gb0aNyEppOsnLotJ2kpdFpekkL4tK00leFpWmk7wsKk0neVkkj07y3+XwRXs4O8lL7Wuu3aXpJC+LSttJXhaVppO8LCpNJ3lZVJpO8rKoNJ3kZZE8OslZu4mIiKgi+aTe1lOnTsHJyQmamprw8fFBdnZhh2ZKSgpWr179kbWLhIWFyfxLNhERERXH2k1EREREREQk2Sd1kv/444/YsWMHdu/eDVVVVdHy1q1bw8fHR2aNIyKi8oEX7lQ81m4iIioN1m4iIiKqSD6pkzwoKAjt2rUrtlxfXx/Jycmf2yYiIiKSMdZuIiIiIiIiIsk+qZPcwsICISEhxZbfuHEDNWvW/OxGERFR+VIghxuVDms3ERGVBms3ERERVSSl6iQ/dOgQsrOzMWHCBMycORN3796FQCBAZGQkDh8+jLlz52Ly5MnyaisREZVRQjncqGRYu4mI6FOwdhMREVFFolKa4DFjxqBbt25YuHAhCgoK8M033yAjIwPt2rWDuro65s6di+nTp8urrURERFRKrN1EREREREREH1aqTnKhsPD3f4FAgCVLlmDevHkICQlBWloa6tevDx0dHbk0koiIyjZerEtxWLuJiOhTsHYTERFRRVKqTnKg8Ev2W2pqaqhfv75MG0REROUP5yFVLNZuIiIqLdZuIiIiqkhK3Un+zTffQEXlw6v5+Ph8coOIiIhItli7iYiIiIiIiKQrdSe5k5MTT80mIqJS4Wg0xWLtJiKi0mLtJiIiooqk1J3k8+bNg5mZmTzaQkRERHLA2k1EREREREQkXak6yd+d05SIiKikhCwfCsPaTUREn4K1m4iIiCqSUnWSC4VCebWDiIjKMZ6yrTis3URE9ClYu4mIiKgiUSpNcFhYGExNTZGVlSU1Jioq6rMbRURERLLB2k1ERERERET0YaXqJK9evToEAgGaNm0KX1/fYvefOnUKjRo1klXbiIionCiQw41KhrWbiIg+BWs3ERERVSSl6iR/q0OHDmjZsiV+/vlnAEB6ejpGjx6NESNGYPHixTJtIBERlX1COdyodFi7iYioNFi7iYiIqCIp1Zzkb23btg3Ozs4YP348Lly4gKioKOjo6MDLywsNGzaUdRuJiIjoM7F2ExEREREREUn2SZ3kANC9e3f07dsX27dvh4qKCs6fP88v2UREJFGBQNEtIIC1m4iISo61m4iIiCqST5puJTQ0FK1atcKFCxfw999/Y/78+ejduzfmz5+P3NxcWbeRiIiIPhNrNxEREREREZFkn9RJbmdnBysrKzx8+BBdunTBjz/+iKtXr+L06dNo0aKFrNtIRERl3Ndw8a+tW7eiRo0a0NDQgIODA7y8vD4Yf+LECdStWxcaGhqwtbXFn3/+KXb/6dOn0bVrVxgbG0MgEEi8KOZbQqEQ3bt3h0AgwNmzZz+h9Z+PtZuIiErja6jdRERERF/KJ3WSb9u2DR4eHjAwMBAtc3R0xIMHD9C0aVNZtY2IiMoJRX/RPnbsGFxdXbFixQr4+PigcePGcHJyQmxsrMT4W7duYciQIRg3bhwePHgAFxcXuLi4wM/PTxSTnp6ONm3aiC6E+SEbNmyAQKDY89ZZu4mIqDQUXbuJiIiIviSBUCgsdxcab1apraKbIFdKgk/6baNMycjPVnQT5CoyI0HRTZCrxvo1FN0EuUovyFF0E+TKK/KazLfpbjlc5tucE/F7iWMdHBzQvHlzbNmyBQBQUFCAatWqYfr06Vi4cGGx+EGDBiE9PR0XLlwQLWvZsiXs7OywY8cOsdjw8HBYWVnhwYMHsLOzK7YtX19f9OzZE/fv30elSpVw5swZuLi4lLjtFcW2arJ/jXxN2iinKLoJcqdnkKXoJsjVvRgzRTdBrjo2eqnoJshVYoSmopsgVzaBF2W+TUXXbiIiIqIv6ZMv3AkAAQEBiIiIQE5OUYeRQCBAr169PrthRERUfsjj19js7GxkZ4v/oKaurg51dXWxZTk5OfD29saiRYtEy5SUlNC5c2fcvn1b4rZv374NV1dXsWVOTk6lniolIyMDQ4cOxdatW2FhYVGqdeWFtZuIiEqi3I2kIiIiIvqAT+okf/bsGb799ls8fvwYAoEAbwejvz2VPD8/X3YtJCIiksDNzQ3ff/+92LIVK1Zg5cqVYsvi4+ORn58Pc3NzseXm5uZ48uSJxG1HR0dLjI+Oji5VG2fPng1HR0f06dOnVOvJA2s3ERERERERkWSfNG/HzJkzYWVlhdjYWGhpacHf3x///fcfmjVrBk9PTxk3kYiIyroCgexvixYtQkpKitjt3dHiinbu3DlcuXIFGzZsUHRTALB2ExFR6cijdhMRERF9rT5pJPnt27dx5coVmJiYQElJCUpKSmjTpg3c3NwwY8YMPHjwQNbtJCKiMkweF+uSNLWKJCYmJlBWVkZMTIzY8piYGKlToFhYWJQqXpIrV64gNDRU7EKZANCvXz+0bdv2i3dMs3YTEVFp8EKbREREVJF80kjy/Px86OrqAijsfIiMjAQAVK9eHUFBQbJrHRER0WdSU1ODvb09Ll++LFpWUFCAy5cvo1WrVhLXadWqlVg8AFy6dElqvCQLFy7Eo0eP4OvrK7oBwPr167F///7SJ/KZWLuJiIiIiIiIJPukkeQNGzbEw4cPYWVlBQcHB6xduxZqamrYtWsXatasKes2EhFRGafoi3+5urpi1KhRaNasGVq0aIENGzYgPT0dY8aMAQCMHDkSVapUgZubG4DCqUnat28Pd3d3ODs7w8PDA/fv38euXbtE20xMTERERISos/ltR7OFhYXY7X2WlpawsrKSd8rFsHYTEVFpKLp2ExEREX1Jn9RJvnTpUqSnpwMAvv/+e/Tq1Qtt27aFsbExPDw8ZNpAIiIq+woU/FV70KBBiIuLw/LlyxEdHQ07OztcvHhRdHHOiIgIKCkVnVzl6OiII0eOYOnSpVi8eDGsra1x9uxZNGzYUBRz7tw5USc7AAwePBiA5IuHfg1Yu4mIqDQUXbuJiIiIviSBUCiUyaefxMREGBoaQiBQ/BVZTPRsFN0EuYp6dlHRTZC7Vc2WKboJcvVfXszHg8qwJiomim6CXN3JLd/P3+1XV2W+zZ+qD5P5Npc8PyzzbVY0X1PtjunYXtFNkCtdl3qKboLcLV+fougmyNWq7SWfbqlMehWu6BbIlaCevaKbIFcarWVfZ1m7iYiIqCIp1UjysWPHlihu3759n9QYIiIqn3jxL8Vh7SYiok/B2k1EREQVSak6yQ8cOIDq1aujSZMmkNEAdCIiIpIj1m4iIiIiIiKiDytVJ/nkyZNx9OhRhIWFYcyYMRg+fDiMjIzk1TYiIion2DWrOKzdRET0KVi7iYiIqCJR+nhIka1btyIqKgrz58/H+fPnUa1aNQwcOBB///03R6cREZFUBXK4UcmwdhMR0adg7SYiIqKKpFSd5ACgrq6OIUOG4NKlSwgICECDBg0wZcoU1KhRA2lpafJoIxEREX0G1m4iIiIiIiIi6Uo13cr7lJSUIBAIIBQKkZ+fL6s2ERFROVMgUHQL6C3WbiIiKgnWbiIiIqpISj2SPDs7G0ePHkWXLl1gY2ODx48fY8uWLYiIiICOjo482khERGVcAYQyv1HJsXYTEVFpsXYTERFRRVKqkeRTpkyBh4cHqlWrhrFjx+Lo0aMwMTGRV9uIiIjoM7F2ExEREREREX1YqTrJd+zYAUtLS9SsWRPXrl3DtWvXJMadPn1aJo0jIqLygWPHFIe1m4iIPgVrNxEREVUkpeokHzlyJAQCTk5HRERUVrB2ExEREREREX1YqTrJDxw4IKdmEBFReVag6AZUYKzdRET0KVi7iYiIqCIpVSc5ERHRp+DFuoiIiMoW1m4iIiKqSJQU3QAiIiIiIiIiIiIiIkXhSHIiIpI7jkUjIiIqW1i7iYiIqCJhJzkREckd5zUlIiIqW1i7iYiIqCLhdCtEREREREREREREVGFxJDkREckdL/5FRERUtrB2ExERUUXCkeREREREREREREREVGFxJDkREckdx6IRERGVLazdREREVJGwk5yIiOSOF/8iIiIqW1i7iYiIqCLhdCtEREREREREREREVGFxJDkREcmdkCdtExERlSms3URERFSRsJOciIjkjqdsExERlS2s3URERFSRcLoVIiIiIiIiIiIiIqqwOJKciIjkroCnbBMREZUprN1ERERUkXAkORERERERERERERFVWBxJTkREcsexaERERGULazcRERFVJOwkJyIiueMp20RERGULazcRERFVJBW+k3zshGGYNmMczMxN4e/3BAvnrcID70dS43u7dMOipbNQzbIKnoWG44cVv+Lff66J7nfu1RWjxw1GY7sGMDIyRIfWfeD3OFBsG+rqavhh9SJ8268H1NTUcPXyDcx3XYm4uAS55Hj01HnsP3IS8YlJqFO7JhbPngzb+nWkxv995Tq27D6EV9ExqF61CmZPHoN2ji0AALl5edi86yCu376Pl5FR0NHWRsvmTTD7uzEwMzUutq2cnBwMmTAbQSHPcHL/FtS1qSXz/FqM6ILWk5yhY6qPmMAI/LHiIF49fCY1vkGPFug0ZwAMqpogMSwG/6w5imDPh6L76zk1Q/NhnVHZtga0DHWxrcdiRAc8l7q9EQfmw7pDYxyZuA5P/vGWaW4A4DKqNwZ/NxBGpkYICQzFpmVb8MQ3SGp8e+d2GDdvNCyqWuBl+CvsXL0bd694ie5v270Neg/vCZtGNtA31MP4rpMQEhAqto2ew5zR2aUTrBvWhrauNnrW74O01HSZ5wYArUd0RadJvaBrqo/IwAicXrEfEQ9DpcY37uGA7nMGwqiqKeLConFhzREEevqK7rd1ao7Ww7qgqq0VtA118UuPBYh87/kbsHo8bFrbQs/cEDnpWQjzeYoLa44gNjRS5vn1G+WCYZMHFT5/AaFYt2wTAnyfSI3v1LM9Js4bW/j8hb3E1tW7cPvKXdH97bu3xbcjeqFuIxvoG+pjZNfxCPYXf7z6DOuJri7foI6tNbR1tdGlXk+5PX9EiqDp4gLtQYOhZGSEvNBQpG7aiLwn0t9X6u07QGfsWChbWCDv5Suk7dqBnLtF7yv1tm2h2asPVG1soKSvj4Tx45AXGiK+z569oPHNN1CxtoGStjZiezpDmJ4mtxxVGrWHin1XCLT0UBD/Ermex1AQEy41Xrl2U6i26g2BnjGEybHIuXkGBeF+RffXsoOKbTsomVlCoKmDzMM/Qhj/smgD6lpQbdkLytXrQaBrBGFmGvJDfZF7+xyQkyXz/BxHdEGHN8f+qMAInFlxAC8+cOxv1MMB3eYMgGFVU8SHReOPNUfx5J1jPwA4ze4PhyGdoKmnjbD7QTi9dB/iw6NF91dpUAPOC4eiWuOaKMgvwOO/vHDux9+Qk5Et8/w8rj/GwSsPkPA6AzaVjbGgXzvYVjeXGv+Pbwi2/XkXkYmvYWmqj5m9WqFt/Rqi+y8/DMWJW/4IfBGLlIxseMwdiLpVTUX3p6RnYftFL9x+8gLRya9hqK2JjrZWmNLDAbqa6rLPzyccB+89Q0J6NmzM9LDgmwawrWQgPb+gKGy7EYTIlExYGmpjZvu6aFvTrCi/p1E44RuBwJgUpGTlwmNkG9Q11y/KLzMH228+xe3weES/zoShpho6WltgShsb6Kqryj6/y/dw8OItxKekwaaaORYO6w7bmlWk53cvAFvPXEVkfDIszY0xa8A3aNvIWnT/v96BOOHpjcDwKKSkZ+LYyomoa2khto0fDl7A3YAwxCW/hpa6GhrXropZAzrDqpKJzPMjIiIiouIq9JzkLn17YNXqRfhlzRZ0ausC/8dPcOL0XpiYGEmMb96iCXbtW4fDh06gYxsX/PnHvzh0ZCvq1iv6EKylrYm7t73xw/Jfpe73R7fFcOrWEeNGzkSfHsNhUckMBw5vkXl+APDXv9ewdvMuTB47DCf2bUad2laY5LoUCUnJEuMfPA7A/JVr8G1PJ5zYvwWd2rbCjEWrEPwsHACQlZWNgKBQTBo9BMf3bcGG1UsRHvES0xZ8L3F77tv2wUzK4ykLDXu2RLelw+C58TR2OC9FdEAERh5aCG1jPYnx1Zpao/+mafA55ontPZYg8J/7GLLLFWY2VUUxaloaiLgfhH/WeHx0/63GdYNQKL9RNh17dcCU5d/hwPrfMKH7dwgNeIZffl8DA2MDifEN7Otj+dYl+MPjIsZ3+w43Lt7Ej3u+h1WdGqIYDS0NPL7nh12rd0vdr4aGOrw87+HwlqMyzkicXc9WcFk6An9vPAl350WIDHiOSYcWQUfK81ejqQ1GbJqBu8eu4tceC+H3z32M3TUXFu88f+paGnh2/wnOrzkidb8vH4fh6LztWNN5DnaOXA0BgO8OLYZASSDT/L7p3REzVkzG3nUHMbrbRAQHhGL94bUwlPL82TZrgO+3LsP5o39ilNME/Pf3Dfy8dxVqvvP8aWpp4JGXH7b+tEvqfjU01XHH0wsHNx+WaT6fo0AON6qY1Dt2hO7kqUg7eBAJEycgNzQUhmt/hcDAQGK8aoMG0F+2DJl//omECROQfeM6DFb9BOUaVqIYgYYmcv0eI23XTqn7FairI9vLC+mHf5d1SsUoW9tDtW1/5N69gKyjqyGMewl1l+mApq7EeKVKNaHWfRzy/G8i68hPyA/1hXrP7yAwrlwUpKqO/MgQ5Nw8I3EbAh0DCHT0kXv9FLJ+/wE5/xyEcvUGUOs8Uub5Ne7ZEr2XjsCljaewwXkxIgOeY8KhhVKP/dWbWmPYpunwOuaJ9T0Wwe+f+xi9a47Ysb/jd73QZkw3nFqyF5tcliEnMxsTDi2EypsOVD0zQ0w6vATxz6OxyWUZ9oxaA3Obqhj862SZ5/e3TzDcz97ApG7NcXTuQNhUMcGUHeeR+DpDYrxvWBQWHfoHLi3rwWPuQHS0rYnZe/9CSFTR4InMnDw0saqEmb0cJW4jLjUdcSnpcO3jiJMLhuCHod/g5pMIfO9xVfb5PYmEu2cgJjla4+jINrAx1cWUE3eRmC75xwbfV4lYdP4BXGyrwWNUG3S0NsfsM/cREve6KL/cfDSpaoSZ7etKzi8tG3Fp2XDtUA8nR7fDD90b42ZYHL6/KH1gy6e66OWPX4/9g0m928NjxUTUqWaByesOI0HKj82+IS+wcOcpfNu2CY6tnIiOTepg1uZjCH4ZW5Rfdi6aWFfDrAHfSN1v/eqV8MPY3jjz0xRsnzMMQgDfuf+O/ALFVTzWbiIiIqpIvrpOcnl2OL5v8rQx+O3gcRw9fBpPg0IxZ9ZyZGZmYeiI/hLjJ00ehSv/XseWTXsR/DQUa37ciEcPAzB+4nBRzAmP/+HXn7fimuctidvQ1dPBsJH9sWyxG67/dwcPff0xffIiOLS0h33zxjLP8dCxM+jfqzu+de6KWlbVsXzedGioq+PMhX8kxv9+/H9o7dAMY4f1R60alpg+cSTq29TCkZPnC9uvo409G1ej2zftYFW9Kho3rIfFrpMREBSMqOhYsW1dv30Pt7x8MHfaeJnn9Zbj+O7w9riKByf+Q1zIK5xfsg+5mdloOrC9xPiWY7sh5Noj3Nz1B+JDI3Fl3UlE+YfDYVRXUczDMzfguekMnt30k7iNtyzqV4fjeGecnS+9s/JzDZjYD38c/RMXj/+N58ERWLdwA7KystFjcDeJ8f3G9YWX5z0c23EcESER2PfrAQT7heDb0X1EMZdO/YtDG36H93Ufqfs9ufc0jmz1QIBPoNQYWegw3hm3Pa7A68Q1xIS8wokle5CTmQOHgR0kxrcb2x1Prj3E1V0XEBsaib/WHcdL/zC0HeUkirl/5jr+2XQaTz/w/N0+ehnPvJ4g6WUcXvqH40/34zCsYgKjqmZS1/kUQyYMwLkjf+CP4xcRHvwcaxeuQ3ZmFnoO7i4xfuC4frjr6YXDO47heUgEdv2yH0F+weg/5ltRzMVTl7BvwyHcuy79rIVje07ht61H4ecTINN8iKT5krVbe8BAZP5xAVkX/0L+8+d4vc4dwqwsaHbvITFeq19/5Hh5IeOYB/IjniN9/z7kBj+F1rdF76usS/8g/dBBZHtLf19lnDqJjKNHkBsg//eVStPOyPO/ifyA2xAmRiHnyhEI83Kh0kByB6mKXScUPPdHns8lCJOikXvnPApiI6DSuIMoJv/JXeR5/YmCCMkj7oUJkcj5Yxfywx5DmBKPgpdByL31Pyhb2QIC2X5cbD/eGXc9ruDem2P/qSV7kZuZg+ZSjv1tx3ZH0LWH8Hxz7P973Qm88g9D63eO/W3Hdse/m8/A/5I3op5EwMN1G/TMDdGwazMAQL1vmiA/Nx9nlu1H3LMovHj0DKeW7EWjHg4w/sAI70/xm6cv+rZqABeHeqhlYYSlAzpAQ00FZ+9KrqlHrj2CY11LjO7UFDUtjDC1hwPqVTWFx/XHopiezetgUrfmcHjnh4F31a5kDPex3dG+oRWqmeijhU1VTHNuiWt+YcjLl23X5G/3w9C3UTW42FZDLRNdLO1qCw1VZZz1eyE5P+9wOFqZYnSLWqhprIupbeqgnrk+PB6EF+XXoComOVrDobrkUdO1TXXh7mKP9rXNUc1QGy2qm2Ba2zq4FhqLPBl3Iv/29230bdcULm3tUKuKKZaOdIaGmirOXn8gMf7wpbtwbFgbo7s7omZlU0zr2xH1qleCx5V7ophejo3wXe/2cKhfU+p++3ewh32d6qhiYoB61Sth2rcdEZ2Yisj4ZJnmR0RERESSfXWd5Orq6ggMlG/HHACoqqqisV0DXLta1JktFApxzfMWmrewk7hOsxZ2xTq/r16+gWYtmpR4v3Z2DaGmpia2nZDgZ3gR8QrNS7GdksjNzUVAUDBaNrcTLVNSUkLLZnZ46Cf5MX7oH4hWzezEljk62OOhv/TnJC0tAwKBALq62qJl8YlJWPnzRrgtmwsNDY3PykMaZVVlVGpohdB3OkOFQiFCb/qhalNrietUa1K7WOd3yH+PUK1p7VLtW1VDDf03TsUfyw8gLS6l9I0vARVVFdSxtRHrzBYKhfC+7oP6TetLXKeBff1ind9e1+6hvr3keEVSVlVG1YZWeHqzqBNAKBQi+OZjVG9qI3GdGk2sxeIBIOi/h1LjS0JNUx0OAzogISIGyVHxn7yd96moqqBOIxuxzmyhUIh7N3zQ0L6BxHUa2tcv1vl91/Oe1PiyRCiH/+jr8aVqN1RUoGJjg5x3O7OFQuT4eEO1geT3iWr9BuLxAHLu3ZMar3BKylAys0RBxLuPpxAFEYFQspDcwaZUqSby3+v8LogIgLKU+BJT1yycakUou05IZVVlVGloJfZDZuGx3w/VpdTu6k2sEfxe7Q7675Eo3qiaGfTMDMVisl5nIsI3VBSjoqaK/Nw8sR90crNyAABWzaVPQVdauXn5CHwZJ9aZraQkgINNVTx6Z+qXdz0Kj4aDTTWxZa3qVpMaX1JpmTnQ0VCDirLsPu7n5hcgMDpFrDNbSSCAQ3UTPIpMlrjOo8ikYp3frWqY4lFk0me1JS07FzpqKlBRkmF+efkIfB6FlvWLzjRRUhKgZX0rPAp9KXGdR6EvxeIBwLFhLTwKkRxfEhnZOfjfDV9UMTGAhZH+x1eQE9ZuIiIiqkgUNie5q6urxOX5+flYs2YNjI0L57det26dXPZvbGwIFRUVxMWJd4rFxcbD2kbyl0ozcxPExYrHx8bGw8y85HMFmpmbIDs7B6kpr8WWx8UlwMxMtnMOJiWnIj+/AMZGhmLLjY0MERYh+YN7fEJSsXgTI0PEJ0j+IpOdnYP12/ehR+f20NEu7CQXCoVY+tM6DHRxRsN6NngVFSODbIrTMtSFsooy0uPFO6nT41JhWquyxHV0TA2Q9l58WlwKdEwMSrXvbsuH44X3Uzy5JPs5yN/SN9KHsooyEuPEH/uk+CRY1q4mcR0jU0Mkxr8XH5cMI1P5TXnzqbQN9aCsoozX7z0fr+NSYFZL8ryfuqYGEuP1TEr/BbL18C7otWgY1LU1EBP6CtuHr0Z+bn6ptyONgZE+VFSUiz0fiXFJqF7LUuI6xqZGxZ7vxPgkGJsaSowvS3iKdfmg6NqtpK8PgbIKCpLE3ycFSUlQs5T8vlIyMpIYr2T49R0XAUCgqQOBkjKEGaliy4UZr6FkZCF5HS09ifECbcnTl5SIhjZUW/RAnt+NT9+GBG+P/e/X4sJjv+TaLenYnxaXAt03tVvXVF+0jWIxpoUxIbf80XvpcHSY2BPX9/8FNU0NOC8YAqBwKhZZSUrPQn6BEMa6WmLLjXW1EB4j+bNU/OsMGOtqFouPT5U8PUuJ2pGWid3/3ENfR9n+GJSUmYN8oRDGWuLznBtrqSM8UfJ0JPHp2TDWVhOP11ZDvJTpWUrUjowc7L4dgr6NJX8e+uTtvs4ofP70tMWWG+tpI0zKD+nxKWkw1tMpFh+fWvprFhy7cg/rT/yLzOxc1LAwxs65w6Gqolzq7cgKazcRERFVJArrJN+wYQMaN24Mg/fmEBUKhQgMDIS2tjYEgo/PD5ydnY3sbPEP2UJhAQQyPjWYisvNy8OcZashFAqxbN400fLDJ88hPSMD40cMVGDr5KdO56ao2aoBtjsvVnRT6DN4/+8Ggm48hp6ZATpO6IlRW2diU/8VyMvOVXTTiL5a8qzd2QUFUJfhiFD6DGoaUO8zDcLEKOTePa/o1shETPBLeMzZjl7LRqD7/MEQ5hfgxoGLSI1LhlCBcz7LQ1pWDqbvuoCa5kb4rltzRTdH5tKyczH99D3UNNbBd46ffibZ16hHS1u0bFAT8clpOPj3bczbfgoHF4+BuqrCvrIRERERVRgK+8S1evVq7Nq1C+7u7ujUqZNouaqqKg4cOID69Us2PYSbmxu+/178opGaakbQUjf+4HoJCUnIy8uDqan46G1TMxPExsRJXCc2Jh6m7432NjMzQWxMyadoiI2Jh7q6GvT0dcVGk5uaGiM2VnZTPQCAoYEelJWVkJAoPnIpITEJJkaSR02ZGBsWi49PTIKJsXj82w7yyJhY7Nu0RjSKHAC8vB/iod8TNO3YW2ydQeNnwLlLR6xeNvdz0hLJSHqN/Lx8aL83iljbVK/YaLK30uKSofNevI6pPtJKMd9jTcf6MKxuhkWPxC98OXj7LDy/9wT7B/9U4m19SEpiCvLz8mH03ihiQxNDJMZKHo2WGJcEI5P34k0NkBiXKJM2yVJ6Uiry8/Kh+97zoWuqj9S4ZInrvI5LlhwfX/opb7JeZyLrdSbiw6Px/EEwfnq4F7ZOzfHgnOTrCZRWcmIK8vLyiz0fRqaGSJDyfCTEJRZ7vo1MDJEQ93mnpH8NeIp1+SDP2j2nuiXmWdX44HoFKSkQ5udByVD8faJkaIj8RMnvq4LERInxBUlf33ERAISZaRAW5EOgJT4KXKClC2F6quR1MlJLFf9BqupQ7zMdyMlC9oUdgIw7kN8e+9+vxaU99uuY6uP1m9r9tubrmurj9Tvb0DHVR2RAuOjvB+du4cG5W9Ax0UdORhYgBNqNd0ZChPg1VT6HobYGlJUESHjvIp0JrzNgoqclcR0TXS0kvM4scfyHpGflYMqO89DWUMO6cd2hqizbUciGmmpQFgiQkCH+I1dCRjZMtNUlrmOirY6E9Bzx+PQcqfEfkp6ThyknvaCtqox1LvZQleFUMgBgqKtV+Py9d5HOhNR0mOjrSFzHRF8HCe+NGk9ITYeJnuT4D9HV0oCulgaqmxujUa2qaDNtLa54P0H3lg1LvS1ZYO0mIiKiikRhQ7YWLlyIY8eOYfLkyZg7dy5ycz9t9OaiRYuQkpIidtNU+/hps7m5uXjo6492HVqJlgkEArRr3wr3vHwlrnPfyxft2rcSW9a+oyPue0m+kI8kvr5+yMnJEdtO7dpWqGZZBfdKsZ2SUFVVRf061rh731e0rKCgAHe9fdG4YT2J6zRuUA93vH3Flt2+9wCNGxTFv+0gj3gRiT0bVsNAX/yL+aJZ3+HUwa04eaDwtu2XHwAAv36/CDMmjZJNcgDyc/MR5ReGmu+cSiwQCFDTsSFe+gRLXOfFgxCxeACo1aYhXviElHi/17efx7Zui7C9x2LRDQD+WvU7zsyV3UU883LzEPT4KZq2aSpaJhAIYN+mCQKkXJDR3zsATduIz23frK09Ary/vgs45ufm46VfGGwci774CQQCWDs2xHOfpxLXCX8QLBYPADZtGkmNLzGBAAKBACpqqp+3nXfk5eYh6NFTNHvv+WvWpin8vP0lruPnHSAWDwAt2tlLjS9LCuRwoy9PnrV7RnXJ06WIyctD3tOnUGtqX7RMIIBa06bI9Zf8PskN8BePB6Bm30xqvMIV5KMgNgJK1eq+s1AApWp1URD9TPIqUc+gLBYPKFWrh3wp8VKpaUD925lAQT6yz28D8vNK2fiPy8/Nxyu/MFi/d+yv7dgAz6XU7ucPgmH9Xu22aWMrik98EYvU2CSxbarraMLSrpbEbabFpyAnIxuNe7ZCXnYOnt54XCzmU6mqKKNeVVN4BRdNa1dQIITX05doVEPydDmNaliIxQPAnSDp8dKkZeVg8vZzUFVWwobxPeQy+lhVWQn1LPTh9bxoYEeBUAiv5wloVNlA4jqNKhvCK0J8IMid53FoVLl009ykZedi8vG7hfn1bQ51OUxDoqqijHrVK+FuYJhoWUGBEHcDw9ColuSLpjaqVVUsHgDu+D9Do9qS40uqcP58IXLyZP8+LCnWbiIiIqpIFHpec/PmzeHt7Y24uDg0a9YMfn5+JTpN+13q6urQ09MTu5V0qpXtW/ZjxKiBGDT0W1jb1MKv67+HlpYmjv5+CgCwdedaLF0xRxS/c/tBdOrcFlOmjUVt65qYv2g67Jo0xJ5dv4tiDAz10dC2HurULbwQZG1rKzS0rSeab/x1ahoOHzqJVasXoU1bBzS2a4BN293gddcH3vcelir3khg56FucPH8R//vzEkLDI7Dq1y3IzMqGi3MXAMCiVb9i/fb9ovjhA/vg5h1vHDh6Cs+ev8DWvb/D/0kwhvbvBaCwg9x1yU/wfxKMNSvmo6CgAPEJiYhPSBR1llSyMIN1zRqiWw3Lwi8J1apUgoWZqUzzu7XnL9gP6Qi7fm1hUqsyev40Bmpa6vA5cQ0A0Nf9O3SeP0gUf2ffRdRu3wiO43vApFYldJzVF5Vta+LuwX9EMZr62rCoXx2mtQvnxTapWQkW9atD582cp2lxKYh9+lLsBgApkfFIfin5LIRPdWLXKfQc0gNO/bvAsrYlZrvNhIamBv46dhEAsGjDAkxYOE4Uf2rvabTo0BwDJ/aHZa1qGO06EnUa2eDMgf+JYnQNdFG7fi1Ut6kOAKhWqxpq168lNoLZyNQQtevXQpUahfPDWtW1Qu36taBroCvT/Dz3/IGWQzqheb92MKtVGf1/Ggc1LXXcffP8DXWfAuf5g0Xx/+37C3XbN0aH8c4wq1UZTrP6o5ptTVw/+LcoRktfG5XrV4fFm+fPrGZlVK5fXTRnrXE1M3wzpQ+qNrSCQWVj1Ghqg9FbZyE3KweBV2X7Q9XR3SfQe2hP9BjghOq1LTF/zWxoaGrgwpvnb/nGRZi8cLwo/vjeU2jZoQWGTBqA6rWqYZzrKNRtVAcn958RxegZ6MK6QS1Y2dQAAFjWsoR1g+LPn3WDWqhao/AxqFW3Jqwb1IKejJ8/qpjkVbtLOtVK+onj0OzpDA0nJyhbVofubFcINDSRdfEvAIDeosXQGT9BFJ9x6iTUWrSA1oCBUK5mCe1Ro6Fapw4yzhS9rwS6ulCpVRsqNQqPi8qW1aBSq7bYvOVKhkaFMVUK31cqNWtCpVZtCHRl/77K8/kXKg3bQLleSwgMLaDaaQgEqmrICyg800Wt62ioOroUxftegVL1BlBp0hkCQ3OoOvSEknl15D30LNqouhYEJlUhMK70Jh9zCEyqAm9HoKtpQN1lBgSqasj59xCgpll4n5YeUMrn92Ou7fkDDkM6otmbY3/fn8ZCTUsd994c+we7T0b3d4791/f9hTrtG6P9eGeY1qqMrrP6oaptTdx859h/fd9f+Ga6C+p3todFnWoYsm4yUmOS4PfPfVFM65FdUaVBDZhYWcBxRBd8+8No/LnWA1mfMfe3JCM62OH07QCc83qCZ9GJ+OmEJzJz8tDHoXDAwdLf/8Wm87dF8UPbN8KtwAgcuvoAYTFJ2P6XFwJexGJwW1tRTEp6Fp68jMOzmMIzIJ7HJuPJyzjEvxnx/LaDPDMnDyuHdEJ6Vg7iU9MRn5qOfBmfDTCimRVOP3qBc34v8SzhNX76xw+ZuXno07BwfvClf/hi039FF5Idal8Dt8LicOjeM4QlpGH7zacIiE7B4CY1ivLLzMGTmBQ8Sygckf08KR1PYlIQn5ZVmF92Liaf8EJmbj5WOjVCenYu4tOyEJ9WOAe8TPNzaoXT13xw7uZDPIuMw4+//YHM7Fy4tLEDACzZfRYbT14WxQ/r4oBbfqE4ePE2wqLisf2sJ/zDIzG4U9FUNylpmXgSEY1nkYWfE8OjE/AkIhrxKYX5voxNwt4/biAgPBJRCSnwDXmBudtPQl1VFW0aSb6gbUWxdetW1KhRAxoaGnBwcICXl9cH40+cOIG6detCQ0MDtra2+PPPP8XuFwqFWL58OSpVqgRNTU107twZwcHiP6b5+PigS5cuMDAwgLGxMSZOnIi0tNLPMU9ERERli8InuNPR0cHBgwfh4eGBzp07Iz9fdhfO+5izp/+EsYkRFi6eATNzU/g9DsTAfuMQF5cAAKhatRIK3vlicc/rASaNm4PFy2ZhyQpXPAsNx8ihU/EksOiDVbfunbBlx8+iv/cc2AAAWOu2GWvdNgMAli5ajQKhEPt/3ww1NTVcvXwD811XyiXH7p3bIyk5BVv2/I74xETUta6FHe6rRNOtRMXEQumdL79NbOvj55ULsHnXQWzceQDVq1bBJrdlsK5ZAwAQG5eAqzfuAAD6j54qtq99m39Gi6aN5JKHNH4X7kDLSBedZveHjqk+ogOf47dRPyM9vvAUc/0qxm9G4hR64ROMkzO34ps5A9B53kAkhEfj6MR1oo5uAKjTxR59f50k+nvglukAgKsbTuHqhtNfKLNCV897wsBYH2PmjoaRqSFCAkIxf8QiJL05xdy8ipnYXKr+3gFYNW01xs0fg/ELxuJV2CssHb8CYUHhopjWXVph4fr5or9XbF8KADiw7hAOrDsEAOg9ohdGu44UxWw+vQEAsGb2Wlw8UfSDwufyvXAbOkZ66DZ7APRMDfAq8Dl2jlojuqCbYRUTsecv3Ocpfpu5GT3mDILzvMGIC4/Gvom/Ivqd569Bl2YY+utk0d+jtswEAFzccBJ/bziJ3Oxc1GxeF+3HdIemvg5ex6fgmVcgNvZbjrSET5ia4AMun7sKQyN9jJ87GsamRgj2D8Xs4QuQ9OZinuaVzcSOMY/v+2PFtB8xcf5YfLdgPF6EvcKCccvw7J3nr01XRyxbv1D094/blwMA9rgfwN51BwEA347ojfFzRotidpzZBABYNXsN/jxe1Kn0JRUIecp2eaLI2p199Spe6xtAZ/RYKBkZIS80BEkL5okuzqlsZiY2RUiuvz9SflwFnbHjoDN+AvJfvUTysiXIDy8a+anu2Br6CxeJ/jZYvhIAkHZgP9IPHgAAaPbuDZ3RY0QxRpsKa3rKGjdk/X1RpjnmB3sjV1MXqi17QaClh4L4l8g+uxnIKJymTaBrBLzzniqIeoaci3uh6tgbqo59IEyORfaFHRAmRIpilGs2hnrXorO51HsU/pCQe+cCcu9egJKpJZQrFV64XHP0j2Ltydy3BMLXCTLL7+GFO9Ax0oPT7P7QNTVAZOBz7PnAsf+5TzAOz9yCbnMGovu8QYgPj8aBie5ix/6rO85DTVMd/d3GQ1NPC2H3grB71Bqx60xUa1wLXWf3h7qWBmKfReLk4j3wOSPbC5MCgFNTaySlZ2L7X3cRn5qBOlVMsG1ST9HFPKOSXov9sGRnVQmrR3bB1j/uYvOFO7A0NcD6cd1Ru1LR1IGefmFYcfSK6O8Fhwpr8SSn5pjcvQUCX8Th8fPCC6X3+rFo8AYA/LFsBKoYf8ZFXN/Pr25lJGXkYPvNp4hPz0YdMz1s698Cxm+mT4l6nSmeXxUjrO7ZBFuvB2Hz9SBYGmph/bfNUNu06Acmz9AYrPjrUVF+5wt/tJ7kaI3JrW0QGJOKx1HJhfnt8RTPb2JHVNEv/dQ00nRr0QBJr9Ox7awn4lPSUKeaObbNHgrjN9OtRCemQEnpnfxqV4PbxL7YcvoqNp++AktzI2yYPgjWVc2K8vMNwvJ954ry21E4IOe73u0w2aUD1FRV4PM0Ar9fuovU9EwY6+nAvo4lDi0eU+wiol+Somv3sWPH4Orqih07dsDBwQEbNmyAk5MTgoKCYGZmViz+1q1bGDJkCNzc3NCzZ08cOXIELi4u8PHxQcOGhWearF27Fps2bcLBgwdhZWWFZcuWwcnJCQEBAdDQ0EBkZCQ6d+6MQYMGYcuWLUhNTcWsWbMwevRonDx58ks/BERERPQFCYTCr6fn4uXLl/D29kbnzp2hrf3pHwhN9MrXRXzeF/VMtl/Gv0armi1TdBPk6r+8GEU3Qa6aqJh8PKgMu5Nbvp+/26+uynybI6r3lfk2f3v+ZX+0IslkVbtjOraXYau+Proukqc5K0+Wry/99SHKklXbW308qCx7Fa7oFsiVoJ79x4PKMI3Ww2S+TUXXbgcHBzRv3hxbtmwBUDhtZLVq1TB9+nQsXLiwWPygQYOQnp6OCxcuiJa1bNkSdnZ22LFjB4RCISpXrow5c+Zg7tzCaySlpKTA3NwcBw4cwODBg7Fr1y4sW7YMUVFRUHpzhtPjx4/RqFEjBAcHo3bt2p+TPhEREX3FFDrdyvuqVq2KPn36fNaXbCIi+voI5XCjrwNrNxFR+SSP2p2dnY3U1FSxW3a2+IVgASAnJ0f0A+xbSkpK6Ny5M27fvl0sHgBu374tFg8ATk5OoviwsDBER0eLxejr68PBwUEUk52dDTU1NVEHOQBoamoCAG7ckP2ZJ0RERPT1+Ko6yYmIqHwqgFDmNyIiIpIfedRuNzc36Ovri93c3NyK7Ts+Ph75+fkwNzcXW25ubo7o6GiJ7Y2Ojv5g/Nt/PxTTqVMnREdH45dffkFOTg6SkpJEo9ajoqI+4VEkIiKisoKd5ERERERERCR3ixYtQkpKitht0aJFH1/xC2nQoAEOHjwId3d3aGlpwcLCAlZWVjA3NxcbXU5ERETlj8Iv3ElEROWfkCO/iYiIyhR51G51dXWoq6t/NM7ExATKysqIiRG/DkxMTAwsLCwkrmNhYfHB+Lf/xsTEoFKlSmIxdnZ2or+HDh2KoUOHIiYmBtra2hAIBFi3bh1q1qxZohyJiIiobOLP4UREJHcFcrgRERGR/CiydqupqcHe3h6XL18uak9BAS5fvoxWrSRfRLdVq1Zi8QBw6dIlUbyVlRUsLCzEYlJTU3H37l2J2zQ3N4eOjg6OHTsGDQ0NdOnSpRQZEBERUVnDTnIiIqoQtm7diho1akBDQwMODg7w8vL6YPyJEydQt25daGhowNbWFn/++afY/adPn0bXrl1hbGwMgUAAX19fsfsTExMxffp01KlTB5qamrC0tMSMGTOQkpIi69SIiIjKHVdXV+zevRsHDx5EYGAgJk+ejPT0dIwZMwYAMHLkSLGpWmbOnImLFy/C3d0dT548wcqVK3H//n1MmzYNACAQCDBr1iz8+OOPOHfuHB4/foyRI0eicuXKcHFxEW1ny5Yt8PHxwdOnT7F161ZMmzYNbm5uMDAw+JLpExER0RfG6VaIiEjuFH2hzWPHjsHV1RU7duyAg4MDNmzYACcnJwQFBcHMzKxY/K1btzBkyBC4ubmhZ8+eOHLkCFxcXODj44OGDRsCANLT09GmTRsMHDgQEyZMKLaNyMhIREZG4tdff0X9+vXx/PlzfPfdd4iMjMTJkyflnjMREdHnUHTtHjRoEOLi4rB8+XJER0fDzs4OFy9eFF14MyIiQmyecEdHRxw5cgRLly7F4sWLYW1tjbNnz4rqNgDMnz8f6enpmDhxIpKTk9GmTRtcvHgRGhoaohgvLy+sWLECaWlpqFu3Lnbu3IkRI0Z8ucSJiIhIIQRCobDcTRRromej6CbIVdSzi4pugtytarZM0U2Qq//yYj4eVIY1UTFRdBPk6k5u+X7+br+6KvNtDqjeR+bbPPH8fyWOdXBwQPPmzbFlyxYAhadsV6tWDdOnT8fChQuLxQ8aNAjp6em4cOGCaFnLli1hZ2eHHTt2iMWGh4fDysoKDx48EJvTVGKbT5zA8OHDkZ6eDhUV/k79rpiO7RXdBLnSdamn6CbI3fL15fssiVXbJU/xUG68Cld0C+RKUM9e0U2QK43Ww2S+TUXXbiIiIqIvidOtEBGR3Anl8F92djZSU1PFbtnZ2cX2nZOTA29vb3Tu3Fm0TElJCZ07d8bt27cltvf27dti8QDg5OQkNb6kUlJSoKenxw5yIiL66smjdhMRERF9rdhJTkREciePi3+5ublBX19f7Obm5lZs3/Hx8cjPzxednv2Wubk5oqOjJbY3Ojq6VPElER8fj1WrVmHixImfvA0iIqIvhRfdJiIiooqEQ9mIiKhMWrRoEVxdXcWWqaurK6g1H5aamgpnZ2fUr18fK1euVHRziIiIiIiIiOgd7CQnIiK5k8flL9TV1UvUKW5iYgJlZWXExIjPJR8TEwMLCwuJ61hYWJQq/kNev36Nbt26QVdXF2fOnIGqqmqpt0FERPSllcNLVxERERFJxelWiIhI7goglPmtpNTU1GBvb4/Lly8XtaegAJcvX0arVpIvxNeqVSuxeAC4dOmS1HhpUlNT0bVrV6ipqeHcuXPQ0NAo1fpERESKosjaTURERPSlcSQ5ERGVe66urhg1ahSaNWuGFi1aYMOGDUhPT8eYMWMAACNHjkSVKlVEc5rPnDkT7du3h7u7O5ydneHh4YH79+9j165dom0mJiYiIiICkZGRAICgoCAAhaPQLSwsRB3kGRkZ+P3330UXFwUAU1NTKCsrf8mHgIiIiIiIiIikYCc5ERHJnaIv1jVo0CDExcVh+fLliI6Ohp2dHS5evCi6OGdERASUlIpOrnJ0dMSRI0ewdOlSLF68GNbW1jh79iwaNmwoijl37pyokx0ABg8eDABYsWIFVq5cCR8fH9y9excAULt2bbH2hIWFoUaNGvJKl4iI6LMpunYTERERfUnsJCciogph2rRpmDZtmsT7PD09iy0bMGAABgwYIHV7o0ePxujRo6Xe36FDB87nSkRERERERFQGsJOciIjkTsh5SImIiMoU1m4iIiKqSNhJTkREcseLdREREZUtrN1ERERUkSh9PISIiIiIiIiIiIiIqHziSHIiIpI7zs1NRERUtrB2ExERUUXCTnIiIpK7AkU3gIiIiEqFtZuIiIgqEk63QkREREREREREREQVFkeSExGR3Al58S8iIqIyhbWbiIiIKhKOJCciIiIiIiIiIiKiCosjyYmISO4KOBqNiIioTGHtJiIiooqEneRERCR3QiG/aBMREZUlrN1ERERUkXC6FSIiIiIiIiIiIiKqsDiSnIiI5I6nbBMREZUtrN1ERERUkXAkORERERERERERERFVWOVyJHlDPUtFN0Gu1tsvV3QT5M5YKFB0E+QqLT9b0U2Qq6HC8p1ftIq+optQ5gg5Go0+4kWwoaKbIFd+a9MU3QS5G6VWvnOc+J2nopsgVzfSQhXdBLk6r/9U0U2Qq4bPhsl8m6zdREREVJGUy05yIiL6uhTw4l9ERERlCms3ERERVSScboWIiIiIiIiIiIiIKiyOJCciIrnjWDQiIqKyhbWbiIiIKhJ2khMRkdwV8Ks2ERFRmcLaTURERBUJp1shIiIiIiIiIiIiogqLI8mJiEjuOBqNiIiobGHtJiIiooqEI8mJiIiIiIiIiIiIqMLiSHIiIpI7oZCj0YiIiMoS1m4iIiKqSNhJTkREcsdTtomIiMoW1m4iIiKqSDjdChERERERERERERFVWBxJTkREcifkaDQiIqIyhbWbiIiIKhJ2khMRkdxxXlMiIqKyhbWbiIiIKhJOt0JEREREREREREREFRZHkhMRkdzx4l9ERERlC2s3ERERVSQcSU5EREREREREREREFRZHkhMRkdxxXlMiIqKyhbWbiIiIKhJ2khMRkdzxlG0iIqKyhbWbiIiIKhJOt0JEREREREREREREFRZHkhMRkdwJORqNiIioTGHtJiIiooqEneRERCR3BZzXlIiIqExh7SYiIqKKhNOtEBEREREREREREVGFxZHkREQkdzxlm4iIqGxh7SYiIqKKhCPJiYiIiIiIiIiIiKjC4khyIiKSO85rSkREVLawdhMREVFFwk5yIiKSO56yTUREVLawdhMREVFFwulWiIiIiIiIiIiIiKjC4khyIiKSO56yTUREVLawdhMREVFFUuE7yV1G9cbg7wbCyNQIIYGh2LRsC574BkmNb+/cDuPmjYZFVQu8DH+Fnat34+4VL9H9bbu3Qe/hPWHTyAb6hnoY33USQgJCxbbRc5gzOrt0gnXD2tDW1UbP+n2QlpoutxybjOyMFhOdoW2qj9jACPy74hCiHz6TGl+nRwu0mdMf+lVNkBQeg2trPPDs6kPR/dbdmsFu2DewsK0BTUNdHOi+GLEBEVK31//gPNTs0BinJ6xHyD/eMs0NABqN7Az7Sc7QMtVHfGAEPJcfQswH8qvt3AKt5vSHXlUTJIfH4KabB8Lfya9Wt2awHf4NzN7kd7jbYsR/IL8+B+ehRsfGOD9+PZ7JIb8Bo7/FiClDYGxqhOCAUPyyZAP8fQOlxn/TswMmLxiPSlUt8CLsJTb/uAM3r9wR3d+xRzv0G9kHdW3rwMBIH0M7j8FT/xCxbXw7vBe6fdsFdWxtoKOrjQ51uiMtNU3muQGA2ajusJjsAlVTA2QEhCNi2R6k+wZLjTfs6Ygq84ZAvaoZssKi8HL1IaRc8Sm6v3tLmI5wgnajWlAx1IVf19nI9A8vth1t+zqoumAYtJtYA/kFyPAPQ9CwHyDMypFpfl1Gdkevid9C39QAEYHhOLBiN0IfSs/PoYcjBswZCtOqZogOj8LRNYfge7XoddW8W0t0HtYNVrY1oWuoh4XdZ+N5QFhRXvo6GOA6BLZt7WBSxQSpCam4/89dHHc/gszXGTLNrTR4yjbJkumo7rD47tvC40ZgOF4s2/3h44azIyrPG1p43AiPwqvVh5Bypeh9ZdC9JUyHd4N2o5pQMdSDf9fZyHznfQUAAnVVVFs2BkZ92kCgporUa754vngH8uJT5JJj3VGd0XCyMzRN9ZEYEIG7yw4h3ld6baveswWazusPnaomSA2Lwf3VHnh1pai2WXZvhjojvoFxoxrQMNTFua6LkegvXtuU1VXRbPlQWPVpCWU1VbzyfIQ7iw8gKz5V5vkZjegB04l9oWJqiKzAMESu3InMDxwb9Xq0hrnrcKhVNUNOWCSifz6A155Fz6GeUysYDesOzYa1oGKoh+AeM5AVKP4cGg5xgkHv9tBsUAvKulrwbzQYBa/l8/mr88hu6DHRBfqmBngRGI5DK/bg2cMQqfEterRCvzlDYFLVDDHhUTi25jc8vOojFtPXdTA6DukCLT0tPL3/BAeW7EJMeJTo/uoNa2LwwhGwalQbBQUFuP/XbRxedQDZGVkyz2/EuEGYOG0UTM1MEOj/FCsXrsFDHz+p8T16d4Hr4qmoWq0ywp5F4OfvN8Dz3xtiMbMXTsHgEX2hp6+L+16+WDb3J4Q/K3qNWtWqjkXfz4Z9CzuoqqniiX8w1rltxZ0b92Sen9EIZ5hMKHp9Rq3cicxHT6XG63UvfH2qVjVHTnjh6zPN837R/U6tYDS0OzQa1oaKoR5CnKcXf30OdoJB7w7QePP6DGg8SG6vz5Ji7SYiIqKKpEJPt9KxVwdMWf4dDqz/DRO6f4fQgGf45fc1MDA2kBjfwL4+lm9dgj88LmJ8t+9w4+JN/Ljne1jVqSGK0dDSwON7fti1erfU/WpoqMPL8x4Obzkq44yKq9vTAR2XDsPNjWdwsOdSxAVGYOBvC6BlrCcxvrK9NXptnorHx6/hgPNSBP/jjW93zYaJTVVRjKqmOl7dC8K1Ncc+uv9m47pBKMdRKNa9HNB22TDc3XAGR50L83P5fQE0peRXyd4a3TdPhf+xazjSYylC//ZGz92zYfxuflrqiLwXhJtuH8+vybhugBzz69K7E2avnIbd7gcw3Gk8ngaEYPNRdxhKeY02atYQP21fgf8d+QPDuo6D58Xr+HX/atSqYyWK0dTShO/dx9j80w6p+9XQ1MCtq3exf9Nvsk5JjFHv1qi2Ygwi1x2Df7c5yAgIh83h5VAx1pcYr9OsDmptdUX80cvwd5qD5L/vovbehdCsYymKUdJSR5pXIF78dEjqfrXt68Dm92VIueaLAOf5CHCeh5gDfwIFBTLNr2XP1hixdCxObfTA4p6ueB4YjoW/rYCelPys7etg+uY58Dz+LxY5u+L+P3cxZ9dCVLUpyk9dUwNB9wJwdI3k/AzNjWBgboTDPx3AvC4zsWPuJjRu3wST1k6TaW5EimLYqzWqLR+LyPUeCOjuisyAcFj/vkLqcUPbvg5qbp2DeI9/EdDNFckX76LWnoXQEDtuaCDtXgBerpZ+3Ki2Yiz0uzRH6KRfENR/KVTNDVF790KZ5wcANXo7oPmKYfBddwbnui1FYkAEuhxeAA0ptc20mTXab52Kp0ev4ZzTUkT87Y1Oe2fDoE5RbVPRUkesVxC8f5Je25qvHIZqXZrAc9JmXOz3I7QsDNFxzyxZpwd95zaotGQ8YjceRUjPWcgKDIPVwR+gLOU51GpaF5Yb5yHp+D8IcZ6J1Et3YLlzCdRtxJ/DjHsBiP75oNT9KmmoI+2aD+K2nZB5Tu9y6NkaQ5eOwZmNx7Gs51xEBIZj/m/LP3jsn7LZFdeOX8Yy5znw/scLs3YtEDv2O3/3LbqOdsb+xTuwss9CZGdkY/5vy6CqrgoAMDAzxMLDKxATHoWVLgvwy8hVqGJjiYnu02Wen7OLE5asmouNv+xEz06DEegXhIMntsPYxEhifNPmjbFx9xoc//0MnDsOwqU/r2LnbxtgU7e2KGbSjDEYPXEIls79Ed92HY7MjEwcPLEdaupqopi9RzZDWVkZw1wmoHenIXjiH4S9RzbDxMxYpvnpObeFxeLxiN10FKG9ZiIrMAw1PvD61GxaF9U2zkfS8UsI7TkDqf/cgeWOJVC3qS6KUdLUQPr9AMT8fEDqfpU01fH6P2/EbT8u03yIiIiIqGQqdCf5gIn98MfRP3Hx+N94HhyBdQs3ICsrGz0Gd5MY329cX3h53sOxHccRERKBfb8eQLBfCL4d3UcUc+nUvzi04Xd4X/eRuA0AOLn3NI5s9UCAj/TRwLLSbHx3PPK4Cr8T/yEhOBJ/L96P3Mxs2A5sLzl+jBPCrj2C184/kBgSiRvuJxHjF46mo7qIYgLO3MStTWcRfkP6iCEAMKtvieYTeuDiPOk/GHyupuO7w//oVQSc+A+JwZG4smg/8jKz0WCQ5Pzsxjrh+bVH8Nn5B5JCInHH/SRi/cLReHRRfk9O34TXxrOI+Eh+JvUt0WRiD1ySY37DJg3C2cPncf7Ynwh7Gg63+b8iKzMLvYc4S4wfPL4/bl/1wm/bjyI8+Dl2rN2LJ4+fYuDYvqKYP0/+jT3rD8Drv/sStwEAR3efwMEth+Hn7S/znN5lPqE34o5cQvzxK8gKfonnC3egIDMbJoO/kRw/ridSPB8gesdZZIW8xKtfjiLD7xnMxvQQxSScuobIDceRev2hxG0AgOXKMYjd9weit55G1tMXyAqNRNL5WxDm5Mk0P+fxfXDF4x9cO3EFr4JfYu/i7cjJzEaHgZLz6z6mFx5e88GFnWcRGfISJ9yPIMzvGZxGFeV344wnTm86jsc3HkncxsunEdjw3c/wuXwPsRHR8L/1GMd+OYym3zSHkrLiDvkFQqHMb1QxmU/sg/ij/yBBdNzYjoKsDx03eiHF0wcxb44bkb8eKTxujC56XyWe8kTUhuNIvS75faWsqwWTwZ3x8od9eH3rMTIehyLcdTN0mteDdlMbmefYYEJ3PD1yFSHH/0NKcCRuLyysbdaDJde2+uOc8MrzEfx3/IGUkEg8+OUkEv3CUW9MUW17duomHm44i6jrkmubqq4mrAd3wL3vDyP6ZgASHofj5uxdMG9uA9OmtWSan8l4FyQd+xtJJy8jO+QFXi3ZhoLMbBgN6CIx3nhMb7y+5oP4XWeQHfoSMesOI8s/FMYje4piks9cRexmD6Td8JW634T95xC34yQyHjyRaT7v6z6+Fzw9LuH6iSuIDH6J/Yt3IjszG+0GdpIY33VMTzy69gB/7vwfIkNe4ZT7UYT7haHzqO6imG7jeuLclpPwuXQPL548x07XTTAwM4J91xYAgCbfNEN+bj4OLtuN6GeRCHsUgv2Ld6BFj1Ywq24h0/zGTxmBY7+dxskj/0NI0DMsmfMjMjOzMGCYi8T4MZOG4drlW9i15SBCn4ZhndtW+D8KxMjxg0UxYycNwxb33bj0lyeeBARjzuSlMLcwRdcehY+ZoZEBrGpXx46N+/AkIBjhzyLw8w8boaWtiTr1akvc76cyGVf4+kw++S+yQ14gculWFGRmw1DK69NkdG+8/s8b8btPIzv0JWLX/1789Xn2KuI2eyDtpq/U/SbsP4f4HSeR+UD6Ga1fGms3ERERVSQVtpNcRVUFdWxtxDqzhUIhvK/7oH7T+hLXaWBfv1jnt9e1e6hvLzle0ZRUlWFha4XwG+90dAqFeH7DH5WbSv5CUblp7WKd32H/PZIaL42Khhp6bpqKS8sOID1OPqeiK6kqw8zWChHv5Rdxwx8WUtpbqWntYp3fEf89khovjYqGGrptngrPpQeQIaf8VFRVULeRDe5eLzqdXCgUwuv6fTSybyBxnUbNGsLrunjn921PL9jaN5RLGz+HQFUF2o1qiXdmC4VIvfEIOvZ1JK6jbV+nWOd3iqcvdOxL3kmlYqwPnaZ1kBufgnr/c4Od737UOfkjdJrX+6Q8pFFWVYGVbS34vdOZLRQK4XfjIaybSs7PumkdsXgAePTfA6nxJaWlp4XMtAwU5Mt2pHxZs3XrVtSoUQMaGhpwcHCAl5fXB+NPnDiBunXrQkNDA7a2tvjzzz/F7j99+jS6du0KY2NjCAQC+Pr6FttGVlYWpk6dCmNjY+jo6KBfv36IiYmRZVoVikBVBdq2tcQ7s4VCpF5/CG0p75PC44b4+yr12gOpxxlJtGxrQUlNVWw7WaGvkP0yFjqf+f58n5KqMowbWSHqunhti7rhD1N7ybXK1L52sc7vV56PpMZLYtzICspqKmL7TQmNQtrLeJjaW5cuiQ8QqKpAs2FtpN0QP/an3fSFlpTHUqtJ3WKdi6//ewCtpnVl1i5ZUVZVQQ3bWvB/79jvf+MRakvJr3ZTG7F4AHj8zrHftJo5DMwM4ffOY5b5OgPPfINF21RRV0Vebp7Y2Xs5b6YPqyPD+qaqqoKGjevhxrWiadyEQiFuXruDps0bSVynSfNGuPlOPAD8d+WWKL5a9SowszDFjWt3Rfe/fp0GX+/HopikxGSEBoeh76Be0NTShLKyMoaO6o/42AQ89g2QWX6i1+e7r7e3r88mkl9vmk3rIv2912fadR9oSoknIiIioq9The0k1zfSh7KKMhLjksSWJ8UnwcjMUOI6RqaGSIx/Lz4uGUamkk8vVTQtQ10oqSgj4735UtPjU6BtKuW0dFMDZLw392h6fCq0TQ1Kte9Oy4cj0jsYIZekj6j/XJpGkvPL+EB+WqYGyIgTzy8jrvT5tVsxHFH3g/FMjvkZGOlDRUUFiXGJYssT45JgLOXUYmNTIwnxiTA2+/peoypGuhCoKCP3vecvNy4ZqlKeD1VTA+TGJYvHxydD1VTye1YS9ermAIAqcwYj7vAlPB32AzL8QlHn2PdQt6pUqhw+RM9QF8oqykiJF29vSnwKDKS018DUoFTxJaFrqItvpw/E5aP/fPI2ZEEoh/9K49ixY3B1dcWKFSvg4+ODxo0bw8nJCbGxsRLjb926hSFDhmDcuHF48OABXFxc4OLiAj+/oo7I9PR0tGnTBj///LPU/c6ePRvnz5/HiRMncO3aNURGRqJv375S4+nDRMeN944DefEpUJVSu1VNDZD33vsqNy6lVMcNVTNDFGTnIv+964fkxSdDRcp+P5X6m9qW+d6xMTMuBZpSapumqQEy36ttmfGp0CxFbdM01Ud+di5yUsWvXfCh/X4KZUM9CFSUkffe56m8+GSoSHlOVCQ8h4XxBjJrl6zoSjn2p8Ynw0BKe6Ud+/XfxBuYGYiWicckQ//NYxZw8zH0TQ3QY1IfKKuqQEtPG4MWjnizvuxeo4bGhlBRUUF8bILY8vjYBJiamUhcx9TMBPFx78XHFcW//fdDMQAwvO9E1G9UF37Pb+FJpBfGTRmBUQOnIDXl9Wfn9VbR6zNZbPkHX58mhhLjpX2WKUsUXbuJiIiIvqSvupP8xYsXGDt27AdjsrOzkZqaKnYrEFbs0ZKKVrtzU1R3rI/L38t3PmtFserSFNUc6+O/cppfeSdQEgAAYn//G/HHryDDPwwvVu5HVugrmA6SPF1DWaWpo4n5+5fhVcgLnFrvodC2CIUFMr+Vxrp16zBhwgSMGTMG9evXx44dO6ClpYV9+/ZJjN+4cSO6deuGefPmoV69eli1ahWaNm2KLVu2iGJGjBiB5cuXo3PnzhK3kZKSgr1792LdunXo1KkT7O3tsX//fty6dQt37tyRuE558Km1O0eY/4VaSFT+vAp+gV1zNqP7+N7Y++Qottzfh7gXMUiOTUJBQfnomPxh7WIkxCVioPMYuHQZhn/+vIo9RzbB1Fxy5zx9PkXXbiIiIqIv6avuJE9MTMTBg9IvwAQAbm5u0NfXF7tFvA7/6LZTElOQn5cPo/dGhRiaGCIxNkniOolxSTAyeS/e1KDYyN2vRUbSaxTk5UPLRHwEmLaJvtQpUNLjkqFlovdevB7S3xu19yGWjvVhUN0MMx/vwtzQg5gbWvgcuuyYicEeS0qXxAdkJkrOT+sD+WXEJUPLVDw/LdPS5VfNsT70q5vhO79dmP7sIKY/K8zPeedM9Dsmu/ySE1OQl5dX7EwFI1NDJLw3guuthLhECfFGSIj9+l6jeYmvIczLh+p7z5+k0eJvSRplrmpigNw4ye9ZSXJiCmOznr4UW54V8hJqVWT3RTs16TXy8/Khb2IgtlzfRB/JUtqbHJdcqvgP0dDWwMJDK5CZnol1E9cgP6/8dUBK6mjNzs4uFpeTkwNvb2+xzmwlJSV07twZt2/flrjt27dvF+v8dnJykhovibe3N3Jzc8W2U7duXVhaWpZqO2XNp9buA6+DP7pt0XHjveOAiok+cqXU7ty4ZKi8975SNdUv1XEjNzYJSuqqUNbTfm+/BsiTst9Plf2mtmm+d2zUNNVHppTalhmXDM33apumiR4yS1HbMuNSoKyuCjU9rRLv91PkJ6VCmJcPlfc+T6mYGCBPynOSJ+E5LIxPllm7ZOW1lGO/nokBkqW0V9qxP+VNfHJssmiZeIwBUt55zG7/7zqmNx+HGQ7jMdluFM6sPwY9Yz3ERUR/TkpikhKSkJeXV+ximSZmxoiLjZe4TlxsPExM34s3LYp/+++HYhzbtUCnru0wY8ICeHv5wv/REyyftxpZmVnoN7i3THID3n19Gogt/+DrMz5JYry0zzJERERE9HVSaCf5uXPnPni7evXqR7exaNEipKSkiN0sdWt8dL283DwEPX6Kpm2aipYJBALYt2mCAB/Jcxv6ewegaZsmYsuatbVHgLfs5kKUpYLcfEQ/DkP11u/MXy0QoHrrBoj0CZG4TqRPiHg8gBptG0qNl+Tu9vPY77QYB7ovEd0A4MoPv+OvebtKn4gUBbn5iH0chmrv5VetdQNES2lvlE+IeDyAam0aSo2X5P628zjcdTGOdFsiugHAfz/8jktzZZdfXm4enjx6ihZt7EXLBAIBmrexxyMpF9R8dN8Pzd+JBwCHds3w2PvDFyFVBGFuHtIfhUKvzTtzmAoE0GtjizRvyRetSvcOEo8HoN+uMdK8n5Z4vzkvYpETlQCNWpXFlqvXrIzsV3ElT+Aj8nPzEPY4FA1bF7VXIBCgQetGCPaRnF+wTxAatBbPz7atndR4aTR1NLHo95XIy8nDr+N+Qm52bukTkLECCGV+k9TR6ubmVmzf8fHxyM/Ph7m5udhyc3NzREdL7jyKjo4uVby0baipqcHAwOCztvO1kVftHq378Xmvhbl5SH8cCt1ix41GSJfyPpF03NBrayf1OCNJxuNQFOTkiu1XvWZlqFc1Q1op358fU5Cbj4RHYajURry2VWrTAHHekmtVnHeIeDyAyu0aSo2XJOFRGPJz8sS2o1erEnSqmiDO++M/YJSUMDcPmX4h0G4t/hzqODZGhpTHMuPBE+i0biy2TKeNHTJ85HsBzk+Rn5uH8MehqC/h2B8iJb8Qn6do0NpWbFnDto1Fx/63I8LfrQ8aOpqoaWctcZup8SnIzsiCQ6/WyM3OFZvL/HPl5ubB72EgWrdzEC0TCARwbOcAn3uSL3z74N4jsXgAaNOhpSj+xfNXiI2OE4vR0dWGnb2tKEZTUxMAUFAgPhJZKBRC6c0ZYrLw9vWp4/jO6+3t61PKBV8zfZ5A29FObJlO6ybIlPMFYr8EedRuIiIioq+ViiJ37uLiAoFAIHaRofcJBB/+4Kuurg51dXWxZUqCkvX9n9h1CovWz0fQwyAE+gah//i+0NDUwF/HLgIAFm1YgPjoeOxesxcAcGrvaWw8uQ4DJ/bHnct30alPR9RpZAP3BetF29Q10IV5ZTMYWxSOhqlWqxqAwnmh385/bmRqCCNTI1SpUdhJZ1XXCplpmYiJjMXrZNnNqwgA9/f8hR7ukxD9KAxRD0PRbGw3qGqp4/GJawCAHusmIS06Cf+tPV4Yv/9vDDm2BM0ndEfoFV/U69UKFrY18ffCoikJNPS1oVfFGDrmhaPAjGoWzuOcHpcidntfamQCUl7IrhMSAHz2/IWu7pMQ+zgM0b6haDKuML+A44X5dV1fmN+tnwvz8933N/odX4ImE7oj/IovbHq3gnmjmrjyTn7q+trQfSc/w1qF+WXEpYjd3vf6VQJSZZzf4Z3HsHLjYgQ8fAJ/30AMnTAAmlqaOO9ReAHB7zctQWx0PLau3gkA8NhzErtOb8awSYNw4/JtOPX5BvUb18Xqeb+ItqlnoAuLKuai05Or17IEACTEJiLhzVkRxqZGMDYzQlWrqgCA2vVqIiMtA9GvYpAqw9dozO5zsFo/A+mPQpH+IBjmE3pCSVMD8ccuAwCsNs5AblQiXq75vTB+7wXUOfkjzCf1Rsq/3jDq0wZajWohfP520TaVDXSgVsUEauaFI+o1a1UBAOTGJotGHUbvOIvKcwYjIyAcGf5hMBnQEZq1qiB04i+QpT/2/A+T3WcGOacBAAAj6klEQVTi2aMQhDwMRvexvaCupYFrJwrzm7xuJpKiE+CxtjC/v/afx/JjP8F5Qh88uHIfrXq1RU3bWti9cJtom9r6OjCpYgrDN/lVqll4HEmOS0JKXHJhB/lvK6GuqQ73mWugqasFTd3CkaGpCakQFpSfU50XLVoEV1dXsWXv1wOSPXnVbjWBcon2H7Prf7BaPxMZD0OQ7hsM8/G9xI4bNTbMRG50Al6JjhvnUefkTzCf2Acpl+/DqE/bwuPGgqL3lbKBDtQqm0LNovB99fZHtNy4JOTFJSP/dQbiPf5FteVjkJ/8GvmvM2G5agLS7j9Buk/Jf6QrKf/df6Ht+kmIfxSG+AehqD+hG1Q01RF8rLC2tdk4CRlRSfBZU1jbAvb+je4nl6DBpO54+a8vrPq0gnGjmrg1v6i2qRloQ6eKMTTf1Da9N7UtMzYFmXEpyH2diWAPTzRfMQzZyWnIfZ0Jhx9HIvb+U8T5hMo0v/g9Z1HVfTYyH4Ug8+FTGI/tAyUtDSSd/BcAUNV9NnKjExDzyyEAQML+c6jp4QaT8S54feU+9Hu1haZtbbxaXDT9kbK+DlQrm0L1zbFRvWbhsT8vLkk0X7SKiQFUTA2h9ubzl0bd6ihIy0RuZBzyU9Jklt9fe85jovt0hD0KwbOHwXAa2wvqWur478QVAMCkdTOQFJ2A42sPAwD+2X8Bi4+tQvcJveF7xRste7WBlW0t7Fu4Q7TNi3svoM/0/ogOi0Lcixj0nzMEybGJ8P6n6ALEnUd1R7B3ELLTM9GwbWMMXjwKx9f8hoz35pn/XHu2/Qb3ravwyNcfD338MHbScGhpaeLkkbMAAPdtPyI6Kha/rNoEANi/8zA8zu/F+CkjceXSf+j1bTfY2jXA4tmrRNvct/Mwps2ZgPBnz/Hi+Su4Lp6KmOg4/PNn4WPmc+8hUpJT8evWH7H5l53IysrG4BF9UdWyCq7+c12m+cXvPYuqv85G5uPgwtfnGPHXZ5VfXZEXk4CYXwrPmIk/cA41j66B8bhv8frqPRj0agcN29p4taT461PFvPD7gVrNws9XEl+f1Qvfmxp1a6AgLUPmr08iIiIikkyhneSVKlXCtm3b0KdPH4n3+/r6wt7eXuJ9snD1vCcMjPUxZu5oGJkaIiQgFPNHLELSmw+r5lXMxDqU/L0DsGraaoybPwbjF4zFq7BXWDp+BcKCwkUxrbu0wsL180V/r9i+FABwYN0hHFhX+GWv94heGO06UhSz+fQGAMCa2Wtx8YRsL6735MJdaBrroY1rP2ib6iM24DlOjFwrujinXmUTCN+ZqzLSOxgXZmxD27kD0HbeQCSFR+PMxPWIf2dqitpdmqKH+yTR3723TgcA3Fx/Gjc3nJZp+z8m+PxdaBrpoaVrP2iZ6iM+4DnOjijKT/e9/KK8g3FxxjY4zh0Ax/kDkRwejQsT1iPhnfxqdmmKruuK8uvxJr8760/j7vovm9+lc1dgaGyA7+aPg7GpEZ76h2D60LmiC8haVDEXm2v00X0/LJnyPaYsmICpiybiRdhLzB2zGKFBYaKYdl3bYOXGxaK/3XZ+DwDY9es+7HLfDwDoN7IPJs4tmlN4z9mtAICVM1fjwvG/ZJZf4rmbUDHSQ5W5g6FqaogM/zA8Hf4D8t5cnEytsinwTn5p94PwbNp6VJk/FFUXDEdWWBRCxq1BZlCEKMaga3PUXD9D9Het7XMBAK/cPRC57hgAIGbPBQjU1WC5ciyUDXSQGRCOoCHfI/u5bEf33rlwE3rG+ujvOgQGpoZ4HhCGNSO/F118zaSyqdjrM9g7CFtmrMPAucMwaN5wRIdHwn3iGrx8WpSffZcWmOxelN/MrfMAACfXe+DUBg/UaFgL1k3rAAA2Xi/qYAGA6a0nIv6l5AtVytuHOlQ/laSOVklMTEygrKyMmJgYseUxMTGwsLCQuI6FhUWp4qVtIycnB8nJyWKjyUu7na+Nomt30vmbUDHWR+W5QwqPGwFhCB7xvei4oV5F/LiR7h2EsGnrUGX+MFRZMBzZYZEIHb8GWe8eN7q0gJXYcaPwfRW5zgOR6wrn83/x/T6gQIhauxZAoKaK1GsP8HzxTrnkGH7uLjSM9NBkbj9omuoj0f85Lg1fi6w3tU2nsolYjnH3g3Ft2jY0nT8ATRcMRGpYNK6MW4/koKLaZtm1KdqsL6ptHbYX1jZf99PwXVdY2+6tPAxhgRAdd82EkroKIj0f487iAzLPL+WPG1Ax1oe56zComBgiK/AZwkavEHUWqr537M/weYKIWb/CYs5wmM8diZzwSERM+gnZ7xwbdTs7oNqvs4ry3bIAABCz4QhiNx4FABgN6w7zWUNFMbWOF15098XcDUg+dVlm+d29cBO6xnro5zoE+qYGiAgIwy8jVyH1zWvUuLKJ2OfLYO8gbJ+xHv3nDsWAecMQEx6FDRN/Fjv2/7HjDNS11DHW7Tto6Wnj6f1A/DJyldiZQrUaW6Pv7MHQ0NJAVOgr7F+0AzfPXJNZXqK2nP0bxiaGcF04BSZmJgj0C8LogVMQ/+aH9spVLMRGfPvce4hZExdhzpJpmLt0OsKfRWDSiFl4+qToTIedm/ZDS0sTq9cth56+Lu7dfYDRA6cgJzsHAJCUmIzRA6dg7pLpOHx2N1RUVRD8JBQTh89EoL9sf6hK/eM6oo30YTZ7uOj1GT56OfLfvD4LP5sU5Zfp8wQvZv0C8zkjil6f3/2E7KfPRTG6nR1Q9ZfZor8tNxe+PmM3HkHsxiMAAKNhPWA2s+j1WfNY4evz5bz1Mn19loY8ajcRERHR10ogVOCnn969e8POzg4//PCDxPsfPnyIJk2aFDu18mM6VJV8EbXyoody2e1cKSn1cv6Z/Lfc5x8PKsO2K5Xvi2itUynfL9Cjz8/KfJtVjRrKfJsvE0s+jZCDgwNatGiBzZs3Ayg8Zd/S0hLTpk3DwoULi8UPGjQIGRkZOH/+vGiZo6MjGjVqhB07xH98CA8Ph5WVFR48eAA7OzvR8pSUFJiamuLo0aPo168fACAoKAh169bF7du30bJly9Kk+9WQV+2+X9VFBq37evkJdRTdBLmzV5Pd3OVfo7UFqopuglzdSJPtGQNfm/P61RTdBLlq+OyCzLep6NpNRERE9CUpdCT5vHnzkJ6eLvX+2rVrl2huUyIiog9xdXXFqFGj0KxZM7Ro0QIbNmxAeno6xowZAwAYOXIkqlSpIprTfObMmWjfvj3c3d3h7OwMDw8P3L9/H7t2FV13IDExEREREYiMjARQ2AEOFI4gt7CwgL6+PsaNGwdXV1cYGRlBT08P06dPR6tWrcpsBznA2k1ERERERETlj0I7ydu2bfvB+7W1tdG+ffsv1BoiIpIXRZ+yPWjQIMTFxWH58uWIjo6GnZ0dLl68KLo4Z0REBJSUiq5n4ejoiCNHjmDp0qVYvHgxrK2tcfbsWTRsWDSq7ty5c6JOdgAYPHgwAGDFihVYuXIlAGD9+vVQUlJCv379kJ2dDScnJ2zbVjQXdlnE2k1EVDEounYTERERfUkKnW5FXjjdStnH6VbKNk63UrbJY7qVSgb1Zb7NqOQAmW+TFIfTrZR9nG6lbON0K2WbPKZbYe0mIiKiikTp4yFEREREREREREREROWTQqdbISKiikGI8j36noiIqLxh7SYiIqKKhCPJiYiIiIiIiIiIiKjCYic5ERHJnVAolPmNiIiI5OdrqN1bt25FjRo1oKGhAQcHB3h5eX0w/sSJE6hbty40NDRga2uLP//8s1hOy5cvR6VKlaCpqYnOnTsjODhYLObp06fo06cPTExMoKenhzZt2uDq1aulbjsRERGVLewkJyIiuSuAUOY3IiIikh9F1+5jx47B1dUVK1asgI+PDxo3bgwnJyfExsZKjL916xaGDBmCcePG4cGDB3BxcYGLiwv8/PxEMWvXrsWmTZuwY8cO3L17F9ra2nByckJWVpYopmfPnsjLy8OVK1fg7e2Nxo0bo2fPnoiOjv60B5KIiIjKBHaSExERERER0Vdl3bp1mDBhAsaMGYP69etjx44d0NLSwr59+yTGb9y4Ed26dcO8efNQr149rFq1Ck2bNsWWLVsAFI4i37BhA5YuXYo+ffqgUaNGOHToECIjI3H27FkAQHx8PIKDg7Fw4UI0atQI1tbWWLNmDTIyMsQ624mIiKj8YSc5ERHJ3ddwyjYRERGVnDxqd3Z2NlJTU8Vu2dnZxfadk5MDb29vdO7cWbRMSUkJnTt3xu3btyW29/bt22LxAODk5CSKDwsLQ3R0tFiMvr4+HBwcRDHGxsaoU6cODh06hPT0dOTl5WHnzp0wMzODvb39Zz+mRERE9PViJzkREcldgVAo8xsRERHJjzxqt5ubG/T19cVubm5uxfYdHx+P/Px8mJubiy03NzeXOu1JdHT0B+Pf/vuhGIFAgH///RcPHjyArq4uNDQ0sG7dOly8eBGGhoaf9kASERFRmaCi6AYQERERERFR+bdo0SK4urqKLVNXV1dQa4oTCoWYOnUqzMzMcP36dWhqamLPnj3o1asX7t27h0qVKim6iURERCQn7CQnIiK54/QoREREZYs8are6unqJOsVNTEygrKyMmJgYseUxMTGwsLCQuI6FhcUH49/+GxMTI9bZHRMTAzs7OwDAlStXcOHCBSQlJUFPTw8AsG3bNly6dAkHDx7EwoULS5YoERERlTmcboWIiIiIiIi+GmpqarC3t8fly5dFywoKCnD58mW0atVK4jqtWrUSiweAS5cuieKtrKxgYWEhFpOamoq7d++KYjIyMgAUzn/+LiUlJRQUFHx+YkRERPTV4khyIiKSuwJwJDkREVFZouja7erqilGjRqFZs2Zo0aIFNmzYgPT0dIwZMwYAMHLkSFSpUkU0p/nMmTPRvn17uLu7w9nZGR4eHrh//z527doFoHC+8VmzZuHHH3+EtbU1rKyssGzZMlSuXBkuLi4ACjvaDQ0NMWrUKCxfvhyamprYvXs3wsLC4OzsrJDHgYiIiL4MdpITEZHccboVIiKiskXRtXvQoEGIi4vD8uXLER0dDTs7O1y8eFF04c2IiAixEd+Ojo44cuQIli5disWLF8Pa2hpnz55Fw4YNRTHz589Heno6Jk6ciOTkZLRp0wYXL16EhoYGgMJpXi5evIglS5agU6dOyM3NRYMGDfC///0PjRs3/rIPABEREX1RAqGiP/3IQYeqnRXdBLnqoSx5Hr7yRL3cvSrF/Zb7XNFNkKvtSiaKboJcrVMp3y/Qo8/Pynybeto1Zb7N1PRnMt8mKc79qi6KboJc+Ql1FN0EubNXS1F0E+RqbYGqopsgVzfSQhXdBLk6r19N0U2Qq4bPLsh8m6zdREREVJFwJDkREcldQfn7PZaIiKhcY+0mIiKiioSd5EREJHdCzklORERUprB2ExERUUWi9PEQIiIiIiIiIiIiIqLyiSPJiYhI7njKNhERUdnC2k1EREQVCUeSExEREREREREREVGFxZHkREQkd0KORiMiIipTWLuJiIioImEnORERyR0v/kVERFS2sHYTERFRRcLpVoiIiIiIiIiIiIiowuJIciIikjuesk1ERFS2sHYTERFRRcKR5ERERERERERERERUYXEkORERyR1HoxEREZUtrN1ERERUkbCTnIiI5I5fs4mIiMoW1m4iIiKqSDjdChERERERERERERFVWAIhz6P7LNnZ2XBzc8OiRYugrq6u6ObIRXnPkfmVbcyPiEqrIryvynuOzK9sY35ERERE9LVhJ/lnSk1Nhb6+PlJSUqCnp6fo5shFec+R+ZVtzI+ISqsivK/Ke47Mr2xjfkRERET0teF0K0RERERERERERERUYbGTnIiIiIiIiIiIiIgqLHaSExEREREREREREVGFxU7yz6Suro4VK1aU64vylPccmV/ZxvyIqLQqwvuqvOfI/Mo25kdEREREXxteuJOIiIiIiIiIiIiIKiyOJCciIiIiIiIiIiKiCoud5ERERERERERERERUYbGTnIiIiIiIiIiIiIgqLHaSy8iaNWsgEAgwa9YsRTdFJvLz87Fs2TJYWVlBU1MTtWrVwqpVq1BWp7D/77//0KtXL1SuXBkCgQBnz54V3Zebm4sFCxbA1tYW2traqFy5MkaOHInIyEjFNfgTfCjHtwIDA9G7d2/o6+tDW1sbzZs3R0RExJdvbCm5ubmhefPm0NXVhZmZGVxcXBAUFCQWk5WVhalTp8LY2Bg6Ojro168fYmJiFNTi0ilJfm8JhUJ0795d6nNMRCXH2v11Y+0uxNr9dWLtJiIiIipf2EkuA/fu3cPOnTvRqFEjRTdFZn7++Wds374dW7ZsQWBgIH7++WesXbsWmzdvVnTTPkl6ejoaN26MrVu3FrsvIyMDPj4+WLZsGXx8fHD69GkEBQWhd+/eCmjpp/tQjgAQGhqKNm3aoG7duvD09MSjR4+wbNkyaGhofOGWlt61a9cwdepU3LlzB5cuXUJubi66du2K9PR0Uczs2bNx/vx5nDhxAteuXUNkZCT69u2rwFaXXEnye2vDhg0QCAQKaCVR+cLa/fVj7Wbt/pqxdhMRERGVM0L6LK9fvxZaW1sLL126JGzfvr1w5syZim6STDg7OwvHjh0rtqxv377CYcOGKahFsgNAeObMmQ/GeHl5CQEInz9//mUaJWOSchw0aJBw+PDhimmQjMXGxgoBCK9duyYUCoXC5ORkoaqqqvDEiROimMDAQCEA4e3btxXVzE/2fn5vPXjwQFilShVhVFRUiV7HRCQZa3fZw9pd9rF2s3YTERERfc04kvwzTZ06Fc7OzujcubOimyJTjo6OuHz5Mp4+fQoAePjwIW7cuIHu3bsruGVfRkpKCgQCAQwMDBTdFJkoKCjAH3/8ARsbGzg5OcHMzAwODg5l9pTflJQUAICRkREAwNvbG7m5uWLvw7p168LS0hK3b99WSBs/x/v5AYWjJocOHYqtW7fCwsJCUU0jKhdYu8sn1u6vG2s3azcRERHR10xF0Q0oyzw8PODj44N79+4puikyt3DhQqSmpqJu3bpQVlZGfn4+fvrpJwwbNkzRTZO7rKwsLFiwAEOGDIGenp6imyMTsbGxSEtLw5o1a/Djjz/i559/xsWLF9G3b19cvXoV7du3V3QTS6ygoACzZs1C69at0bBhQwBAdHQ01NTUinWMmJubIzo6WgGt/HSS8gMKT0l3dHREnz59FNg6orKPtbt8Yu3+urF2s3YTERERfe3YSf6JXrx4gZkzZ+LSpUtlYl7I0jp+/DgOHz6MI0eOoEGDBvD19cWsWbNQuXJljBo1StHNk5vc3FwMHDgQQqEQ27dvV3RzZKagoAAA0KdPH8yePRsAYGdnh1u3bmHHjh1l6ov21KlT4efnhxs3bii6KXIhKb9z587hypUrePDggQJbRlT2sXaXT6zdXz/WbiIiIiL62nG6lU/k7e2N2NhYNG3aFCoqKlBRUcG1a9ewadMmqKioID8/X9FN/Czz5s3DwoULMXjwYNja2mLEiBGYPXs23NzcFN00uXn7Jfv58+e4dOlSuRmJBgAmJiZQUVFB/fr1xZbXq1cPERERCmpV6U2bNg0XLlzA1atXUbVqVdFyCwsL5OTkIDk5WSw+JiamTJ3eLC2/K1euIDQ0FAYGBqLjDQD069cPHTp0UFBricoe1u7yh7X768fazdpNREREVBZwJPkn+uabb/D48WOxZWPGjEHdunWxYMECKCsrK6hlspGRkQElJfHfUJSVlUWjmsqbt1+yg4ODcfXqVRgbGyu6STKlpqaG5s2bIygoSGz506dPUb16dQW1quSEQiGmT5+OM2fOwNPTE1ZWVmL329vbQ1VVFZcvX0a/fv0AAEFBQYiIiECrVq0U0eRS+Vh+CxcuxPjx48WW2draYv369ejVq9eXbCpRmcbaXb6wdn/dWLtZu4mIiIjKEnaSfyJdXV2xOQcBQFtbG8bGxsWWl0W9evXCTz/9BEtLSzRo0AAPHjzAunXrMHbsWEU37ZOkpaUhJCRE9HdYWBh8fX1hZGSESpUqoX///vDx8cGFCxeQn58vmgvTyMgIampqimp2qXwoR0tLS8ybNw+DBg1Cu3bt0LFjR1y8eBHnz5+Hp6en4hpdQlOnTsWRI0fwv//9D7q6uqLnR19fH5qamtDX18e4cePg6uoKIyMj6OnpYfr06WjVqhVatmyp4NZ/3Mfys7CwkDiqztLSstiXciKSjrW7bGHtZu3+mrF2ExEREZUzQpKZ9u3bC2fOnKnoZshEamqqcObMmUJLS0uhhoaGsGbNmsIlS5YIs7OzFd20T3L16lUhgGK3UaNGCcPCwiTeB0B49epVRTe9xD6U41t79+4V1q5dW6ihoSFs3Lix8OzZs4prcClIe372798visnMzBROmTJFaGhoKNTS0hJ+++23wqioKMU1uhRKkp+kdc6cOfPF2khUXrF2f71Yuwuxdn+dWLuJiIiIyheBUCgUyqrDnYiIiIiIiIiIiIioLOGFO4mIiIiIiIiIiIiowmInORERERERERERERFVWOwkJyIiIiIiIiIiIqIKi53kRERERERERERERFRhsZOciIiIiIiIiIiIiCosdpITERERERERERERUYXFTnIiIiIiIiIiIiIiqrDYSU5EREREREREREREFRY7yanCEQgEOHv2LAAgPDwcAoEAvr6+JV6/Q4cOmDVrllzaVlI1atTAhg0bFNqGd61cuRJ2dnaKbgYREZVTrN2yx9pNRERERFSEneSkMKNHj4ZAIIBAIICamhpq166NH374AXl5eYpuWqmFhIRg7NixsLS0hLq6OqpUqYJvvvkGhw8fLpbP1atX0aNHDxgbG0NLSwv169fHnDlz8OrVK7HHRNKtRo0aikmQiIgIrN2s3URERERE5RM7yUmhunXrhqioKAQHB2POnDlYuXIlfvnll1JvJz8/HwUFBXJo4cd5eXmhadOmCAwMxNatW+Hn5wdPT0+MHz8e27dvh7+/vyh2586d6Ny5MywsLHDq1CkEBARgx44dSElJgbu7OzZu3IioqCjRDQD2798v+vvevXuf3M7c3NzPzpWIiIi1m7WbiIiIiKi8YSc5KZS6ujosLCxQvXp1TJ48GZ07d8a5c+ewbt062NraQltbG9WqVcOUKVOQlpYmWu/AgQMwMDDAuXPnUL9+fairqyMiIgL37t1Dly5dYGJiAn19fbRv3x4+Pj6lapOfnx+6d+8OHR0dmJubY8SIEYiPj5cYKxQKMXr0aNjY2ODmzZvo1asXrK2tYW1tjSFDhuDGjRto1KgRAODly5eYMWMGZsyYgX379qFDhw6oUaMG2rVrhz179mD58uXQ19eHhYWF6AYABgYGor9NTU1F+87IyMDYsWOhq6sLS0tL7Nq1S3Tf21PRjx07hvbt20NDQwOHDx8GAOzZswf16tWDhoYG6tati23btonltGDBAtjY2EBLSws1a9bEsmXLin1JX7NmDczNzaGrq4tx48YhKytL7H5PT0+0aNEC2traMDAwQOvWrfH8+fNSPQ9ERPR1Yu1m7SYiIiIiKm/YSU5fFU1NTeTk5EBJSQmbNm2Cv78/Dh48iCtXrmD+/PlisRkZGfj555+xZ88e+Pv7w8zMDK9fv8aoUaNw48YN3LlzB9bW1ujRowdev35dov0nJyejU6dOaNKkCe7fv4+LFy8iJiYGAwcOlBjv6+uLwMBAzJ07F0pKkt9OAoEAAHDixAnk5OQUy+MtAwODErXxLXd3dzRr1gwPHjzAlClTMHnyZAQFBYnFLFy4EDNnzkRgYCCcnJxw+PBhLF++HD/99BMCAwOxevVqLFu2DAcPHhSto6uriwMHDiAgIAAbN27E7t27sX79etH9x48fx8qVK7F69Wrcv38flSpVEvuynpeXBxcXF7Rv3x6PHj3C7du3MXHiRNHjQERE5Qtrd8mxdhMRERERfaWERAoyatQoYZ8+fYRCoVBYUFAgvHTpklBdXV04d+7cYrEnTpwQGhsbi/7ev3+/EIDQ19f3g/vIz88X6urqCs+fPy9aBkB45swZoVAoFIaFhQkBCB88eCAUCoXCVatWCbt27Sq2jRcvXggBCIOCgoRCoVDYvn174cyZM4VCoVDo4eEhBCD08fERxcfExAi1tbVFt61btwqFQqFw8uTJQj09vY8/MO94t63vql69unD48OGivwsKCoRmZmbC7du3i+W1YcMGsfVq1aolPHLkiNiyVatWCVu1aiW1Db/88ovQ3t5e9HerVq2EU6ZMEYtxcHAQNm7cWCgUCoUJCQlCAEJPT88S5UhERGUHa/fHsXYTEREREZU9Kl++W56oyIULF6Cjo4Pc3FwUFBRg6NChWLlyJf7991+4ubnhyZMnSE1NRV5eHrKyspCRkQEtLS0AgJqamuh06LdiYmKwdOlSeHp6IjY2Fvn5+cjIyEBERESJ2vPw4UNcvXoVOjo6xe4LDQ2FjY3NR7dhbGwMX19fAECHDh2Qk5MDoPD0blmOyHo3d4FAAAsLC8TGxorFNGvWTPT/6enpCA0Nxbhx4zBhwgTR8ry8POjr64v+PnbsGDZt2oTQ0FCkpaUhLy8Penp6ovsDAwPx3Xffie2nVatWuHr1KgDAyMgIo0ePhpOTE7p06YLOnTtj4MCBqFSpkmwSJyIihWLt/nSs3UREREREXydOt0IK1bFjR/j6+iI4OBiZmZk4ePAg4uLi0LNnTzRq1AinTp2Ct7c3tm7dCgCiL61A4end739xHTVqFHx9fbFx40bcunULvr6+MDY2FlvvQ9LS0tCrVy/4+vqK3YKDg9GuXbti8dbW1gAgdqq0srIyateujdq1a0NFpeh3KBsbG6SkpIgu6vW5VFVVxf4WCATFLoCmra0tlhsA7N69Wyw3Pz8/3LlzBwBw+/ZtDBs2DD169MCFCxfw4MEDLFmypMSP31v79+/H7du34ejoiGPHjsHGxka0DyIiKttYuz8dazcRERER0deJneSkUNra2qhduzYsLS1FX0q9vb1RUFAAd3d3tGzZEjY2NoiMjCzR9m7evIkZM2agR48eaNCgAdTV1aVeuEuSpk2bwt/fHzVq1BB9WX57e/dL61tNmjRB3bp18euvvxb7kvu+/v37Q01NDWvXrpV4f3Jyconb+SnMzc1RuXJlPHv2rFhuVlZWAIBbt26hevXqWLJkCZo1awZra+tiF+2qV68e7t69K7ZM0pfoJk2aYNGiRbh16xYaNmyII0eOyC85IiL6Yli7i7B2ExERERGVD5xuhb46tWvXRm5uLjZv3oxevXrh5s2b2LFjR4nWtba2xm+//YZmzZohNTUV8+bNg6amZon3PXXqVOzevRtDhgzB/PnzYWRkhJCQEHh4eGDPnj1QVlYWixcIBNi/fz+6dOmC1q1bY9GiRahXrx5yc3Px33//IS4uTrROtWrVsH79ekybNg2pqakYOXIkatSogZcvX+LQoUPQ0dGBu7t7yR+oT/D9999jxowZ0NfXR7du3ZCdnY379+8jKSkJrq6usLa2RkREBDw8PNC8eXP88ccfOHPmjNg2Zs6cidGjR6NZs2Zo3bo1Dh8+DH9/f9SsWRMAEBYWhl27dqF3796oXLkygoKCEBwcjJEjR8o1NyIiUhzWbvlh7SYiIiIikj+OJKevTuPGjbFu3Tr8/PPPaNiwIQ4fPgw3N7cSrbt3714kJSWhadOmGDFiBGbMmAEzM7MS77ty5cq4efMm8vPz0bVrV9ja2mLWrFkwMDCAkpLkt0vLli3h7e2NOnXqYOrUqahfvz4cHR1x9OhRrF+/HpMnTxbFTpkyBf/88w9evXqFb7/9FnXr1sX48eOhp6eHuXPnlridn2r8+PHYs2cP9u/fD1tbW7Rv3x4HDhwQjUbr3bs3Zs+ejWnTpsHOzg63bt3CsmXLxLYxaNAgLFu2DPPnz4e9vT2eP38ulqOWlhaePHmCfv36wcbGBhMnTsTUqVMxadIkuedHRESKwdotP6zdRERERETyJxAKhUJFN4KIiIiIiIiIiIiISBE4kpyIiIiIiIiIiIiIKix2khMRERERERERERFRhcVOciIiIiIiIiIiIiKqsNhJTkREREREREREREQVFjvJiYiIiIiIiIiIiKjCYic5EREREREREREREVVY7CQnIiIiIiIiIiIiogqLneREREREREREREREVGGxk5yIiIiIiIiIiIiIKix2khMRERERERERERFRhcVOciIiIiIiIiIiIiKqsNhJTkREREREREREREQV1v8Bjn7tJOgaaF4AAAAASUVORK5CYII=",
+      "text/plain": [
+       "<Figure size 1500x1000 with 10 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import re\n",
+    "\n",
+    "fig, axs = plt.subplots(2, 3, figsize=(15, 10))\n",
+    "axs = axs.ravel()\n",
+    "\n",
+    "flags = [\"MaxTenuringThreshold\", \"ParallelGCThreads\"]\n",
+    "goal=\"Average GC Pause\"\n",
+    "i=0\n",
+    "files = sorted(glob.glob(\"datasets/kafka/norm_ext*\"), \n",
+    "               key=lambda x:float(re.findall(\"(\\d+)\",x)[0]))\n",
+    "\n",
+    "for csv_file in files:\n",
+    "    df = pd.read_csv(csv_file)\n",
+    "    x = df.iloc[:, 0].values\n",
+    "    y = df.iloc[:, 1].values\n",
+    "    z = df.iloc[:, 2].values\n",
+    "    \n",
+    "    data = pd.DataFrame({\n",
+    "        flags[0]: x, \n",
+    "        flags[1]: y, \n",
+    "        goal: z})\n",
+    "    \n",
+    "    data_pivoted = data.pivot(index=flags[0], columns=flags[1], values=goal)\n",
+    "    sns.heatmap(data_pivoted, annot=True,  ax=axs[i], fmt=\".3f\") # ax=axs[i],\n",
+    "    axs[i].invert_yaxis()\n",
+    "    axs[i].set_title(os.path.basename(csv_file))\n",
+    "    i += 1\n",
+    "\n",
+    "fig.delaxes(axs[-1])\n",
+    "plt.tight_layout()\n",
+    "plt.show()\n",
+    "    "
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -337,12 +502,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# External Info"
+    "# Create a dataset with extra parameters"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -361,7 +526,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -401,67 +566,67 @@
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>10</td>\n",
-       "      <td>20</td>\n",
-       "      <td>0.01203</td>\n",
-       "      <td>-439501.0</td>\n",
-       "      <td>-2197504.0</td>\n",
-       "      <td>5.6</td>\n",
-       "      <td>1832.0</td>\n",
-       "      <td>1828.775</td>\n",
-       "      <td>16.9</td>\n",
+       "      <td>16</td>\n",
+       "      <td>0.00945</td>\n",
+       "      <td>-188826.0</td>\n",
+       "      <td>-944128.0</td>\n",
+       "      <td>12.2</td>\n",
+       "      <td>184.0</td>\n",
+       "      <td>181.406</td>\n",
+       "      <td>36.2</td>\n",
        "      <td>4747.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>10</td>\n",
-       "      <td>16</td>\n",
-       "      <td>0.00983</td>\n",
-       "      <td>-306176.0</td>\n",
-       "      <td>-1530880.0</td>\n",
-       "      <td>6.1</td>\n",
-       "      <td>1993.0</td>\n",
-       "      <td>1990.138</td>\n",
-       "      <td>18.4</td>\n",
-       "      <td>4773.0</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.01123</td>\n",
+       "      <td>15.6</td>\n",
+       "      <td>78.0</td>\n",
+       "      <td>12.2</td>\n",
+       "      <td>184.0</td>\n",
+       "      <td>181.407</td>\n",
+       "      <td>36.2</td>\n",
+       "      <td>4804.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>7</td>\n",
-       "      <td>24</td>\n",
-       "      <td>0.01115</td>\n",
-       "      <td>-419430.0</td>\n",
-       "      <td>-2097152.0</td>\n",
-       "      <td>6.1</td>\n",
-       "      <td>1993.0</td>\n",
-       "      <td>1990.138</td>\n",
-       "      <td>18.4</td>\n",
-       "      <td>4724.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.00722</td>\n",
+       "      <td>-89498.0</td>\n",
+       "      <td>-447488.0</td>\n",
+       "      <td>12.2</td>\n",
+       "      <td>184.0</td>\n",
+       "      <td>181.406</td>\n",
+       "      <td>36.2</td>\n",
+       "      <td>4720.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
+       "      <td>13</td>\n",
        "      <td>16</td>\n",
-       "      <td>8</td>\n",
-       "      <td>0.00665</td>\n",
-       "      <td>-280576.0</td>\n",
-       "      <td>-1402880.0</td>\n",
-       "      <td>5.6</td>\n",
-       "      <td>1832.0</td>\n",
-       "      <td>1828.775</td>\n",
-       "      <td>16.9</td>\n",
-       "      <td>4720.0</td>\n",
+       "      <td>0.00850</td>\n",
+       "      <td>133.8</td>\n",
+       "      <td>669.0</td>\n",
+       "      <td>12.2</td>\n",
+       "      <td>184.0</td>\n",
+       "      <td>181.407</td>\n",
+       "      <td>36.2</td>\n",
+       "      <td>4777.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>1</td>\n",
+       "      <td>13</td>\n",
        "      <td>20</td>\n",
-       "      <td>0.00989</td>\n",
-       "      <td>-270541.0</td>\n",
-       "      <td>-1352704.0</td>\n",
-       "      <td>6.1</td>\n",
-       "      <td>1993.0</td>\n",
-       "      <td>1990.138</td>\n",
-       "      <td>18.4</td>\n",
-       "      <td>4800.0</td>\n",
+       "      <td>0.00975</td>\n",
+       "      <td>-182886.0</td>\n",
+       "      <td>-914432.0</td>\n",
+       "      <td>12.2</td>\n",
+       "      <td>184.0</td>\n",
+       "      <td>181.406</td>\n",
+       "      <td>36.2</td>\n",
+       "      <td>4720.0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -469,25 +634,25 @@
       ],
       "text/plain": [
        "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
-       "0                    10                 20     0.01203     -439501.0   \n",
-       "1                    10                 16     0.00983     -306176.0   \n",
-       "2                     7                 24     0.01115     -419430.0   \n",
-       "3                    16                  8     0.00665     -280576.0   \n",
-       "4                     1                 20     0.00989     -270541.0   \n",
+       "0                    10                 16     0.00945     -188826.0   \n",
+       "1                    10                 20     0.01123          15.6   \n",
+       "2                     1                  4     0.00722      -89498.0   \n",
+       "3                    13                 16     0.00850         133.8   \n",
+       "4                    13                 20     0.00975     -182886.0   \n",
        "\n",
        "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
-       "0      -2197504.0                 5.6            1832.0           1828.775   \n",
-       "1      -1530880.0                 6.1            1993.0           1990.138   \n",
-       "2      -2097152.0                 6.1            1993.0           1990.138   \n",
-       "3      -1402880.0                 5.6            1832.0           1828.775   \n",
-       "4      -1352704.0                 6.1            1993.0           1990.138   \n",
+       "0       -944128.0                12.2             184.0            181.406   \n",
+       "1            78.0                12.2             184.0            181.407   \n",
+       "2       -447488.0                12.2             184.0            181.406   \n",
+       "3           669.0                12.2             184.0            181.407   \n",
+       "4       -914432.0                12.2             184.0            181.406   \n",
        "\n",
        "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
-       "0                 16.9               4747.0  \n",
-       "1                 18.4               4773.0  \n",
-       "2                 18.4               4724.0  \n",
-       "3                 16.9               4720.0  \n",
-       "4                 18.4               4800.0  "
+       "0                 36.2               4747.0  \n",
+       "1                 36.2               4804.0  \n",
+       "2                 36.2               4720.0  \n",
+       "3                 36.2               4777.0  \n",
+       "4                 36.2               4720.0  "
       ]
      },
      "metadata": {},
@@ -496,21 +661,32 @@
    ],
    "source": [
     "bm = \"avrora\"\n",
+    "xmx = 32\n",
     "\n",
-    "x, y, z =  get_data_from_csv(f\"summaries_{bm}\", goals)\n",
+    "x, y, z =  get_data_from_csv(f\"summaries_{bm}/val/summary_gc_{bm}_{xmx}_*.csv\", goals)\n",
     "\n",
-    "df = pd.DataFrame({\n",
+    "avrora_df = pd.DataFrame({\n",
     "    \"MaxTenuringThreshold\": y,\n",
     "    \"ParallelGCThreads\": x,\n",
     "})\n",
-    "df[goals] = z\n",
-    "display(df[:5])\n",
-    "# df.to_csv(f\"datasets/ext_{bm}_real_saved_states.csv\", index=False)"
+    "avrora_df[goals] = z\n",
+    "display(avrora_df[:5])\n",
+    "avrora_df.to_csv(f\"datasets/avrora/ext_{bm}_{xmx}_real_saved_states.csv\", index=False)\n",
+    "\n",
+    "# from sklearn.preprocessing import MinMaxScaler\n",
+    "\n",
+    "# scaler = MinMaxScaler()\n",
+    "# scaler.fit(avrora_df)\n",
+    "\n",
+    "# normalized_avrora_df = avrora_df.copy()\n",
+    "# normalized_avrora_df.iloc[:, 3:] = pd.DataFrame(scaler.transform(avrora_df)).iloc[:, 3:]\n",
+    "# display(normalized_avrora_df[:5])\n",
+    "# normalized_avrora_df.to_csv(f\"datasets/norm_ext_avrora_real_saved_states.csv\", index=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -648,152 +824,2036 @@
     "\n",
     "x, y, z =  get_data_from_csv(f\"summaries_{bm}\", goals)\n",
     "\n",
-    "df = pd.DataFrame({\n",
+    "kafka_df = pd.DataFrame({\n",
     "    \"MaxTenuringThreshold\": y,\n",
     "    \"ParallelGCThreads\": x,\n",
     "})\n",
-    "df[goals] = z\n",
-    "display(df[:5])\n",
+    "kafka_df[goals] = z\n",
+    "display(kafka_df[:5])\n",
     "# df.to_csv(f\"datasets/ext_{bm}_real_saved_states.csv\", index=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Successfully initialized a JVM Environment!\n",
-      " JDK: jdk-11.0.20.1.jdk/bin,\n",
-      " Benchmark: avrora (dacapo-bench.jar),\n",
-      " Number of iterations: 5,\n",
-      " Goal: avgGCPause,\n",
-      " Number of JVM options: 2,\n",
-      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16}, 'ParallelGCThreads': {'min': 4, 'max': 24}},\n",
-      " Env. default state: [7, 12, 0.01047, 4777.0, 0.05264, 3072.0, -329318.0],\n",
-      " Env. default goal value: 0.01047,\n",
-      "\n"
-     ]
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>10</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.21015</td>\n",
+       "      <td>94.274</td>\n",
+       "      <td>754.188</td>\n",
+       "      <td>35.0</td>\n",
+       "      <td>11425.0</td>\n",
+       "      <td>10839.973</td>\n",
+       "      <td>100.0</td>\n",
+       "      <td>814.539</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>7</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.22059</td>\n",
+       "      <td>95.001</td>\n",
+       "      <td>760.008</td>\n",
+       "      <td>34.9</td>\n",
+       "      <td>11423.0</td>\n",
+       "      <td>10839.972</td>\n",
+       "      <td>100.0</td>\n",
+       "      <td>813.475</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>10</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.14916</td>\n",
+       "      <td>83.676</td>\n",
+       "      <td>753.083</td>\n",
+       "      <td>35.5</td>\n",
+       "      <td>11604.0</td>\n",
+       "      <td>10839.989</td>\n",
+       "      <td>100.0</td>\n",
+       "      <td>847.287</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>24</td>\n",
+       "      <td>0.26639</td>\n",
+       "      <td>108.906</td>\n",
+       "      <td>871.250</td>\n",
+       "      <td>35.0</td>\n",
+       "      <td>11425.0</td>\n",
+       "      <td>10839.987</td>\n",
+       "      <td>100.0</td>\n",
+       "      <td>814.474</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>13</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.20498</td>\n",
+       "      <td>93.689</td>\n",
+       "      <td>749.509</td>\n",
+       "      <td>34.9</td>\n",
+       "      <td>11423.0</td>\n",
+       "      <td>10839.988</td>\n",
+       "      <td>100.0</td>\n",
+       "      <td>812.446</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                    10                  4     0.21015        94.274   \n",
+       "1                     7                 20     0.22059        95.001   \n",
+       "2                    10                  8     0.14916        83.676   \n",
+       "3                     1                 24     0.26639       108.906   \n",
+       "4                    13                  4     0.20498        93.689   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0         754.188                35.0           11425.0          10839.973   \n",
+       "1         760.008                34.9           11423.0          10839.972   \n",
+       "2         753.083                35.5           11604.0          10839.989   \n",
+       "3         871.250                35.0           11425.0          10839.987   \n",
+       "4         749.509                34.9           11423.0          10839.988   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0                100.0              814.539  \n",
+       "1                100.0              813.475  \n",
+       "2                100.0              847.287  \n",
+       "3                100.0              814.474  \n",
+       "4                100.0              812.446  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     }
    ],
    "source": [
-    "from env.PyEnvironmentsTest import JVMEnv\n",
+    "bm = \"h2\"\n",
     "\n",
-    "env_args = {\n",
-    "    \"jdk_path\": \"jdk-11.0.20.1.jdk\",\n",
-    "    \"bm_path\": \"dacapo-bench.jar\",\n",
-    "    \"gc_viewer_jar\": \"gcviewer-1.36.jar\",\n",
-    "    \"callback_path\": \"callback/VMStatCallback.java\",\n",
-    "    \"n\": 5,\n",
-    "    \"goal\": \"avgGCPause\",\n",
-    "    \"verbose\": False,\n",
-    "}\n",
+    "x, y, z =  get_data_from_csv(f\"summaries_{bm}\", goals)\n",
     "\n",
-    "env = JVMEnv(bm_name=\"avrora\", **env_args)"
+    "h2_df = pd.DataFrame({\n",
+    "    \"MaxTenuringThreshold\": y,\n",
+    "    \"ParallelGCThreads\": x,\n",
+    "})\n",
+    "h2_df[goals] = z\n",
+    "display(h2_df[:5])\n",
+    "h2_df.to_csv(f\"datasets/ext_{bm}_real_saved_states.csv\", index=False)"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 4,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "TimeStep(\n",
-       "{'discount': array(1., dtype=float32),\n",
-       " 'observation': array([ 7.00000e+00,  1.20000e+01,  1.04700e-02,  4.77700e+03,\n",
-       "        5.26400e-02,  3.07200e+03, -3.29318e+05], dtype=float32),\n",
-       " 'reward': array(0., dtype=float32),\n",
-       " 'step_type': array(0, dtype=int32)})"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
    "source": [
-    "env.reset()"
+    "### Normalized Dataset"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 14,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "TimeStep(\n",
-       "{'discount': array(0.5, dtype=float32),\n",
-       " 'observation': array([ 1.00000e+01,  1.20000e+01,  8.32000e-03,  4.72000e+03,\n",
-       "        5.03200e-02,  3.07200e+03, -3.96902e+05], dtype=float32),\n",
-       " 'reward': array(0.2053, dtype=float32),\n",
-       " 'step_type': array(1, dtype=int32)})"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
    "source": [
-    "env.step(1)"
+    "### Avrora XMX"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
      "data": {
+      "text/html": [
+       "<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MinMaxScaler()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MinMaxScaler</label><div class=\"sk-toggleable__content\"><pre>MinMaxScaler()</pre></div></div></div></div></div>"
+      ],
       "text/plain": [
-       "{0: {'args': [7, 12],\n",
-       "  'goal': 0.01047,\n",
-       "  'extra': [4777.0, 0.05264, 3072.0, -329318.0],\n",
-       "  'count': 1},\n",
-       " 1: {'args': [10, 12],\n",
-       "  'goal': 0.00832,\n",
-       "  'extra': [4720.0, 0.05032, 3072.0, -396902.0],\n",
-       "  'count': 3},\n",
-       " 2: {'args': [4, 12],\n",
-       "  'goal': 0.009,\n",
-       "  'extra': [4804.0, 0.05416, 3072.0, -382566.0],\n",
-       "  'count': 2}}"
+       "MinMaxScaler()"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "env._perf_states"
+    "bm = \"avrora\"\n",
+    "avrora_dfs = []\n",
+    "for xmx in [2, 4, 8, 16, 32]:\n",
+    "    \n",
+    "    x, y, z =  get_data_from_csv(f\"summaries_{bm}/summary_gc_{bm}_{xmx}_*.csv\", goals)\n",
+    "\n",
+    "    avrora_df = pd.DataFrame({\n",
+    "        \"MaxTenuringThreshold\": y,\n",
+    "        \"ParallelGCThreads\": x,\n",
+    "    })\n",
+    "    avrora_df[goals] = z\n",
+    "    avrora_dfs.append(avrora_df)\n",
+    "\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "\n",
+    "scaler = MinMaxScaler()\n",
+    "scaler.fit(pd.concat(avrora_dfs))\n",
+    "\n",
+    "# normalized_avrora_df = avrora_df.copy()\n",
+    "# normalized_avrora_df.iloc[:, 3:] = pd.DataFrame(scaler.transform(avrora_df)).iloc[:, 3:]\n",
+    "# display(normalized_avrora_df[:5])\n",
+    "# normalized_avrora_df.to_csv(f\"datasets/norm_ext_avrora_real_saved_states.csv\", index=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "text/plain": [
-       "0.00832"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>7</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.00775</td>\n",
+       "      <td>0.974383</td>\n",
+       "      <td>0.995319</td>\n",
+       "      <td>0.571429</td>\n",
+       "      <td>0.566038</td>\n",
+       "      <td>0.571418</td>\n",
+       "      <td>0.576923</td>\n",
+       "      <td>0.000690</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>13</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.00944</td>\n",
+       "      <td>0.447141</td>\n",
+       "      <td>0.456749</td>\n",
+       "      <td>0.428571</td>\n",
+       "      <td>0.433962</td>\n",
+       "      <td>0.428563</td>\n",
+       "      <td>0.432692</td>\n",
+       "      <td>0.037241</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>13</td>\n",
+       "      <td>16</td>\n",
+       "      <td>0.00667</td>\n",
+       "      <td>0.649946</td>\n",
+       "      <td>0.663912</td>\n",
+       "      <td>0.428571</td>\n",
+       "      <td>0.433962</td>\n",
+       "      <td>0.428563</td>\n",
+       "      <td>0.432692</td>\n",
+       "      <td>0.000690</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.00681</td>\n",
+       "      <td>0.974187</td>\n",
+       "      <td>0.995119</td>\n",
+       "      <td>0.571429</td>\n",
+       "      <td>0.566038</td>\n",
+       "      <td>0.571418</td>\n",
+       "      <td>0.576923</td>\n",
+       "      <td>0.000690</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>10</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.00942</td>\n",
+       "      <td>0.399137</td>\n",
+       "      <td>0.407713</td>\n",
+       "      <td>0.428571</td>\n",
+       "      <td>0.433962</td>\n",
+       "      <td>0.428563</td>\n",
+       "      <td>0.432692</td>\n",
+       "      <td>0.000690</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                     7                  8     0.00775      0.974383   \n",
+       "1                    13                 20     0.00944      0.447141   \n",
+       "2                    13                 16     0.00667      0.649946   \n",
+       "3                     4                  8     0.00681      0.974187   \n",
+       "4                    10                 20     0.00942      0.399137   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0        0.995319            0.571429          0.566038           0.571418   \n",
+       "1        0.456749            0.428571          0.433962           0.428563   \n",
+       "2        0.663912            0.428571          0.433962           0.428563   \n",
+       "3        0.995119            0.571429          0.566038           0.571418   \n",
+       "4        0.407713            0.428571          0.433962           0.428563   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0             0.576923             0.000690  \n",
+       "1             0.432692             0.037241  \n",
+       "2             0.432692             0.000690  \n",
+       "3             0.576923             0.000690  \n",
+       "4             0.432692             0.000690  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>13</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.00748</td>\n",
+       "      <td>0.974282</td>\n",
+       "      <td>0.995216</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000690</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>13</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.00721</td>\n",
+       "      <td>0.798274</td>\n",
+       "      <td>0.815427</td>\n",
+       "      <td>0.571429</td>\n",
+       "      <td>0.566038</td>\n",
+       "      <td>0.571398</td>\n",
+       "      <td>0.576923</td>\n",
+       "      <td>0.037931</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>4</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.00863</td>\n",
+       "      <td>0.577671</td>\n",
+       "      <td>0.590083</td>\n",
+       "      <td>0.571429</td>\n",
+       "      <td>0.566038</td>\n",
+       "      <td>0.571418</td>\n",
+       "      <td>0.576923</td>\n",
+       "      <td>0.000690</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>24</td>\n",
+       "      <td>0.01017</td>\n",
+       "      <td>0.063108</td>\n",
+       "      <td>0.064463</td>\n",
+       "      <td>0.428571</td>\n",
+       "      <td>0.433962</td>\n",
+       "      <td>0.428563</td>\n",
+       "      <td>0.432692</td>\n",
+       "      <td>0.013793</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>16</td>\n",
+       "      <td>16</td>\n",
+       "      <td>0.00884</td>\n",
+       "      <td>0.798274</td>\n",
+       "      <td>0.815427</td>\n",
+       "      <td>0.142857</td>\n",
+       "      <td>0.150943</td>\n",
+       "      <td>0.142854</td>\n",
+       "      <td>0.144231</td>\n",
+       "      <td>0.038621</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                    13                  4     0.00748      0.974282   \n",
+       "1                    13                  8     0.00721      0.798274   \n",
+       "2                     4                 20     0.00863      0.577671   \n",
+       "3                     1                 24     0.01017      0.063108   \n",
+       "4                    16                 16     0.00884      0.798274   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0        0.995216            0.000000          0.000000           0.000000   \n",
+       "1        0.815427            0.571429          0.566038           0.571398   \n",
+       "2        0.590083            0.571429          0.566038           0.571418   \n",
+       "3        0.064463            0.428571          0.433962           0.428563   \n",
+       "4        0.815427            0.142857          0.150943           0.142854   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0             0.000000             0.000690  \n",
+       "1             0.576923             0.037931  \n",
+       "2             0.576923             0.000690  \n",
+       "3             0.432692             0.013793  \n",
+       "4             0.144231             0.038621  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>10</td>\n",
+       "      <td>24</td>\n",
+       "      <td>0.00934</td>\n",
+       "      <td>0.172060</td>\n",
+       "      <td>0.175758</td>\n",
+       "      <td>0.428571</td>\n",
+       "      <td>0.433962</td>\n",
+       "      <td>0.428563</td>\n",
+       "      <td>0.432692</td>\n",
+       "      <td>0.039310</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>10</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0.00920</td>\n",
+       "      <td>0.624057</td>\n",
+       "      <td>0.637466</td>\n",
+       "      <td>0.428571</td>\n",
+       "      <td>0.433962</td>\n",
+       "      <td>0.428563</td>\n",
+       "      <td>0.432692</td>\n",
+       "      <td>0.039310</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>13</td>\n",
+       "      <td>24</td>\n",
+       "      <td>0.01206</td>\n",
+       "      <td>0.094930</td>\n",
+       "      <td>0.096970</td>\n",
+       "      <td>0.428571</td>\n",
+       "      <td>0.433962</td>\n",
+       "      <td>0.428563</td>\n",
+       "      <td>0.432692</td>\n",
+       "      <td>0.000690</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>13</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0.00785</td>\n",
+       "      <td>0.723302</td>\n",
+       "      <td>0.738843</td>\n",
+       "      <td>0.085714</td>\n",
+       "      <td>0.094340</td>\n",
+       "      <td>0.095217</td>\n",
+       "      <td>0.096154</td>\n",
+       "      <td>0.000690</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>16</td>\n",
+       "      <td>24</td>\n",
+       "      <td>0.00897</td>\n",
+       "      <td>0.189861</td>\n",
+       "      <td>0.193939</td>\n",
+       "      <td>0.057143</td>\n",
+       "      <td>0.056604</td>\n",
+       "      <td>0.047599</td>\n",
+       "      <td>0.048077</td>\n",
+       "      <td>0.024138</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                    10                 24     0.00934      0.172060   \n",
+       "1                    10                 12     0.00920      0.624057   \n",
+       "2                    13                 24     0.01206      0.094930   \n",
+       "3                    13                 12     0.00785      0.723302   \n",
+       "4                    16                 24     0.00897      0.189861   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0        0.175758            0.428571          0.433962           0.428563   \n",
+       "1        0.637466            0.428571          0.433962           0.428563   \n",
+       "2        0.096970            0.428571          0.433962           0.428563   \n",
+       "3        0.738843            0.085714          0.094340           0.095217   \n",
+       "4        0.193939            0.057143          0.056604           0.047599   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0             0.432692             0.039310  \n",
+       "1             0.432692             0.039310  \n",
+       "2             0.432692             0.000690  \n",
+       "3             0.096154             0.000690  \n",
+       "4             0.048077             0.024138  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>16</td>\n",
+       "      <td>0.00834</td>\n",
+       "      <td>0.350054</td>\n",
+       "      <td>0.357576</td>\n",
+       "      <td>0.428571</td>\n",
+       "      <td>0.433962</td>\n",
+       "      <td>0.428563</td>\n",
+       "      <td>0.432692</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>4</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0.00928</td>\n",
+       "      <td>0.485977</td>\n",
+       "      <td>0.496419</td>\n",
+       "      <td>0.428571</td>\n",
+       "      <td>0.433962</td>\n",
+       "      <td>0.428563</td>\n",
+       "      <td>0.432692</td>\n",
+       "      <td>0.037241</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>7</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0.00743</td>\n",
+       "      <td>0.355447</td>\n",
+       "      <td>0.363085</td>\n",
+       "      <td>0.428571</td>\n",
+       "      <td>0.433962</td>\n",
+       "      <td>0.428563</td>\n",
+       "      <td>0.432692</td>\n",
+       "      <td>0.039310</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>7</td>\n",
+       "      <td>16</td>\n",
+       "      <td>0.00854</td>\n",
+       "      <td>0.610033</td>\n",
+       "      <td>0.623140</td>\n",
+       "      <td>0.571429</td>\n",
+       "      <td>0.566038</td>\n",
+       "      <td>0.571418</td>\n",
+       "      <td>0.576923</td>\n",
+       "      <td>0.039310</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>4</td>\n",
+       "      <td>16</td>\n",
+       "      <td>0.00893</td>\n",
+       "      <td>0.438513</td>\n",
+       "      <td>0.447934</td>\n",
+       "      <td>0.428571</td>\n",
+       "      <td>0.433962</td>\n",
+       "      <td>0.428582</td>\n",
+       "      <td>0.432692</td>\n",
+       "      <td>0.015862</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                     1                 16     0.00834      0.350054   \n",
+       "1                     4                 12     0.00928      0.485977   \n",
+       "2                     7                 12     0.00743      0.355447   \n",
+       "3                     7                 16     0.00854      0.610033   \n",
+       "4                     4                 16     0.00893      0.438513   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0        0.357576            0.428571          0.433962           0.428563   \n",
+       "1        0.496419            0.428571          0.433962           0.428563   \n",
+       "2        0.363085            0.428571          0.433962           0.428563   \n",
+       "3        0.623140            0.571429          0.566038           0.571418   \n",
+       "4        0.447934            0.428571          0.433962           0.428582   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0             0.432692             0.000000  \n",
+       "1             0.432692             0.037241  \n",
+       "2             0.432692             0.039310  \n",
+       "3             0.576923             0.039310  \n",
+       "4             0.432692             0.015862  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>10</td>\n",
+       "      <td>16</td>\n",
+       "      <td>0.00945</td>\n",
+       "      <td>0.476807</td>\n",
+       "      <td>0.487052</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.999981</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.960690</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>10</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.01123</td>\n",
+       "      <td>0.974152</td>\n",
+       "      <td>0.995083</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.00722</td>\n",
+       "      <td>0.738403</td>\n",
+       "      <td>0.754270</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.999981</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.942069</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>13</td>\n",
+       "      <td>16</td>\n",
+       "      <td>0.00850</td>\n",
+       "      <td>0.974463</td>\n",
+       "      <td>0.995401</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.981379</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>13</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.00975</td>\n",
+       "      <td>0.492451</td>\n",
+       "      <td>0.503030</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.999981</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.942069</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                    10                 16     0.00945      0.476807   \n",
+       "1                    10                 20     0.01123      0.974152   \n",
+       "2                     1                  4     0.00722      0.738403   \n",
+       "3                    13                 16     0.00850      0.974463   \n",
+       "4                    13                 20     0.00975      0.492451   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0        0.487052                 1.0               1.0           0.999981   \n",
+       "1        0.995083                 1.0               1.0           1.000000   \n",
+       "2        0.754270                 1.0               1.0           0.999981   \n",
+       "3        0.995401                 1.0               1.0           1.000000   \n",
+       "4        0.503030                 1.0               1.0           0.999981   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0                  1.0             0.960690  \n",
+       "1                  1.0             1.000000  \n",
+       "2                  1.0             0.942069  \n",
+       "3                  1.0             0.981379  \n",
+       "4                  1.0             0.942069  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "for xmx in [2, 4, 8, 16, 32]:\n",
+    "    x, y, z =  get_data_from_csv(f\"summaries_{bm}/summary_gc_{bm}_{xmx}_*.csv\", goals)\n",
+    "    avrora_df = pd.DataFrame({\n",
+    "        \"MaxTenuringThreshold\": y,\n",
+    "        \"ParallelGCThreads\": x,\n",
+    "    })\n",
+    "    avrora_df[goals] = z\n",
+    "    \n",
+    "    normalized_avrora_df = avrora_df.copy()\n",
+    "    normalized_avrora_df.iloc[:, 3:] = pd.DataFrame(scaler.transform(avrora_df)).iloc[:, 3:]\n",
+    "    display(normalized_avrora_df[:5])\n",
+    "    normalized_avrora_df.to_csv(f\"datasets/avrora/norm_ext_avrora_{xmx}_real_saved_states.csv\", index=False)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### KAFKA XMX"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>16</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.01004</td>\n",
+       "      <td>0.992679</td>\n",
+       "      <td>0.990706</td>\n",
+       "      <td>0.070423</td>\n",
+       "      <td>0.015997</td>\n",
+       "      <td>0.016267</td>\n",
+       "      <td>0.980892</td>\n",
+       "      <td>0.607461</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>16</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.00845</td>\n",
+       "      <td>0.991301</td>\n",
+       "      <td>0.990694</td>\n",
+       "      <td>0.070423</td>\n",
+       "      <td>0.015997</td>\n",
+       "      <td>0.016267</td>\n",
+       "      <td>0.980892</td>\n",
+       "      <td>0.516616</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.00875</td>\n",
+       "      <td>0.994496</td>\n",
+       "      <td>0.990722</td>\n",
+       "      <td>0.075117</td>\n",
+       "      <td>0.017294</td>\n",
+       "      <td>0.016168</td>\n",
+       "      <td>0.980892</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>24</td>\n",
+       "      <td>0.01219</td>\n",
+       "      <td>0.994137</td>\n",
+       "      <td>0.990713</td>\n",
+       "      <td>0.131455</td>\n",
+       "      <td>0.025508</td>\n",
+       "      <td>0.018433</td>\n",
+       "      <td>0.936306</td>\n",
+       "      <td>0.717602</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>7</td>\n",
+       "      <td>24</td>\n",
+       "      <td>0.01290</td>\n",
+       "      <td>0.992581</td>\n",
+       "      <td>0.990701</td>\n",
+       "      <td>0.126761</td>\n",
+       "      <td>0.025076</td>\n",
+       "      <td>0.018433</td>\n",
+       "      <td>0.936306</td>\n",
+       "      <td>0.538301</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                    16                  4     0.01004      0.992679   \n",
+       "1                    16                  8     0.00845      0.991301   \n",
+       "2                     1                 20     0.00875      0.994496   \n",
+       "3                     4                 24     0.01219      0.994137   \n",
+       "4                     7                 24     0.01290      0.992581   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0        0.990706            0.070423          0.015997           0.016267   \n",
+       "1        0.990694            0.070423          0.015997           0.016267   \n",
+       "2        0.990722            0.075117          0.017294           0.016168   \n",
+       "3        0.990713            0.131455          0.025508           0.018433   \n",
+       "4        0.990701            0.126761          0.025076           0.018433   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0             0.980892             0.607461  \n",
+       "1             0.980892             0.516616  \n",
+       "2             0.980892             1.000000  \n",
+       "3             0.936306             0.717602  \n",
+       "4             0.936306             0.538301  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.00832</td>\n",
+       "      <td>0.993528</td>\n",
+       "      <td>0.990677</td>\n",
+       "      <td>0.741784</td>\n",
+       "      <td>0.306961</td>\n",
+       "      <td>0.30799</td>\n",
+       "      <td>0.921444</td>\n",
+       "      <td>0.469815</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>4</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.00994</td>\n",
+       "      <td>0.996329</td>\n",
+       "      <td>0.990687</td>\n",
+       "      <td>0.741784</td>\n",
+       "      <td>0.306961</td>\n",
+       "      <td>0.30799</td>\n",
+       "      <td>0.921444</td>\n",
+       "      <td>0.452939</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>7</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.01153</td>\n",
+       "      <td>0.997237</td>\n",
+       "      <td>0.990690</td>\n",
+       "      <td>0.741784</td>\n",
+       "      <td>0.306961</td>\n",
+       "      <td>0.30799</td>\n",
+       "      <td>0.921444</td>\n",
+       "      <td>0.509204</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>10</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.01063</td>\n",
+       "      <td>0.996504</td>\n",
+       "      <td>0.990687</td>\n",
+       "      <td>0.741784</td>\n",
+       "      <td>0.306961</td>\n",
+       "      <td>0.30799</td>\n",
+       "      <td>0.921444</td>\n",
+       "      <td>0.456277</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>10</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.00950</td>\n",
+       "      <td>0.997864</td>\n",
+       "      <td>0.990692</td>\n",
+       "      <td>0.741784</td>\n",
+       "      <td>0.306961</td>\n",
+       "      <td>0.30799</td>\n",
+       "      <td>0.921444</td>\n",
+       "      <td>0.627278</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                     1                  4     0.00832      0.993528   \n",
+       "1                     4                  4     0.00994      0.996329   \n",
+       "2                     7                  4     0.01153      0.997237   \n",
+       "3                    10                  4     0.01063      0.996504   \n",
+       "4                    10                  8     0.00950      0.997864   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0        0.990677            0.741784          0.306961            0.30799   \n",
+       "1        0.990687            0.741784          0.306961            0.30799   \n",
+       "2        0.990690            0.741784          0.306961            0.30799   \n",
+       "3        0.990687            0.741784          0.306961            0.30799   \n",
+       "4        0.990692            0.741784          0.306961            0.30799   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0             0.921444             0.469815  \n",
+       "1             0.921444             0.452939  \n",
+       "2             0.921444             0.509204  \n",
+       "3             0.921444             0.456277  \n",
+       "4             0.921444             0.627278  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.01070</td>\n",
+       "      <td>0.986314</td>\n",
+       "      <td>0.990877</td>\n",
+       "      <td>0.906103</td>\n",
+       "      <td>0.735409</td>\n",
+       "      <td>0.737983</td>\n",
+       "      <td>0.643312</td>\n",
+       "      <td>0.000429</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>7</td>\n",
+       "      <td>24</td>\n",
+       "      <td>0.01116</td>\n",
+       "      <td>0.560922</td>\n",
+       "      <td>0.367135</td>\n",
+       "      <td>0.892019</td>\n",
+       "      <td>0.730653</td>\n",
+       "      <td>0.733301</td>\n",
+       "      <td>0.634820</td>\n",
+       "      <td>0.000827</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>16</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.00870</td>\n",
+       "      <td>0.949091</td>\n",
+       "      <td>0.936298</td>\n",
+       "      <td>0.995305</td>\n",
+       "      <td>0.766105</td>\n",
+       "      <td>0.768837</td>\n",
+       "      <td>0.698514</td>\n",
+       "      <td>0.001164</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.00990</td>\n",
+       "      <td>0.705698</td>\n",
+       "      <td>0.579418</td>\n",
+       "      <td>0.840376</td>\n",
+       "      <td>0.712927</td>\n",
+       "      <td>0.715520</td>\n",
+       "      <td>0.602972</td>\n",
+       "      <td>0.001654</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>16</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.01132</td>\n",
+       "      <td>0.989852</td>\n",
+       "      <td>0.998772</td>\n",
+       "      <td>0.873239</td>\n",
+       "      <td>0.723735</td>\n",
+       "      <td>0.726226</td>\n",
+       "      <td>0.622081</td>\n",
+       "      <td>0.245980</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                     1                  8     0.01070      0.986314   \n",
+       "1                     7                 24     0.01116      0.560922   \n",
+       "2                    16                  8     0.00870      0.949091   \n",
+       "3                     1                 20     0.00990      0.705698   \n",
+       "4                    16                  4     0.01132      0.989852   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0        0.990877            0.906103          0.735409           0.737983   \n",
+       "1        0.367135            0.892019          0.730653           0.733301   \n",
+       "2        0.936298            0.995305          0.766105           0.768837   \n",
+       "3        0.579418            0.840376          0.712927           0.715520   \n",
+       "4        0.998772            0.873239          0.723735           0.726226   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0             0.643312             0.000429  \n",
+       "1             0.634820             0.000827  \n",
+       "2             0.698514             0.001164  \n",
+       "3             0.602972             0.001654  \n",
+       "4             0.622081             0.245980  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>7</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.01131</td>\n",
+       "      <td>0.807811</td>\n",
+       "      <td>0.729143</td>\n",
+       "      <td>0.065728</td>\n",
+       "      <td>0.698227</td>\n",
+       "      <td>0.700512</td>\n",
+       "      <td>0.044586</td>\n",
+       "      <td>0.001654</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>10</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.01266</td>\n",
+       "      <td>0.990237</td>\n",
+       "      <td>0.999619</td>\n",
+       "      <td>0.051643</td>\n",
+       "      <td>0.719412</td>\n",
+       "      <td>0.721958</td>\n",
+       "      <td>0.029724</td>\n",
+       "      <td>0.246225</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>16</td>\n",
+       "      <td>16</td>\n",
+       "      <td>0.01148</td>\n",
+       "      <td>0.956085</td>\n",
+       "      <td>0.946553</td>\n",
+       "      <td>0.164319</td>\n",
+       "      <td>0.740164</td>\n",
+       "      <td>0.742847</td>\n",
+       "      <td>0.101911</td>\n",
+       "      <td>0.000766</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>10</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.00958</td>\n",
+       "      <td>0.986421</td>\n",
+       "      <td>0.991034</td>\n",
+       "      <td>0.230047</td>\n",
+       "      <td>0.768266</td>\n",
+       "      <td>0.770873</td>\n",
+       "      <td>0.135881</td>\n",
+       "      <td>0.000858</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>16</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.01116</td>\n",
+       "      <td>0.737171</td>\n",
+       "      <td>0.625566</td>\n",
+       "      <td>0.154930</td>\n",
+       "      <td>0.738003</td>\n",
+       "      <td>0.740727</td>\n",
+       "      <td>0.095541</td>\n",
+       "      <td>0.001654</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                     7                 20     0.01131      0.807811   \n",
+       "1                    10                  8     0.01266      0.990237   \n",
+       "2                    16                 16     0.01148      0.956085   \n",
+       "3                    10                  4     0.00958      0.986421   \n",
+       "4                    16                 20     0.01116      0.737171   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0        0.729143            0.065728          0.698227           0.700512   \n",
+       "1        0.999619            0.051643          0.719412           0.721958   \n",
+       "2        0.946553            0.164319          0.740164           0.742847   \n",
+       "3        0.991034            0.230047          0.768266           0.770873   \n",
+       "4        0.625566            0.154930          0.738003           0.740727   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0             0.044586             0.001654  \n",
+       "1             0.029724             0.246225  \n",
+       "2             0.101911             0.000766  \n",
+       "3             0.135881             0.000858  \n",
+       "4             0.095541             0.001654  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>24</td>\n",
+       "      <td>0.01056</td>\n",
+       "      <td>0.986570</td>\n",
+       "      <td>0.991253</td>\n",
+       "      <td>0.600939</td>\n",
+       "      <td>0.902291</td>\n",
+       "      <td>0.901674</td>\n",
+       "      <td>0.352442</td>\n",
+       "      <td>0.253729</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.01044</td>\n",
+       "      <td>0.468600</td>\n",
+       "      <td>0.611209</td>\n",
+       "      <td>0.544601</td>\n",
+       "      <td>0.903588</td>\n",
+       "      <td>0.903074</td>\n",
+       "      <td>0.312102</td>\n",
+       "      <td>0.252412</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>13</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.00775</td>\n",
+       "      <td>0.777737</td>\n",
+       "      <td>0.837848</td>\n",
+       "      <td>0.643192</td>\n",
+       "      <td>0.956334</td>\n",
+       "      <td>0.956131</td>\n",
+       "      <td>0.367304</td>\n",
+       "      <td>0.252718</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.01200</td>\n",
+       "      <td>0.746963</td>\n",
+       "      <td>0.639923</td>\n",
+       "      <td>0.690141</td>\n",
+       "      <td>0.941634</td>\n",
+       "      <td>0.941187</td>\n",
+       "      <td>0.403397</td>\n",
+       "      <td>0.253760</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>13</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.00893</td>\n",
+       "      <td>0.441324</td>\n",
+       "      <td>0.191772</td>\n",
+       "      <td>0.676056</td>\n",
+       "      <td>0.969736</td>\n",
+       "      <td>0.969463</td>\n",
+       "      <td>0.386412</td>\n",
+       "      <td>0.252994</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                     1                 24     0.01056      0.986570   \n",
+       "1                     1                  4     0.01044      0.468600   \n",
+       "2                    13                  8     0.00775      0.777737   \n",
+       "3                     4                 20     0.01200      0.746963   \n",
+       "4                    13                  4     0.00893      0.441324   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0        0.991253            0.600939          0.902291           0.901674   \n",
+       "1        0.611209            0.544601          0.903588           0.903074   \n",
+       "2        0.837848            0.643192          0.956334           0.956131   \n",
+       "3        0.639923            0.690141          0.941634           0.941187   \n",
+       "4        0.191772            0.676056          0.969736           0.969463   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0             0.352442             0.253729  \n",
+       "1             0.312102             0.252412  \n",
+       "2             0.367304             0.252718  \n",
+       "3             0.403397             0.253760  \n",
+       "4             0.386412             0.252994  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "bm = \"kafka\"\n",
+    "kafka_dfs = []\n",
+    "for xmx in [2, 4, 8, 16, 32]:\n",
+    "    \n",
+    "    x, y, z =  get_data_from_csv(f\"summaries_{bm}/summary_gc_{bm}_{xmx}_*.csv\", goals)\n",
+    "\n",
+    "    kafka_df = pd.DataFrame({\n",
+    "        \"MaxTenuringThreshold\": y,\n",
+    "        \"ParallelGCThreads\": x,\n",
+    "    })\n",
+    "    kafka_df[goals] = z\n",
+    "    kafka_dfs.append(kafka_df)\n",
+    "\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "\n",
+    "scaler = MinMaxScaler()\n",
+    "scaler.fit(pd.concat(kafka_dfs))\n",
+    "\n",
+    "for xmx in [2, 4, 8, 16, 32]:\n",
+    "    x, y, z =  get_data_from_csv(f\"summaries_{bm}/summary_gc_{bm}_{xmx}_*.csv\", goals)\n",
+    "    kafka_df = pd.DataFrame({\n",
+    "        \"MaxTenuringThreshold\": y,\n",
+    "        \"ParallelGCThreads\": x,\n",
+    "    })\n",
+    "    kafka_df[goals] = z\n",
+    "    \n",
+    "    normalized_kafka_df = kafka_df.copy()\n",
+    "    normalized_kafka_df.iloc[:, 3:] = pd.DataFrame(scaler.transform(kafka_df)).iloc[:, 3:]\n",
+    "    display(normalized_kafka_df[:5])\n",
+    "    normalized_kafka_df.to_csv(f\"datasets/{bm}/norm_ext_{bm}_{xmx}_real_saved_states.csv\", index=False)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Separate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-3 {color: black;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MinMaxScaler()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MinMaxScaler</label><div class=\"sk-toggleable__content\"><pre>MinMaxScaler()</pre></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "MinMaxScaler()"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "\n",
+    "scaler = MinMaxScaler()\n",
+    "scaler.fit(pd.concat([avrora_df, kafka_df, h2_df]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>10</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.01203</td>\n",
+       "      <td>0.034202</td>\n",
+       "      <td>0.034201</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.00000</td>\n",
+       "      <td>0.987496</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>10</td>\n",
+       "      <td>16</td>\n",
+       "      <td>0.00983</td>\n",
+       "      <td>0.327170</td>\n",
+       "      <td>0.327164</td>\n",
+       "      <td>0.028736</td>\n",
+       "      <td>0.028395</td>\n",
+       "      <td>0.029228</td>\n",
+       "      <td>0.02947</td>\n",
+       "      <td>0.993101</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>7</td>\n",
+       "      <td>24</td>\n",
+       "      <td>0.01115</td>\n",
+       "      <td>0.078306</td>\n",
+       "      <td>0.078303</td>\n",
+       "      <td>0.028736</td>\n",
+       "      <td>0.028395</td>\n",
+       "      <td>0.029228</td>\n",
+       "      <td>0.02947</td>\n",
+       "      <td>0.982538</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>16</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.00665</td>\n",
+       "      <td>0.383423</td>\n",
+       "      <td>0.383416</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.00000</td>\n",
+       "      <td>0.981675</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.00989</td>\n",
+       "      <td>0.405474</td>\n",
+       "      <td>0.405467</td>\n",
+       "      <td>0.028736</td>\n",
+       "      <td>0.028395</td>\n",
+       "      <td>0.029228</td>\n",
+       "      <td>0.02947</td>\n",
+       "      <td>0.998922</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                    10                 20     0.01203      0.034202   \n",
+       "1                    10                 16     0.00983      0.327170   \n",
+       "2                     7                 24     0.01115      0.078306   \n",
+       "3                    16                  8     0.00665      0.383423   \n",
+       "4                     1                 20     0.00989      0.405474   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0        0.034201            0.000000          0.000000           0.000000   \n",
+       "1        0.327164            0.028736          0.028395           0.029228   \n",
+       "2        0.078303            0.028736          0.028395           0.029228   \n",
+       "3        0.383416            0.000000          0.000000           0.000000   \n",
+       "4        0.405467            0.028736          0.028395           0.029228   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0              0.00000             0.987496  \n",
+       "1              0.02947             0.993101  \n",
+       "2              0.02947             0.982538  \n",
+       "3              0.00000             0.981675  \n",
+       "4              0.02947             0.998922  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "normalized_avrora_df = avrora_df.copy()\n",
+    "normalized_avrora_df.iloc[:, 3:] = pd.DataFrame(scaler.transform(avrora_df)).iloc[:, 3:]\n",
+    "display(normalized_avrora_df[:5])\n",
+    "# normalized_avrora_df.to_csv(f\"datasets/norm_ext_avrora_real_saved_states.csv\", index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>10</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0.02917</td>\n",
+       "      <td>0.999999</td>\n",
+       "      <td>0.999999</td>\n",
+       "      <td>0.925287</td>\n",
+       "      <td>0.928395</td>\n",
+       "      <td>0.926321</td>\n",
+       "      <td>0.925344</td>\n",
+       "      <td>0.000023</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>10</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.02740</td>\n",
+       "      <td>0.999998</td>\n",
+       "      <td>0.999998</td>\n",
+       "      <td>0.977011</td>\n",
+       "      <td>0.978836</td>\n",
+       "      <td>0.978139</td>\n",
+       "      <td>0.978389</td>\n",
+       "      <td>0.000013</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>7</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.03037</td>\n",
+       "      <td>0.999999</td>\n",
+       "      <td>0.999999</td>\n",
+       "      <td>0.931034</td>\n",
+       "      <td>0.934921</td>\n",
+       "      <td>0.933085</td>\n",
+       "      <td>0.933202</td>\n",
+       "      <td>0.000002</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>10</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.03058</td>\n",
+       "      <td>0.999999</td>\n",
+       "      <td>0.999998</td>\n",
+       "      <td>0.982759</td>\n",
+       "      <td>0.987125</td>\n",
+       "      <td>0.986698</td>\n",
+       "      <td>0.986248</td>\n",
+       "      <td>0.000019</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>10</td>\n",
+       "      <td>24</td>\n",
+       "      <td>0.03323</td>\n",
+       "      <td>0.999999</td>\n",
+       "      <td>0.999999</td>\n",
+       "      <td>0.982759</td>\n",
+       "      <td>0.986949</td>\n",
+       "      <td>0.986498</td>\n",
+       "      <td>0.986248</td>\n",
+       "      <td>0.000019</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                    10                 12     0.02917      0.999999   \n",
+       "1                    10                  8     0.02740      0.999998   \n",
+       "2                     7                 20     0.03037      0.999999   \n",
+       "3                    10                  4     0.03058      0.999999   \n",
+       "4                    10                 24     0.03323      0.999999   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0        0.999999            0.925287          0.928395           0.926321   \n",
+       "1        0.999998            0.977011          0.978836           0.978139   \n",
+       "2        0.999999            0.931034          0.934921           0.933085   \n",
+       "3        0.999998            0.982759          0.987125           0.986698   \n",
+       "4        0.999999            0.982759          0.986949           0.986498   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0             0.925344             0.000023  \n",
+       "1             0.978389             0.000013  \n",
+       "2             0.933202             0.000002  \n",
+       "3             0.986248             0.000019  \n",
+       "4             0.986248             0.000019  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "normalized_kafka_df = kafka_df.copy()\n",
+    "normalized_kafka_df.iloc[:, 3:] = pd.DataFrame(scaler.transform(kafka_df)).iloc[:, 3:]\n",
+    "display(normalized_kafka_df[:5])\n",
+    "# normalized_kafka_df.to_csv(f\"datasets/norm_ext_kafka_real_saved_states.csv\", index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MaxTenuringThreshold</th>\n",
+       "      <th>ParallelGCThreads</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>10</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.21015</td>\n",
+       "      <td>0.999957</td>\n",
+       "      <td>0.988383</td>\n",
+       "      <td>0.983278</td>\n",
+       "      <td>0.981481</td>\n",
+       "      <td>0.999997</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.139725</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>7</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.22059</td>\n",
+       "      <td>0.999959</td>\n",
+       "      <td>0.988386</td>\n",
+       "      <td>0.979933</td>\n",
+       "      <td>0.981277</td>\n",
+       "      <td>0.999997</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.139495</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>10</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0.14916</td>\n",
+       "      <td>0.999934</td>\n",
+       "      <td>0.988383</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.999795</td>\n",
+       "      <td>0.999999</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.146785</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>24</td>\n",
+       "      <td>0.26639</td>\n",
+       "      <td>0.999989</td>\n",
+       "      <td>0.988434</td>\n",
+       "      <td>0.983278</td>\n",
+       "      <td>0.981481</td>\n",
+       "      <td>0.999999</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.139711</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>13</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.20498</td>\n",
+       "      <td>0.999956</td>\n",
+       "      <td>0.988381</td>\n",
+       "      <td>0.979933</td>\n",
+       "      <td>0.981277</td>\n",
+       "      <td>0.999999</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.139273</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MaxTenuringThreshold  ParallelGCThreads  avgGCPause  avgPromotion  \\\n",
+       "0                    10                  4     0.21015      0.999957   \n",
+       "1                     7                 20     0.22059      0.999959   \n",
+       "2                    10                  8     0.14916      0.999934   \n",
+       "3                     1                 24     0.26639      0.999989   \n",
+       "4                    13                  4     0.20498      0.999956   \n",
+       "\n",
+       "   promotionTotal  totalHeapUsedMaxpc  totalHeapUsedMax  totalYoungUsedMax  \\\n",
+       "0        0.988383            0.983278          0.981481           0.999997   \n",
+       "1        0.988386            0.979933          0.981277           0.999997   \n",
+       "2        0.988383            1.000000          0.999795           0.999999   \n",
+       "3        0.988434            0.983278          0.981481           0.999999   \n",
+       "4        0.988381            0.979933          0.981277           0.999999   \n",
+       "\n",
+       "   totalYoungUsedMaxpc  totalTenuredUsedMax  \n",
+       "0                  1.0             0.139725  \n",
+       "1                  1.0             0.139495  \n",
+       "2                  1.0             0.146785  \n",
+       "3                  1.0             0.139711  \n",
+       "4                  1.0             0.139273  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     }
    ],
    "source": [
-    "env._state[2]"
+    "normalized_h2_df = h2_df.copy()\n",
+    "normalized_h2_df.iloc[:, 3:] = pd.DataFrame(scaler.transform(h2_df)).iloc[:, 3:]\n",
+    "display(normalized_h2_df[:5])\n",
+    "# normalized_h2_df.to_csv(f\"datasets/norm_ext_h2_real_saved_states.csv\", index=False)"
    ]
   }
  ],
diff --git a/datasets/avrora/ext_avrora_16_real_saved_states.csv b/datasets/avrora/ext_avrora_16_real_saved_states.csv
new file mode 100644
index 0000000..d0a9c4c
--- /dev/null
+++ b/datasets/avrora/ext_avrora_16_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+1,16,0.00834,-236954.0,-1184768.0,10.2,154.0,151.586,30.3,3354.0
+4,12,0.00928,-185344.0,-926720.0,10.2,154.0,151.586,30.3,3408.0
+7,12,0.00743,-234906.0,-1174528.0,10.2,154.0,151.586,30.3,3411.0
+7,16,0.00854,-138240.0,-691200.0,10.7,161.0,159.041,31.8,3411.0
+4,16,0.00893,-203366.0,-1016832.0,10.2,154.0,151.587,30.3,3377.0
+1,12,0.00822,-173056.0,-865280.0,10.7,161.0,159.041,31.8,3392.0
+7,4,0.00581,-137626.0,-688128.0,10.2,154.0,151.586,30.3,3357.0
+4,4,0.00719,-47309.0,-236544.0,10.7,161.0,159.041,31.8,3355.0
+1,4,0.00629,-50995.0,-254976.0,10.2,154.0,151.586,30.3,3411.0
+10,12,0.00851,-129229.0,-646144.0,10.7,161.0,159.041,31.8,3374.0
+4,24,0.01281,46.8,234.0,10.7,161.0,159.041,31.8,3410.0
+16,4,0.00771,-57549.0,-287744.0,10.2,154.0,151.586,30.3,3411.0
+10,24,0.0103,-192922.0,-964608.0,10.2,154.0,151.585,30.3,3411.0
+1,20,0.01024,-242483.0,-1212416.0,10.7,161.0,159.041,31.8,3355.0
+16,8,0.00722,85.0,425.0,10.7,161.0,159.041,31.8,3355.0
+13,12,0.0074,27.2,136.0,10.7,161.0,159.041,31.8,3411.0
+1,8,0.00723,-178790.0,-893952.0,10.2,154.0,151.586,30.3,3355.0
+7,24,0.00986,-356557.0,-1782784.0,10.2,154.0,151.586,30.3,3354.0
+13,24,0.01207,-134758.0,-673792.0,10.7,161.0,159.042,31.8,3411.0
+16,12,0.00824,-172237.0,-861184.0,9.5,144.0,141.646,28.3,3411.0
+4,8,0.0062,27.2,136.0,10.7,161.0,159.041,31.8,3358.0
+10,4,0.0068,-33792.0,-168960.0,10.7,161.0,159.041,31.8,3374.0
+16,24,0.01499,-134758.0,-673792.0,8.7,131.0,129.221,25.8,3355.0
+10,8,0.00731,-168960.0,-844800.0,10.2,154.0,151.586,30.3,3354.0
+7,20,0.00943,-141722.0,-708608.0,10.7,161.0,159.041,31.8,3388.0
+7,8,0.00753,-60006.0,-300032.0,10.7,161.0,159.041,31.8,3355.0
+1,24,0.01031,-88064.0,-440320.0,10.2,154.0,151.585,30.3,3411.0
+13,4,0.00597,-126362.0,-631808.0,10.2,154.0,151.586,30.3,3386.0
+4,20,0.00943,-265626.0,-1328128.0,10.7,161.0,159.041,31.8,3374.0
+13,8,0.0072,-96256.0,-481280.0,10.7,161.0,159.041,31.8,3374.0
+16,20,0.00931,-239821.0,-1199104.0,10.7,161.0,159.04,31.8,3355.0
+16,16,0.00939,-81510.0,-407552.0,8.7,131.0,129.221,25.8,3355.0
+10,20,0.00875,-81101.0,-405504.0,10.7,161.0,159.041,31.8,3358.0
+10,16,0.00956,-168346.0,-841728.0,8.7,131.0,129.221,25.8,3411.0
+13,20,0.01016,-205210.0,-1026048.0,10.2,154.0,151.586,30.3,3405.0
+13,16,0.00881,-114893.0,-574464.0,10.7,161.0,159.041,31.8,3355.0
diff --git a/datasets/avrora/ext_avrora_2_real_saved_states.csv b/datasets/avrora/ext_avrora_2_real_saved_states.csv
new file mode 100644
index 0000000..cb80747
--- /dev/null
+++ b/datasets/avrora/ext_avrora_2_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+7,8,0.00775,103.2,516.0,10.7,161.0,159.041,31.8,3355.0
+13,20,0.00944,-200090.0,-1000448.0,10.2,154.0,151.586,30.3,3408.0
+13,16,0.00667,-123085.0,-615424.0,10.2,154.0,151.586,30.3,3355.0
+4,8,0.00681,29.0,145.0,10.7,161.0,159.041,31.8,3355.0
+10,20,0.00942,-218317.0,-1091584.0,10.2,154.0,151.586,30.3,3355.0
+10,16,0.00685,-120013.0,-600064.0,10.2,154.0,151.586,30.3,3355.0
+1,8,0.00664,26.2,131.0,8.7,131.0,129.221,25.8,3411.0
+16,20,0.00898,-25395.0,-126976.0,10.7,161.0,159.041,31.8,3411.0
+16,16,0.00917,-254157.0,-1270784.0,10.2,154.0,151.585,30.3,3392.0
+7,24,0.01,-29286.0,-146432.0,9.2,139.0,136.676,27.3,3392.0
+16,4,0.00806,80.2,401.0,8.7,131.0,129.221,25.8,3411.0
+1,20,0.01099,-38093.0,-190464.0,10.2,154.0,151.586,30.3,3374.0
+16,8,0.00634,40.2,201.0,10.7,161.0,159.041,31.8,3355.0
+16,12,0.0079,86.6,433.0,10.7,161.0,159.041,31.8,3374.0
+16,24,0.00891,-113254.0,-566272.0,10.7,161.0,159.04,31.8,3355.0
+4,24,0.01072,-247603.0,-1238016.0,10.7,161.0,159.041,31.8,3404.0
+13,4,0.0066,-72909.0,-364544.0,9.2,139.0,136.676,27.3,3355.0
+4,20,0.00877,-184320.0,-921600.0,8.7,131.0,129.221,25.8,3408.0
+13,8,0.00729,-72294.0,-361472.0,10.7,161.0,159.04,31.8,3411.0
+13,12,0.00899,-130253.0,-651264.0,10.7,161.0,159.041,31.8,3355.0
+13,24,0.01115,-234906.0,-1174528.0,10.7,161.0,159.041,31.8,3374.0
+1,24,0.01013,-154829.0,-774144.0,10.2,154.0,151.586,30.3,3357.0
+10,4,0.00706,9830.0,48.0,8.7,131.0,129.221,25.8,3408.0
+10,8,0.00727,-169165.0,-845824.0,10.2,154.0,151.586,30.3,3411.0
+7,20,0.01087,-177562.0,-887808.0,9.2,139.0,136.676,27.3,3408.0
+10,12,0.00819,-79053.0,-395264.0,9.2,139.0,136.676,27.3,3392.0
+10,24,0.01085,-99738.0,-498688.0,10.7,161.0,159.041,31.8,3411.0
+7,12,0.00763,-150528.0,-752640.0,10.2,154.0,151.586,30.3,3411.0
+4,12,0.00818,-144179.0,-720896.0,10.2,154.0,151.586,30.3,3405.0
+1,16,0.00827,-101786.0,-508928.0,9.4,141.0,139.16,27.8,3408.0
+1,4,0.00719,-98918.0,-494592.0,9.5,144.0,141.646,28.3,3410.0
+1,12,0.00857,8602.0,42.0,10.7,161.0,159.042,31.8,3357.0
+4,16,0.00852,-279142.0,-1395712.0,10.2,154.0,151.586,30.3,3392.0
+4,4,0.00751,-129638.0,-648192.0,10.2,154.0,151.586,30.3,3354.0
+7,16,0.00857,-137421.0,-687104.0,10.2,154.0,151.586,30.3,3380.0
+7,4,0.00693,142.6,713.0,10.7,161.0,159.041,31.8,3376.0
diff --git a/datasets/avrora/ext_avrora_32_real_saved_states.csv b/datasets/avrora/ext_avrora_32_real_saved_states.csv
new file mode 100644
index 0000000..d5ba986
--- /dev/null
+++ b/datasets/avrora/ext_avrora_32_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+10,16,0.00945,-188826.0,-944128.0,12.2,184.0,181.406,36.2,4747.0
+10,20,0.01123,15.6,78.0,12.2,184.0,181.407,36.2,4804.0
+1,4,0.00722,-89498.0,-447488.0,12.2,184.0,181.406,36.2,4720.0
+13,16,0.0085,133.8,669.0,12.2,184.0,181.407,36.2,4777.0
+13,20,0.00975,-182886.0,-914432.0,12.2,184.0,181.406,36.2,4720.0
+4,4,0.0078,-130458.0,-652288.0,11.7,177.0,173.952,34.8,4720.0
+16,16,0.00842,-98714.0,-493568.0,12.2,184.0,181.406,36.2,4720.0
+16,20,0.01044,151.6,758.0,11.7,177.0,173.952,34.8,4747.0
+7,4,0.00595,-36864.0,-184320.0,11.1,167.0,164.013,32.8,4720.0
+7,12,0.00918,-46080.0,-230400.0,11.7,177.0,173.952,34.8,4746.0
+16,24,0.01017,133.8,669.0,12.2,184.0,181.407,36.2,4804.0
+16,12,0.00819,-290611.0,-1453056.0,11.7,177.0,173.952,34.8,4777.0
+4,12,0.00802,-143360.0,-716800.0,12.2,184.0,181.406,36.2,4804.0
+1,16,0.00911,-262758.0,-1313792.0,11.7,177.0,173.951,34.8,4777.0
+1,12,0.00775,15.6,78.0,12.2,184.0,181.406,36.2,4720.0
+10,24,0.01026,60.8,304.0,11.2,169.0,166.497,33.3,4720.0
+10,12,0.00836,-54477.0,-272384.0,11.7,177.0,173.952,34.8,4756.0
+4,16,0.00905,84.2,421.0,12.2,184.0,181.407,36.2,4804.0
+13,24,0.01168,-112640.0,-563200.0,12.2,184.0,181.406,36.2,4720.0
+13,12,0.00816,-161587.0,-807936.0,11.7,177.0,173.952,34.8,4803.0
+7,16,0.00927,-86426.0,-432128.0,11.5,174.0,171.468,34.3,4768.0
+7,8,0.00638,-205.0,-1024.0,12.2,184.0,181.406,36.2,4747.0
+7,24,0.00923,-96870.0,-484352.0,12.2,184.0,181.406,36.2,4803.0
+16,4,0.00774,-306176.0,-1530880.0,11.7,177.0,173.951,34.8,4777.0
+1,20,0.01001,68.0,340.0,12.2,184.0,181.407,36.2,4719.0
+16,8,0.00688,-410.0,-2048.0,12.2,184.0,181.406,36.2,4804.0
+4,24,0.01008,52.8,264.0,12.2,184.0,181.406,36.2,4724.0
+4,8,0.00673,-56115.0,-280576.0,12.2,184.0,181.407,36.2,4795.0
+13,4,0.00559,-56730.0,-283648.0,11.7,177.0,173.952,34.8,4724.0
+4,20,0.01103,-76595.0,-382976.0,11.7,177.0,173.951,34.8,4777.0
+13,8,0.00724,9421.0,46.0,11.7,177.0,173.952,34.8,4747.0
+1,8,0.00712,-15155.0,-75776.0,12.2,184.0,181.406,36.2,4777.0
+1,24,0.00862,1843.0,9216.0,12.2,184.0,181.406,36.2,4804.0
+10,4,0.00629,-4096.0,-20480.0,12.2,184.0,181.407,36.2,4752.0
+10,8,0.00676,-109363.0,-546816.0,12.2,184.0,181.406,36.2,4720.0
+7,20,0.01009,19.0,95.0,12.2,184.0,181.407,36.2,4748.0
diff --git a/datasets/avrora/ext_avrora_4_real_saved_states.csv b/datasets/avrora/ext_avrora_4_real_saved_states.csv
new file mode 100644
index 0000000..f56d7a5
--- /dev/null
+++ b/datasets/avrora/ext_avrora_4_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+13,4,0.00748,64.8,324.0,8.7,131.0,129.221,25.8,3355.0
+13,8,0.00721,-66765.0,-333824.0,10.7,161.0,159.04,31.8,3409.0
+4,20,0.00863,-150528.0,-752640.0,10.7,161.0,159.041,31.8,3355.0
+1,24,0.01017,-345907.0,-1729536.0,10.2,154.0,151.586,30.3,3374.0
+16,16,0.00884,-66765.0,-333824.0,9.2,139.0,136.676,27.3,3410.0
+10,4,0.01688,70.2,351.0,10.7,161.0,159.041,31.8,3377.0
+7,20,0.00975,-129024.0,-645120.0,10.7,161.0,159.041,31.8,3377.0
+10,8,0.00647,-151142.0,-755712.0,9.2,139.0,136.676,27.3,3355.0
+16,20,0.00977,-210739.0,-1053696.0,10.7,161.0,159.042,31.8,3374.0
+13,16,0.00827,-114483.0,-572416.0,10.7,161.0,159.042,31.8,3357.0
+13,20,0.00919,-161382.0,-806912.0,9.5,144.0,141.646,28.3,3392.0
+7,24,0.00995,-212378.0,-1061888.0,8.7,131.0,129.221,25.8,3408.0
+10,16,0.00925,-305357.0,-1526784.0,10.2,154.0,151.586,30.3,3355.0
+16,4,0.00825,78.2,391.0,10.7,161.0,159.041,31.8,3377.0
+16,8,0.0074,-113254.0,-566272.0,10.2,154.0,151.586,30.3,3354.0
+1,20,0.00973,-296346.0,-1481728.0,10.2,154.0,151.586,30.3,3374.0
+10,20,0.01006,-204186.0,-1020928.0,10.7,161.0,159.041,31.8,3355.0
+4,24,0.00937,-211149.0,-1055744.0,10.7,161.0,159.04,31.8,3392.0
+13,24,0.00965,-62669.0,-313344.0,10.7,161.0,159.041,31.8,3412.0
+4,4,0.00618,46.6,233.0,10.7,161.0,159.04,31.8,3408.0
+13,12,0.00856,-238592.0,-1192960.0,10.2,154.0,151.586,30.3,3374.0
+7,4,0.0064,136.6,683.0,8.7,131.0,129.221,25.8,3411.0
+10,24,0.01073,-268288.0,-1341440.0,10.7,161.0,159.041,31.8,3355.0
+10,12,0.009,68.8,344.0,10.7,161.0,159.04,31.8,3410.0
+16,24,0.01018,-128205.0,-641024.0,10.7,161.0,159.04,31.8,3411.0
+1,4,0.00756,3891.0,19.0,8.7,131.0,129.221,25.8,3392.0
+16,12,0.00927,-147866.0,-739328.0,10.2,154.0,151.586,30.3,3357.0
+1,12,0.00887,-19661.0,-98304.0,10.7,161.0,159.041,31.8,3374.0
+1,8,0.00863,-84378.0,-421888.0,9.2,139.0,136.676,27.3,3408.0
+4,16,0.00929,-221389.0,-1106944.0,10.2,154.0,151.586,30.3,3374.0
+7,16,0.00984,-369869.0,-1849344.0,10.2,154.0,151.587,30.3,3386.0
+7,12,0.00809,-102195.0,-510976.0,10.7,161.0,159.041,31.8,3392.0
+7,8,0.00665,-18227.0,-91136.0,10.2,154.0,151.586,30.3,3405.0
+4,12,0.00803,1638.0,8192.0,10.7,161.0,159.04,31.8,3355.0
+4,8,0.00619,-9011.0,-45056.0,9.4,141.0,139.16,27.8,3411.0
+1,16,0.009,-319693.0,-1598464.0,10.2,154.0,151.586,30.3,3357.0
diff --git a/datasets/avrora/ext_avrora_8_real_saved_states.csv b/datasets/avrora/ext_avrora_8_real_saved_states.csv
new file mode 100644
index 0000000..0eca8dd
--- /dev/null
+++ b/datasets/avrora/ext_avrora_8_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+10,24,0.00934,-304538.0,-1522688.0,10.2,154.0,151.586,30.3,3411.0
+10,12,0.0092,-132915.0,-664576.0,10.2,154.0,151.586,30.3,3411.0
+13,24,0.01206,-333824.0,-1669120.0,10.2,154.0,151.586,30.3,3355.0
+13,12,0.00785,-95232.0,-476160.0,9.0,136.0,134.19,26.8,3355.0
+16,24,0.00897,-297779.0,-1488896.0,8.9,134.0,131.705,26.3,3389.0
+16,12,0.00815,14.6,73.0,10.7,161.0,159.041,31.8,3392.0
+7,8,0.00691,-135782.0,-678912.0,9.2,139.0,136.676,27.3,3355.0
+1,20,0.0102,-110797.0,-553984.0,10.7,161.0,159.042,31.8,3392.0
+16,8,0.00702,35.4,177.0,10.7,161.0,159.041,31.8,3354.0
+16,16,0.00832,-207053.0,-1035264.0,9.5,144.0,141.646,28.3,3411.0
+16,4,0.0072,-83149.0,-415744.0,10.2,154.0,151.586,30.3,3388.0
+16,20,0.00881,-211149.0,-1055744.0,10.7,161.0,159.041,31.8,3374.0
+4,24,0.0099,-119398.0,-596992.0,10.7,161.0,159.041,31.8,3380.0
+4,8,0.00757,-58368.0,-291840.0,10.7,161.0,159.041,31.8,3411.0
+7,24,0.00912,-182682.0,-913408.0,10.7,161.0,159.041,31.8,3354.0
+1,8,0.0069,27.2,136.0,10.7,161.0,159.041,31.8,3355.0
+10,8,0.00674,-74342.0,-371712.0,10.2,154.0,151.586,30.3,3408.0
+7,20,0.00884,-237568.0,-1187840.0,10.7,161.0,159.04,31.8,3408.0
+10,16,0.00927,-121856.0,-609280.0,9.2,139.0,136.676,27.3,3411.0
+10,4,0.00637,-43827.0,-219136.0,10.7,161.0,159.04,31.8,3357.0
+10,20,0.01013,-99942.0,-499712.0,10.7,161.0,159.041,31.8,3355.0
+4,20,0.01022,-47514.0,-237568.0,10.7,161.0,159.041,31.8,3377.0
+13,8,0.00762,-87859.0,-439296.0,10.7,161.0,159.041,31.8,3374.0
+13,16,0.00898,-156467.0,-782336.0,10.7,161.0,159.041,31.8,3408.0
+13,4,0.00683,84.8,424.0,10.7,161.0,159.04,31.8,3392.0
+13,20,0.00938,-327066.0,-1635328.0,10.2,154.0,151.586,30.3,3355.0
+1,24,0.0101,-229581.0,-1147904.0,10.7,161.0,159.041,31.8,3355.0
+1,4,0.00704,-33792.0,-168960.0,10.7,161.0,159.041,31.8,3411.0
+4,4,0.00703,-42189.0,-210944.0,10.7,161.0,159.041,31.8,3392.0
+7,4,0.00738,-35840.0,-179200.0,10.7,161.0,159.04,31.8,3411.0
+4,12,0.00842,-154010.0,-770048.0,10.2,154.0,151.585,30.3,3411.0
+1,16,0.00855,-176947.0,-884736.0,10.2,154.0,151.586,30.3,3392.0
+7,12,0.00848,-118170.0,-590848.0,10.2,154.0,151.586,30.3,3355.0
+7,16,0.00893,-268288.0,-1341440.0,10.2,154.0,151.586,30.3,3355.0
+1,12,0.00826,-111411.0,-557056.0,10.7,161.0,159.041,31.8,3392.0
+4,16,0.00829,-89702.0,-448512.0,10.7,161.0,159.041,31.8,3411.0
diff --git a/datasets/ext_h2_real_saved_states.csv b/datasets/ext_h2_real_saved_states.csv
new file mode 100644
index 0000000..60ee860
--- /dev/null
+++ b/datasets/ext_h2_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+10,4,0.21015,94.274,754.188,35.0,11425.0,10839.973,100.0,814.539
+7,20,0.22059,95.001,760.008,34.9,11423.0,10839.972,100.0,813.475
+10,8,0.14916,83.676,753.083,35.5,11604.0,10839.989,100.0,847.287
+1,24,0.26639,108.906,871.25,35.0,11425.0,10839.987,100.0,814.474
+13,4,0.20498,93.689,749.509,34.9,11423.0,10839.988,100.0,812.446
+13,8,0.14861,94.426,755.404,35.0,11438.0,10839.972,100.0,812.749
+4,20,0.17963,76.379,763.794,35.5,11606.0,10839.972,100.0,849.216
+1,4,0.18607,109.583,876.662,34.9,11423.0,10839.977,100.0,813.266
+4,24,0.278,93.911,751.284,35.1,11468.0,10839.989,100.0,813.204
+16,4,0.18847,83.72,753.478,35.5,11604.0,10839.973,100.0,847.306
+4,4,0.19791,92.699,741.592,34.9,11423.0,10839.992,100.0,812.438
+16,8,0.16909,97.88,783.044,35.1,11475.0,10839.972,100.0,812.608
+1,20,0.18954,104.515,940.637,35.5,11606.0,10839.987,100.0,849.446
+7,24,0.25286,85.572,770.149,35.5,11604.0,10839.976,100.0,847.016
+7,4,0.18653,84.462,760.158,35.5,11605.0,10839.973,100.0,847.754
+7,8,0.16755,93.89,751.12,35.0,11430.0,10839.989,100.0,813.025
+10,20,0.20235,85.897,773.075,35.5,11604.0,10839.978,100.0,847.329
+10,16,0.17939,95.027,760.219,35.0,11425.0,10839.989,100.0,815.012
+4,8,0.15689,95.128,761.027,35.1,11466.0,10839.988,100.0,815.667
+13,20,0.22224,94.269,754.152,35.2,11490.0,10839.976,100.0,812.816
+13,16,0.18425,95.858,766.864,35.2,11502.0,10839.989,100.0,812.708
+1,8,0.12919,98.147,981.474,35.5,11605.0,10839.973,100.0,896.418
+16,20,0.20235,84.428,759.854,35.5,11605.0,10839.989,100.0,847.571
+16,16,0.17439,93.567,748.539,35.0,11433.0,10839.987,100.0,813.236
+16,12,0.17112,94.664,757.312,35.0,11433.0,10839.985,100.0,814.023
+7,16,0.1788,93.638,749.102,34.9,11423.0,10839.972,100.0,812.685
+16,24,0.28523,95.429,763.429,34.9,11423.0,10839.977,100.0,813.489
+4,16,0.13649,77.147,771.466,35.5,11604.0,10839.998,100.0,847.062
+1,12,0.15362,112.86,902.879,35.0,11424.0,10839.991,100.0,817.188
+10,12,0.19358,93.874,27505.063,35.5,11606.0,10839.998,100.0,896.418
+1,16,0.16398,113.886,911.088,35.0,11454.0,10839.972,100.0,812.562
+4,12,0.18579,95.516,764.132,35.0,11449.0,10839.986,100.0,814.646
+10,24,0.28042,94.737,757.895,35.0,11434.0,10839.972,100.0,813.926
+13,12,0.16804,95.532,764.253,35.0,11425.0,10839.973,100.0,814.718
+7,12,0.16018,94.805,758.438,34.9,11423.0,10839.988,100.0,812.745
+13,24,0.27699,95.563,764.506,35.4,11561.0,10839.987,100.0,812.85
diff --git a/datasets/norm_ext_avrora_16_real_saved_states.csv b/datasets/norm_ext_avrora_16_real_saved_states.csv
new file mode 100644
index 0000000..ffbdefb
--- /dev/null
+++ b/datasets/norm_ext_avrora_16_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+1,16,0.00834,0.3500535950845275,0.35757575757575755,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0
+4,12,0.00928,0.4859770502424289,0.49641873278236914,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.03724137931034521
+7,12,0.00743,0.35544734118341104,0.36308539944903584,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.03931034482758644
+7,16,0.00854,0.6100332105167514,0.6231404958677685,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.03931034482758644
+4,16,0.00893,0.4385131380382882,0.4479338842975207,0.4285714285714284,0.4339622641509431,0.4285823784156668,0.4326923076923075,0.015862068965517562
+1,12,0.00822,0.5183395268357305,0.5294765840220386,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.026206896551724146
+7,4,0.00581,0.6116502808803815,0.6247933884297521,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.002068965517241672
+4,4,0.00719,0.8495150105741653,0.8677685950413223,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+1,4,0.00629,0.8398073210622098,0.8578512396694215,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.03931034482758644
+10,12,0.00851,0.6337651666188218,0.6473829201101928,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.01379310344827589
+4,24,0.01281,0.9742343277174814,0.9951672262396694,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.038620689655172846
+16,4,0.00771,0.8225462800797474,0.8402203856749311,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.03931034482758644
+10,24,0.0103,0.4660191362105246,0.4760330578512396,0.4285714285714284,0.4339622641509431,0.4285440539608327,0.4326923076923075,0.03931034482758644
+1,20,0.01024,0.3354920608165942,0.3426997245179063,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+16,8,0.00722,0.9743349337238181,0.9952699939738291,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+13,12,0.0074,0.9741827078817695,0.995114497245179,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.03931034482758644
+1,8,0.00723,0.5032380912248913,0.5140495867768595,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0006896551724140387
+7,24,0.00986,0.035059349642743376,0.03581267217630857,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0
+13,24,0.01207,0.6192036323508885,0.6325068870523416,0.5714285714285716,0.5660377358490565,0.5714367838117504,0.5769230769230766,0.03931034482758644
+16,12,0.00824,0.5204964985422664,0.5316804407713498,0.22857142857142865,0.24528301886792425,0.23809067566013864,0.24038461538461497,0.03931034482758644
+4,8,0.0062,0.9741827078817695,0.995114497245179,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0027586206896552667
+10,4,0.0068,0.8851142615598144,0.9041322314049586,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.01379310344827589
+16,24,0.01499,0.6192036323508885,0.6325068870523416,0.0,0.0,0.0,0.0,0.0006896551724140387
+10,8,0.00731,0.5291270190334976,0.5404958677685949,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0
+7,20,0.00943,0.6008627886826143,0.6137741046831955,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.023448275862069323
+7,8,0.00753,0.8160753649601394,0.8336088154269972,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+1,24,0.01031,0.7421799899393994,0.7581267217630854,0.4285714285714284,0.4339622641509431,0.4285440539608327,0.4326923076923075,0.03931034482758644
+13,4,0.00597,0.6413158844242413,0.6550964187327823,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.02206896551724169
+4,20,0.00943,0.2745411497001572,0.28044077134986223,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.01379310344827589
+13,8,0.0072,0.7206050055438651,0.7360881542699724,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.01379310344827589
+16,20,0.00931,0.3425028772791079,0.349862258953168,0.5714285714285716,0.5660377358490565,0.5713984593569155,0.5769230769230766,0.0006896551724140387
+16,16,0.00939,0.7594410309218618,0.7757575757575756,0.0,0.0,0.0,0.0,0.0006896551724140387
+10,20,0.00875,0.7605181999425861,0.7768595041322314,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0027586206896552667
+10,16,0.00956,0.5307440893971278,0.5421487603305785,0.0,0.0,0.0,0.0,0.03931034482758644
+13,20,0.01016,0.4336566596172231,0.4429752066115702,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.03517241379310354
+13,16,0.00881,0.6715213893110068,0.6859504132231404,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
diff --git a/datasets/norm_ext_avrora_2_real_saved_states.csv b/datasets/norm_ext_avrora_2_real_saved_states.csv
new file mode 100644
index 0000000..89ea7b7
--- /dev/null
+++ b/datasets/norm_ext_avrora_2_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+7,8,0.00775,0.9743828664284078,0.9953189566115702,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+13,20,0.00944,0.4471410248644321,0.4567493112947658,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.03724137931034521
+13,16,0.00667,0.6499464049154725,0.6639118457300275,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0006896551724140387
+4,8,0.00681,0.9741874484789267,0.9951193397038567,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+10,20,0.00942,0.39913721131738567,0.40771349862258954,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0006896551724140387
+10,16,0.00685,0.6580370240637978,0.6721763085399448,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0006896551724140387
+1,8,0.00664,0.9741800742166822,0.9951118069903581,0.0,0.0,0.0,0.0,0.03931034482758644
+16,20,0.00898,0.9072291472982547,0.9267217630853994,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.03931034482758644
+16,16,0.00917,0.30474665458692285,0.3112947658402204,0.4285714285714284,0.4339622641509431,0.4285440539608327,0.4326923076923075,0.026206896551724146
+7,24,0.01,0.8969815564433933,0.9162534435261708,0.1428571428571428,0.15094339622641506,0.14285440539608318,0.14423076923076916,0.026206896551724146
+16,4,0.00806,0.9743222921313988,0.9952570807506886,0.0,0.0,0.0,0.0,0.03931034482758644
+1,20,0.01099,0.8737868680191415,0.8925619834710743,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.01379310344827589
+16,8,0.00634,0.9742169455279049,0.9951494705578512,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+16,12,0.0079,0.9743391475879578,0.9952742983815426,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.01379310344827589
+16,24,0.00891,0.6758379663891662,0.6903581267217631,0.5714285714285716,0.5660377358490565,0.5713984593569155,0.5769230769230766,0.0006896551724140387
+4,24,0.01072,0.32200769556938524,0.3289256198347107,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.034482758620689946
+13,4,0.0066,0.7820931843381205,0.7988980716253443,0.1428571428571428,0.15094339622641506,0.14285440539608318,0.14423076923076916,0.0006896551724140387
+4,20,0.00877,0.48867392329187065,0.49917355371900823,0.0,0.0,0.0,0.0,0.03724137931034521
+13,8,0.00729,0.783712888366838,0.8005509641873277,0.5714285714285716,0.5660377358490565,0.5713984593569155,0.5769230769230766,0.03931034482758644
+13,12,0.00899,0.6310682935693799,0.6446280991735537,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+13,24,0.01115,0.35544734118341104,0.36308539944903584,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.01379310344827589
+1,24,0.01013,0.5663433403827769,0.5785123966942148,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.002068965517241672
+10,4,0.00706,1.0,0.9950671487603305,0.0,0.0,0.0,0.0,0.03724137931034521
+10,8,0.00727,0.5285871176905917,0.5399449035812671,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.03931034482758644
+7,20,0.01087,0.5064722319521515,0.5173553719008264,0.1428571428571428,0.15094339622641506,0.14285440539608318,0.14423076923076916,0.03724137931034521
+10,12,0.00819,0.7659119460414697,0.7823691460055096,0.1428571428571428,0.15094339622641506,0.14285440539608318,0.14423076923076916,0.026206896551724146
+10,24,0.01085,0.711434583709728,0.7267217630853994,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.03931034482758644
+7,12,0.00763,0.5776707339234499,0.5900826446280991,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.03931034482758644
+4,12,0.00818,0.5943918735630065,0.6071625344352617,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.03517241379310354
+1,16,0.00827,0.7060408376108444,0.7212121212121212,0.20000000000000018,0.18867924528301883,0.19045337830069364,0.19230769230769207,0.03724137931034521
+1,4,0.00719,0.7135941890813513,0.7289256198347107,0.22857142857142865,0.24528301886792425,0.23809067566013864,0.24038461538461497,0.038620689655172846
+1,12,0.00857,0.9967658592727398,0.9950639204545454,0.5714285714285716,0.5660377358490565,0.5714367838117504,0.5769230769230766,0.002068965517241672
+4,16,0.00852,0.23894453237959545,0.24407713498622585,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.026206896551724146
+4,4,0.00751,0.6326879975980975,0.6462809917355372,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0
+7,16,0.00857,0.6121901822232874,0.6253443526170799,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.01793103448275879
+7,4,0.00693,0.9744866328328492,0.9954249526515151,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.015172413793103523
diff --git a/datasets/norm_ext_avrora_32_real_saved_states.csv b/datasets/norm_ext_avrora_32_real_saved_states.csv
new file mode 100644
index 0000000..45fc6f9
--- /dev/null
+++ b/datasets/norm_ext_avrora_32_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+10,16,0.00945,0.47680662840829185,0.4870523415977961,1.0,0.9999999999999996,0.9999808377725827,1.0,0.960689655172414
+10,20,0.01123,0.9741521573667563,0.9950832902892561,1.0,0.9999999999999996,1.0,1.0,1.0
+1,4,0.00722,0.738403314204146,0.7542699724517906,1.0,0.9999999999999996,0.9999808377725827,1.0,0.9420689655172416
+13,16,0.0085,0.9744634565800805,0.9954012784090909,1.0,0.9999999999999996,1.0,1.0,0.9813793103448276
+13,20,0.00975,0.4924505990271241,0.5030303030303029,1.0,0.9999999999999996,0.9999808377725827,1.0,0.9420689655172416
+4,4,0.0078,0.6305283922264742,0.6440771349862259,0.8571428571428572,0.8679245283018866,0.8571455946039168,0.8653846153846145,0.9420689655172416
+16,16,0.00842,0.7141314567591698,0.7294765840220385,1.0,0.9999999999999996,0.9999808377725827,1.0,0.9420689655172416
+16,20,0.01044,0.9745103358186353,0.9954491649449035,0.8571428571428572,0.8679245283018866,0.8571455946039168,0.8653846153846145,0.960689655172414
+7,4,0.00595,0.8770236424114891,0.8958677685950412,0.6857142857142859,0.6792452830188678,0.6666922163032232,0.6730769230769225,0.9420689655172416
+7,12,0.00918,0.8527517849665129,0.8710743801652892,0.8571428571428572,0.8679245283018866,0.8571455946039168,0.8653846153846145,0.96
+16,24,0.01017,0.9744634565800805,0.9954012784090909,1.0,0.9999999999999996,1.0,1.0,1.0
+16,12,0.00819,0.2087390274928298,0.21322314049586777,0.8571428571428572,0.8679245283018866,0.8571455946039168,0.8653846153846145,0.9813793103448276
+4,12,0.00802,0.5965488452695424,0.609366391184573,1.0,0.9999999999999996,0.9999808377725827,1.0,1.0
+1,16,0.00911,0.28209450117066415,0.28815426997245175,0.8571428571428572,0.8679245283018866,0.8571264323764991,0.8653846153846145,0.9813793103448276
+1,12,0.00775,0.9741521573667563,0.9950832902892561,1.0,0.9999999999999996,0.9999808377725827,1.0,0.9420689655172416
+10,24,0.01026,0.9742711990287043,0.9952048898071625,0.7142857142857144,0.7169811320754715,0.7142911892078336,0.7211538461538454,0.9420689655172416
+10,12,0.00836,0.8306368992280728,0.8484848484848484,0.8571428571428572,0.8679245283018866,0.8571455946039168,0.8653846153846145,0.9668965517241381
+4,16,0.00905,0.9743328267917482,0.9952678417699724,1.0,0.9999999999999996,1.0,1.0,1.0
+13,24,0.01168,0.6774550367527963,0.6920110192837465,1.0,0.9999999999999996,0.9999808377725827,1.0,0.9420689655172416
+13,12,0.00816,0.548545031722496,0.5603305785123966,0.8571428571428572,0.8679245283018866,0.8571455946039168,0.8653846153846145,0.9993103448275864
+7,16,0.00927,0.7464939333524713,0.7625344352617079,0.8000000000000003,0.8113207547169807,0.8095466216993059,0.8173076923076916,0.9751724137931035
+7,8,0.00638,0.9735711708484879,0.9944903581267217,1.0,0.9999999999999996,0.9999808377725827,1.0,0.960689655172414
+7,24,0.00923,0.7189879351802348,0.734435261707989,1.0,0.9999999999999996,0.9999808377725827,1.0,0.9993103448275864
+16,4,0.00774,0.16774603040829705,0.1713498622589532,0.8571428571428572,0.8679245283018866,0.8571264323764991,0.8653846153846145,0.9813793103448276
+1,20,0.01001,0.9742901614173332,0.9952242596418732,1.0,0.9999999999999996,1.0,1.0,0.9413793103448276
+16,8,0.00688,0.973031269505582,0.9939393939393939,1.0,0.9999999999999996,0.9999808377725827,1.0,1.0
+4,24,0.01008,0.9742501297080055,0.995183367768595,1.0,0.9999999999999996,0.9999808377725827,1.0,0.9448275862068969
+4,8,0.00673,0.8263229558150008,0.8440771349862258,1.0,0.9999999999999996,1.0,1.0,0.9937931034482759
+13,4,0.00559,0.8247032517862833,0.8424242424242423,0.8571428571428572,0.8679245283018866,0.8571455946039168,0.8653846153846145,0.9448275862068969
+4,20,0.01103,0.7723854948261649,0.7889807162534435,0.8571428571428572,0.8679245283018866,0.8571264323764991,0.8653846153846145,0.9813793103448276
+13,8,0.00724,0.9989228309792757,0.9950660726584021,0.8571428571428572,0.8679245283018866,0.8571455946039168,0.8653846153846145,0.960689655172414
+1,8,0.00712,0.9341978777926726,0.9542699724517906,1.0,0.9999999999999996,0.9999808377725827,1.0,0.9813793103448276
+1,24,0.00862,0.9789649169473714,0.9999999999999999,1.0,0.9999999999999996,0.9999808377725827,1.0,1.0
+10,4,0.00629,0.9633235799936265,0.984022038567493,1.0,0.9999999999999996,1.0,1.0,0.9641379310344829
+10,8,0.00676,0.6860855572440274,0.7008264462809917,1.0,0.9999999999999996,0.9999808377725827,1.0,0.9420689655172416
+7,20,0.01009,0.9741611118280533,0.9950924371556473,1.0,0.9999999999999996,1.0,1.0,0.9613793103448276
diff --git a/datasets/norm_ext_avrora_4_real_saved_states.csv b/datasets/norm_ext_avrora_4_real_saved_states.csv
new file mode 100644
index 0000000..006d57a
--- /dev/null
+++ b/datasets/norm_ext_avrora_4_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+13,4,0.00748,0.9742817336890537,0.9952156508264463,0.0,0.0,0.0,0.0,0.0006896551724140387
+13,8,0.00721,0.7982744226347712,0.815426997245179,0.5714285714285716,0.5660377358490565,0.5713984593569155,0.5769230769230766,0.03793103448275881
+4,20,0.00863,0.5776707339234499,0.5900826446280991,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+1,24,0.01017,0.06310788282297297,0.06446280991735542,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.01379310344827589
+16,16,0.00884,0.7982744226347712,0.815426997245179,0.1428571428571428,0.15094339622641506,0.14285440539608318,0.14423076923076916,0.038620689655172846
+10,4,0.01688,0.9742959554805254,0.9952301782024793,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.015862068965517562
+7,20,0.00975,0.6343050679617276,0.6479338842975206,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.015862068965517562
+10,8,0.00647,0.5760536635598197,0.5884297520661157,0.1428571428571428,0.15094339622641506,0.14285440539608318,0.14423076923076916,0.0006896551724140387
+16,20,0.00977,0.41909512534928983,0.42809917355371896,0.5714285714285716,0.5660377358490565,0.5714367838117504,0.5769230769230766,0.01379310344827589
+13,16,0.00827,0.6726011919968184,0.687052341597796,0.5714285714285716,0.5660377358490565,0.5714367838117504,0.5769230769230766,0.002068965517241672
+13,20,0.00919,0.5490849330654017,0.5608815426997245,0.22857142857142865,0.24528301886792425,0.23809067566013864,0.24038461538461497,0.026206896551724146
+7,24,0.00995,0.4147785482711306,0.4236914600550964,0.0,0.0,0.0,0.0,0.03724137931034521
+10,16,0.00925,0.1699030021148331,0.17355371900826444,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0006896551724140387
+16,4,0.00825,0.9743170248012242,0.9952517002410468,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.015862068965517562
+16,8,0.0074,0.6758379663891662,0.6903581267217631,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0
+1,20,0.00973,0.19363495821690335,0.19779614325068873,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.01379310344827589
+10,20,0.01006,0.4363535326666649,0.44573002754820934,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+4,24,0.00937,0.4180153226634782,0.42699724517906334,0.5714285714285716,0.5660377358490565,0.5713984593569155,0.5769230769230766,0.026206896551724146
+13,24,0.00965,0.8090619148325384,0.8264462809917354,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.040000000000000036
+4,4,0.00618,0.974233800984464,0.9951666881887051,0.5714285714285716,0.5660377358490565,0.5713984593569155,0.5769230769230766,0.03724137931034521
+13,12,0.00856,0.3457396516714556,0.353168044077135,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.01379310344827589
+7,4,0.0064,0.9744708308423251,0.9954088111225895,0.0,0.0,0.0,0.0,0.03931034482758644
+10,24,0.01073,0.2675303332376435,0.2732782369146005,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+10,12,0.009,0.9742922683494031,0.9952264118457299,0.5714285714285716,0.5660377358490565,0.5713984593569155,0.5769230769230766,0.038620689655172846
+16,24,0.01018,0.6364620396682635,0.6501377410468319,0.5714285714285716,0.5660377358490565,0.5713984593569155,0.5769230769230766,0.03931034482758644
+1,4,0.00756,0.9843586630462551,0.995051545282369,0.0,0.0,0.0,0.0,0.026206896551724146
+16,12,0.00927,0.5846815503859636,0.5972451790633608,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.002068965517241672
+1,12,0.00887,0.9223305829090938,0.9421487603305785,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.01379310344827589
+1,8,0.00863,0.7518876794513549,0.7680440771349861,0.1428571428571428,0.15094339622641506,0.14285440539608318,0.14423076923076916,0.03724137931034521
+4,16,0.00929,0.39104659216906024,0.3994490358126721,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.01379310344827589
+7,16,0.00984,0.0,0.0,0.4285714285714284,0.4339622641509431,0.4285823784156668,0.4326923076923075,0.02206896551724169
+7,12,0.00809,0.70496366859012,0.7201101928374656,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.026206896551724146
+7,8,0.00665,0.9261072586443472,0.9460055096418732,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.03517241379310354
+4,12,0.00803,0.9784250156044656,0.9994490358126721,0.5714285714285716,0.5660377358490565,0.5713984593569155,0.5769230769230766,0.0006896551724140387
+4,8,0.00619,0.9503791160893234,0.9707988980716252,0.20000000000000018,0.18867924528301883,0.19045337830069364,0.19230769230769207,0.03931034482758644
+1,16,0.009,0.13214677942264796,0.13498622589531684,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.002068965517241672
diff --git a/datasets/norm_ext_avrora_8_real_saved_states.csv b/datasets/norm_ext_avrora_8_real_saved_states.csv
new file mode 100644
index 0000000..fa6bc72
--- /dev/null
+++ b/datasets/norm_ext_avrora_8_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+10,24,0.00934,0.17205997382136906,0.17575757575757578,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.03931034482758644
+10,12,0.0092,0.6240574771068662,0.637465564738292,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.03931034482758644
+13,24,0.01206,0.09493045807336864,0.09696969696969693,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0006896551724140387
+13,12,0.00785,0.7233018785933067,0.7388429752066115,0.08571428571428585,0.09433962264150919,0.09521710803663819,0.09615384615384581,0.0006896551724140387
+16,24,0.00897,0.18986091614673728,0.19393939393939397,0.057142857142857384,0.056603773584905426,0.0475989729046109,0.048076923076922906,0.024137931034482918
+16,12,0.00815,0.974149523701669,0.9950806000344352,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.026206896551724146
+7,8,0.00691,0.6165067593014466,0.6297520661157024,0.1428571428571428,0.15094339622641506,0.14285440539608318,0.14423076923076916,0.0006896551724140387
+1,20,0.0102,0.6823088815087741,0.6969696969696969,0.5714285714285716,0.5660377358490565,0.5714367838117504,0.5769230769230766,0.026206896551724146
+16,8,0.00702,0.9742043039354857,0.9951365573347106,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0
+16,16,0.00832,0.4288028148612454,0.4380165289256198,0.22857142857142865,0.24528301886792425,0.23809067566013864,0.24038461538461497,0.03931034482758644
+16,4,0.0072,0.7551244538437025,0.7713498622589531,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.023448275862069323
+16,20,0.00881,0.4180153226634782,0.42699724517906334,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.01379310344827589
+4,24,0.0099,0.6596567280925154,0.6738292011019283,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.01793103448275879
+4,8,0.00757,0.8203893083732114,0.8380165289256198,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.03931034482758644
+7,24,0.00912,0.4929878667049426,0.5035812672176307,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0
+1,8,0.0069,0.9741827078817695,0.995114497245179,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+10,8,0.00674,0.7783191422679543,0.7950413223140496,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.03724137931034521
+7,20,0.00884,0.34843652472089737,0.3559228650137741,0.5714285714285716,0.5660377358490565,0.5713984593569155,0.5769230769230766,0.03724137931034521
+10,16,0.00927,0.6531831793078202,0.6672176308539944,0.1428571428571428,0.15094339622641506,0.14285440539608318,0.14423076923076916,0.03931034482758644
+10,4,0.00637,0.8586854324083024,0.8771349862258953,0.5714285714285716,0.5660377358490565,0.5713984593569155,0.5769230769230766,0.002068965517241672
+10,20,0.01013,0.7108973160319094,0.7261707988980716,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+4,20,0.01022,0.8489751092312595,0.8672176308539944,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.015862068965517562
+13,8,0.00762,0.7427198912823052,0.7586776859504132,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.01379310344827589
+13,16,0.00898,0.562029396969705,0.5741046831955923,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.03724137931034521
+13,4,0.00683,0.9743344069908006,0.995269455922865,0.5714285714285716,0.5660377358490565,0.5713984593569155,0.5769230769230766,0.026206896551724146
+13,20,0.00938,0.11272876673364951,0.11515151515151512,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0006896551724140387
+1,24,0.0101,0.36947160777352583,0.37741046831955927,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.0006896551724140387
+1,4,0.00704,0.8851142615598144,0.9041322314049586,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.03931034482758644
+4,4,0.00703,0.8629993758213743,0.8815426997245178,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.026206896551724146
+7,4,0.00738,0.8797205154609309,0.8986225895316804,0.5714285714285716,0.5660377358490565,0.5713984593569155,0.5769230769230766,0.03931034482758644
+4,12,0.00842,0.5685003120893128,0.5807162534435262,0.4285714285714284,0.4339622641509431,0.4285440539608327,0.4326923076923075,0.03931034482758644
+1,16,0.00855,0.5080919359808691,0.5190082644628099,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.026206896551724146
+7,12,0.00848,0.6628908688197757,0.6771349862258953,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0006896551724140387
+7,16,0.00893,0.2675303332376435,0.2732782369146005,0.4285714285714284,0.4339622641509431,0.42856321618825,0.4326923076923075,0.0006896551724140387
+1,12,0.00826,0.6806918111451439,0.6953168044077134,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.026206896551724146
+4,16,0.00829,0.7378660465263274,0.7537190082644627,0.5714285714285716,0.5660377358490565,0.5714176215843327,0.5769230769230766,0.03931034482758644
diff --git a/datasets/norm_ext_avrora_real_saved_states.csv b/datasets/norm_ext_avrora_real_saved_states.csv
new file mode 100644
index 0000000..d9b45ed
--- /dev/null
+++ b/datasets/norm_ext_avrora_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+10,20,0.01203,0.034202429857518424,0.03420146054264461,0.0,0.0,0.0,0.0,0.9874961895715635
+10,16,0.00983,0.32716991850214694,0.32716397124345553,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9931013459705178
+7,24,0.01115,0.07830631483472705,0.07830334387394944,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9825377819878731
+16,8,0.00665,0.38342319215151865,0.3834163734517526,0.0,0.0,0.0,0.0,0.9816754502341878
+1,20,0.00989,0.40547403594337206,0.40546731511740497,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9989220853078935
+13,20,0.00954,0.6273382656525954,0.6273267894269285,0.0,0.0,0.0,0.0,0.9874961895715635
+16,4,0.00755,0.7195936344375651,0.7195807290485356,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9816754502341878
+13,16,0.01032,0.022053041185355227,0.022050941665652357,0.0,0.0,0.0,0.0,0.9816754502341878
+4,24,0.01006,0.5247309760800402,0.5247224077989947,0.0,0.0,0.0,0.0,0.9883585213252486
+13,8,0.0078,0.25651492784113517,0.2565109540698345,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9997844170615786
+4,20,0.01106,0.1939617270217342,0.19395828281420813,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9816754502341878
+16,20,0.01081,0.19756325497139515,0.19755843655553917,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9816754502341878
+13,4,0.00627,0.6979910589201052,0.6979798066005496,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.98857410426367
+16,16,0.00939,0.3244693218882767,0.3244638559374573,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9920234312784111
+1,24,0.01077,0.39287418160331355,0.3928667770227465,0.0,0.0,0.0,0.0,0.9997844170615786
+7,20,0.00937,0.5886355739031273,0.5886251367076202,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9892208530789339
+10,8,0.00817,0.31636972944016795,0.3163635100194625,0.0,0.0,0.0,0.0,0.9997844170615786
+10,4,0.00832,0.6912406660821806,0.6912295183355539,0.0,0.0,0.0,0.0,0.9825377819878731
+16,12,0.00863,0.3991741087733428,0.3991670460700758,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9997844170615786
+16,24,0.01444,0.0,0.0,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9997844170615786
+7,4,0.00722,0.7200419027119584,0.7200307482662021,0.0,0.0,0.0,0.0,0.9825377819878731
+4,4,0.00742,0.5562328093236883,0.5562237530356411,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9816754502341878
+10,12,0.00832,0.1278091956461741,0.12780545781725083,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9816754502341878
+10,24,0.01179,0.9270539497416466,0.9270395883927351,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9987065023694721
+1,4,0.0061,0.37172207175374894,0.37171587379242677,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,1.0
+13,12,0.00843,0.23221395310330695,0.23220991631585008,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9997844170615786
+13,24,0.01022,0.20116258552755417,0.20115859029687022,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9892208530789339
+7,12,0.01047,0.2763178380805156,0.276311799647155,0.0,0.0,0.0,0.0,0.9939636777242031
+1,8,0.00792,0.600336694300897,0.600325636366946,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9816754502341878
+4,12,0.009,0.1593110288898223,0.15930680305389722,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9997844170615786
+1,16,0.01116,0.5107797247362955,0.5107718120513371,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9997844170615786
+4,8,0.00762,0.24166494255510185,0.241660319886844,0.0,0.0,0.0,0.0,0.9883585213252486
+1,12,0.01112,0.34112116984589147,0.3411145669911132,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9816754502341878
+4,16,0.00969,0.33797010756412593,0.33796443246744856,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.98857410426367
+7,8,0.00692,0.3150183324364818,0.3150134523664634,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9872806066331421
+7,16,0.00889,0.4626282409285345,0.46261975576103476,0.028735632183908066,0.02839506172839501,0.029228366275917794,0.029469548133595314,0.9997844170615786
diff --git a/datasets/norm_ext_h2_real_saved_states.csv b/datasets/norm_ext_h2_real_saved_states.csv
new file mode 100644
index 0000000..3efb23a
--- /dev/null
+++ b/datasets/norm_ext_h2_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+10,4,0.21015,0.9999569137376163,0.9883834936062841,0.983277591973244,0.9814814814814815,0.9999972256817972,1.0,0.13972469196431841
+7,20,0.22059,0.9999585109083665,0.9883860209279964,0.9799331103678929,0.9812768569674647,0.999997114709069,1.0,0.13949531171783813
+10,8,0.14916,0.9999336306349882,0.9883830137625569,0.9999999999999999,0.9997953754859833,0.999999001245447,1.0,0.14678460203173985
+1,24,0.26639,0.9999890592705145,0.9884343275125194,0.983277591973244,0.9814814814814815,0.9999987792999906,1.0,0.13971067907332105
+13,4,0.20498,0.9999556285314418,0.9883814617612167,0.9799331103678929,0.9812768569674647,0.9999988902727187,1.0,0.1392734768742026
+13,8,0.14861,0.9999572476715284,0.9883840216515078,0.983277591973244,0.9828115408225905,0.999997114709069,1.0,0.13933879850454428
+4,20,0.17963,0.9999175996102782,0.9883876649898525,0.9999999999999999,1.0,0.999997114709069,1.0,0.14720046151995456
+1,4,0.18607,0.9999905465945831,0.9884366776611632,0.9799331103678929,0.9812768569674647,0.9999976695727096,1.0,0.13945025488370807
+4,24,0.278,0.999956116250708,0.9883822325509142,0.9866220735785954,0.9858809085328423,0.999999001245447,1.0,0.13943688874152596
+16,4,0.18847,0.999933727300068,0.988383185290405,0.9999999999999999,0.9997953754859833,0.9999972256817972,1.0,0.14678869810756984
+4,4,0.19791,0.9999534535671465,0.988378023822042,0.9799331103678929,0.9812768569674647,0.9999993341636314,1.0,0.13927175221069524
+16,8,0.16909,0.9999648358802921,0.9883960242584028,0.9866220735785954,0.986597094331901,0.999997114709069,1.0,0.13930840131022684
+1,20,0.18954,0.9999794125349379,0.9884644586588516,0.9999999999999999,1.0,0.9999987792999906,1.0,0.14725004559579147
+7,24,0.25286,0.9999377960211538,0.9883904246340934,0.9999999999999999,0.9997953754859833,0.9999975585999815,1.0,0.14672617905542765
+7,4,0.18653,0.9999353574248226,0.9883860860651539,0.9999999999999999,0.9998976877429916,0.9999972256817972,1.0,0.1468852792639826
+7,8,0.16755,0.9999560701151018,0.9883821613342886,0.983277591973244,0.9819930427665234,0.999999001245447,1.0,0.13939829939554854
+10,20,0.20235,0.9999385100245841,0.988391695242913,0.9999999999999999,0.9997953754859833,0.9999977805454375,1.0,0.14679365651515353
+10,16,0.17939,0.9999585680286409,0.9883861125542647,0.983277591973244,0.9814814814814815,0.999999001245447,1.0,0.1398266626941917
+4,8,0.15689,0.9999587899189377,0.9883864634264199,0.9866220735785954,0.9856762840188255,0.9999988902727187,1.0,0.13996786951885767
+13,20,0.22224,0.9999569027529481,0.9883834779733662,0.9899665551839466,0.9881317781870268,0.9999975585999815,1.0,0.1393532425614185
+13,16,0.18425,0.9999603936804888,0.9883889981303434,0.9899665551839466,0.9893595252711275,0.999999001245447,1.0,0.139329959604069
+1,8,0.12919,0.9999654224615717,0.9884821920328665,0.9999999999999999,0.9998976877429916,0.9999972256817972,1.0,0.15737640737931774
+16,20,0.20235,0.9999352827290792,0.988385954053848,0.9999999999999999,0.9998976877429916,0.999999001245447,1.0,0.1468458275862515
+16,16,0.17439,0.9999553605055388,0.9883810405409313,0.983277591973244,0.9822999795375486,0.9999987792999906,1.0,0.13944378739555544
+16,12,0.17112,0.9999577705417326,0.9883848501961516,0.983277591973244,0.9822999795375486,0.9999985573545346,1.0,0.13961345116809304
+7,16,0.1788,0.9999555164878267,0.988381285022396,0.9799331103678929,0.9812768569674647,0.999997114709069,1.0,0.13932500119648528
+16,24,0.28523,0.9999594511959609,0.9883875064894359,0.9799331103678929,0.9812768569674647,0.9999976695727096,1.0,0.13949832987897604
+4,16,0.13649,0.9999192868553072,0.9883909965383366,0.9999999999999999,0.9997953754859833,1.0,1.0,0.14673609587059505
+1,12,0.15362,0.999997745946094,0.988448062333557,0.983277591973244,0.981379169224473,0.9999992231909033,1.0,0.1402957711681965
+10,12,0.19358,0.9999560349641636,1.0,0.9999999999999999,1.0,1.0,1.0,0.15737640737931774
+1,16,0.16398,1.0,0.988451627073065,0.983277591973244,0.9844485369347248,0.999997114709069,1.0,0.13929848449505947
+4,12,0.18579,0.9999596423291869,0.9883878117655809,0.983277591973244,0.9839369756496829,0.9999986683272627,1.0,0.1397477593387295
+10,24,0.28042,0.9999579309178878,0.9883851033625706,0.983277591973244,0.9824022917945571,0.999997114709069,1.0,0.13959253962306617
+13,12,0.16804,0.9999596774801249,0.9883878643095546,0.983277591973244,0.9814814814814815,0.9999972256817972,1.0,0.13976328131029583
+7,12,0.16018,0.9999580803093747,0.9883853391590809,0.9799331103678929,0.9812768569674647,0.9999988902727187,1.0,0.13933793617279058
+13,24,0.27699,0.9999597455850675,0.988387974174227,0.9966555183946487,0.9953959484346225,0.9999987792999906,1.0,0.13936057238132482
diff --git a/datasets/norm_ext_kafka_16_real_saved_states.csv b/datasets/norm_ext_kafka_16_real_saved_states.csv
new file mode 100644
index 0000000..c3865fe
--- /dev/null
+++ b/datasets/norm_ext_kafka_16_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+7,20,0.01131,0.8078110255495372,0.729143131835116,0.06572769953051694,0.698227410289667,0.700512000541368,0.04458598726114649,0.0016539557107417835
+10,8,0.01266,0.990236946153035,0.9996194367664143,0.05164319248826299,0.719412019022914,0.7219576353495966,0.02972399150743099,0.2462249992342791
+16,16,0.01148,0.9560845644382834,0.9465528982894684,0.164319248826291,0.740164288802421,0.7428467195396984,0.10191082802547768,0.0007657202364539373
+10,4,0.00958,0.9864205076030077,0.991033729920282,0.23004694835680795,0.7682663207955037,0.7708729255692714,0.13588110403397025,0.0008576066648284808
+16,20,0.01116,0.7371712735317855,0.6255658374394104,0.15492957746478897,0.7380025940337224,0.7407272290329423,0.09554140127388533,0.0016539557107417835
+4,4,0.00951,0.9865454986555607,0.9912170011617194,0.10798122065727744,0.7124945957630783,0.7150486862499028,0.06581740976645434,0.0013170388067011984
+13,8,0.01375,0.9895721494800099,0.9981572727636903,0.13615023474178445,0.7565931690445308,0.7591385134329109,0.07855626326963905,0.2468375754234433
+4,20,0.01308,0.4343295643863746,0.18151664463405837,0.29577464788732444,0.799827064418504,0.802458366066289,0.17622080679405516,0.0008269778553700036
+13,4,0.01102,0.9901294866323778,0.9993830869687137,0.11267605633802846,0.7431906614785991,0.7457834675402588,0.06369426751592355,0.2457043094734903
+1,24,0.01219,0.8448794102717238,0.7834955734487041,0.15023474178403795,0.7328145265888456,0.735533479577889,0.09341825902335454,0.001592698091824829
+7,4,0.01079,0.9893476655496246,0.9976635420422225,0.11737089201877948,0.7470817120622567,0.7496047102488166,0.06581740976645434,0.24518361971270153
+16,8,0.0114,0.9900247577905625,0.999152746064175,0.018779342723004966,0.7025507998270645,0.7050897703567172,0.010615711252653925,0.24757266685043966
+1,20,0.01626,0.989587175726765,0.9981903216760806,0.08920187793427248,0.7315175097276264,0.7341718175433605,0.05095541401273884,0.24754203804098118
+10,16,0.01015,0.9861739405539822,0.9906721948483757,0.10798122065727744,0.7215737137916126,0.7243139743657036,0.06794055201698512,0.0011638947594105886
+16,4,0.00913,0.9866520484052781,0.9913732323839283,0.18309859154929597,0.7492434068309554,0.752051277268486,0.11040339702760082,0.0006432049986209165
+10,20,0.01129,0.886144215905856,0.8440011216600569,0.164319248826291,0.746649373108517,0.7492221088106343,0.09766454352441611,0.0012557811877851321
+4,24,0.01105,0.5119633512573691,0.29534911669270525,0.24413145539906145,0.7782101167315175,0.7808808595605461,0.1443736730360934,0.0004288033324142404
+13,16,0.00996,0.8903406368178016,0.8501542282578216,0.3615023474178405,0.8331171638564635,0.8360448728153869,0.21019108280254772,0.0014701828539926964
+7,24,0.01094,0.5525287534061769,0.3548291471377639,0.38497652582159647,0.8439256376999568,0.8468479410880543,0.22505307855626322,0.0017458421391154388
+13,20,0.01069,0.667230924999358,0.5230140608099988,0.27699530516431947,0.7937743190661478,0.7966265137591197,0.16560509554140124,0.0009801219026615016
+1,4,0.01128,0.9864396319170595,0.9910617714217042,0.15023474178403795,0.7392996108949416,0.7420411743348179,0.09129511677282376,0.0011638947594105886
+10,24,0.01236,0.932304845937258,0.9116852942354685,0.32863849765258246,0.8149589277993946,0.8179758475250849,0.195329087048832,0.0005513185702472612
+10,12,0.01163,0.9865823812612322,0.9912710812001763,0.15023474178403795,0.7414613056636402,0.7441706419765832,0.09129511677282376,0.0003369169040396969
+13,24,0.01553,0.9862251663951925,0.9907473060128991,0.34741784037558743,0.8236057068741892,0.8266928270038534,0.20382165605095537,0.0007657202364539373
+13,12,0.00879,0.9863781609076072,0.9909716380242759,0.23943661971830998,0.7717250324254216,0.7744738037306675,0.1422505307855626,0.00039817452295576317
+16,24,0.01125,0.5504305429502041,0.3517525938388816,0.20187793427230094,0.7565931690445308,0.7592391523599611,0.12101910828025475,0.0005819473797048502
+16,12,0.01296,0.9897360721718829,0.998517806353403,0.0,0.6926070038910505,0.6950935486543663,0.0,0.2453980213789091
+7,16,0.00948,0.9784654759686602,0.9793694668108801,0.22065727699530546,0.7661046260268051,0.7687039831759475,0.13163481953290868,0.0
+1,12,0.01417,0.9896154059463503,0.9982524135720867,0.06572769953051694,0.7224383916990921,0.7250882868001203,0.03609341825902335,0.24696009066127544
+4,16,0.01126,0.914120355318827,0.8850218323118215,0.15023474178403795,0.7427583225248594,0.7455565961659172,0.09341825902335454,6.125761891606629e-05
+4,12,0.01354,0.9900320427881939,0.9991687697792734,0.07511737089201898,0.7276264591439688,0.7303392963343571,0.04033970276008492,0.2466844313761527
+1,16,0.01083,0.9861780386212791,0.9906782037415375,0.17840375586854496,0.7462170341547772,0.7489431828188529,0.10615711252653925,0.00018377285674908705
+7,12,0.01051,0.986477197533947,0.9911168529423547,0.1737089201877935,0.7457846952010375,0.7484239380098914,0.10615711252653925,0.0016539557107417835
+1,8,0.01394,0.9897233217185,0.9984897648519809,0.07981220657277,0.7315175097276264,0.7341019775982953,0.0424628450106157,0.24858341756255875
+7,8,0.01093,0.9897242328554623,0.9984917678163683,0.06572769953051694,0.7263294422827496,0.7287806943305146,0.03609341825902335,0.2473582651842321
+4,8,0.02374,0.9899172969038829,0.9989163962664744,0.09859154929577496,0.7418936446173799,0.7444100932168061,0.05520169851380041,0.24545927899782516
diff --git a/datasets/norm_ext_kafka_2_real_saved_states.csv b/datasets/norm_ext_kafka_2_real_saved_states.csv
new file mode 100644
index 0000000..d752153
--- /dev/null
+++ b/datasets/norm_ext_kafka_2_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+16,4,0.01004,0.9926787112507247,0.9907061771421705,0.07042253521126751,0.01599654128837008,0.01626706794992866,0.9808917197452227,0.6074611779840113
+16,8,0.00845,0.9913010776277764,0.9906943406241238,0.07042253521126751,0.01599654128837008,0.01626706794992866,0.9808917197452227,0.5166161291310605
+1,20,0.00875,0.9944960907170034,0.9907217902495694,0.07511737089201898,0.017293558149589272,0.01616816417679312,0.9808917197452227,1.0
+4,24,0.01219,0.9941372297939328,0.9907129952329448,0.13145539906103298,0.02550799827064415,0.018432973823901855,0.9363057324840764,0.7176023767956137
+7,24,0.0129,0.9925810829935126,0.9907007400953411,0.12676056338028197,0.02507565931690442,0.018432540035423106,0.9363057324840764,0.5383013262274492
+10,4,0.00858,0.9916409904536889,0.9906972609462004,0.10798122065727744,0.022481625594466037,0.01843384140085913,0.9363057324840764,0.5843364268430875
+7,20,0.01017,0.9928648154148528,0.9907173777190241,0.13615023474178445,0.02680501513186334,0.018432973823901855,0.9363057324840764,0.6610003369169037
+10,8,0.0084,0.9928592543375311,0.9907077274366062,0.07981220657277,0.017725897103329002,0.01626706794992866,0.9808917197452227,0.8046800820852091
+13,4,0.01048,0.9925024943569614,0.9907046629010936,0.07511737089201898,0.01686121919584954,0.01626706794992866,0.9808917197452227,0.731538485099084
+13,8,0.0094,0.9920404372692447,0.990700693025678,0.11737089201877948,0.023346303501945498,0.018433407612380492,0.9363057324840764,0.5330944286195596
+4,20,0.00978,0.9924430382305967,0.9907086508031887,0.13145539906103298,0.02594033722438388,0.01843167245846583,0.9363057324840764,0.6857177861496515
+1,24,0.01254,0.9924421202635222,0.9906996454753034,0.1220657276995305,0.02464332036316469,0.018432540035423106,0.9363057324840764,0.5517473735795884
+1,8,0.00878,0.9917892380381514,0.9907025657973801,0.023474178403755985,0.0,0.0,0.9787685774946921,0.65049465527275
+7,8,0.00843,0.9923002356115491,0.9907073218363177,0.07042253521126751,0.01599654128837008,0.016133894886978528,0.9193205944798302,0.6457778186161898
+4,8,0.00925,0.9927343766648399,0.9907066548491767,0.1220657276995305,0.02464332036316469,0.018433407612380492,0.9363057324840764,0.6230818708076811
+4,12,0.00744,0.9931966618783028,0.9907055882706406,0.13145539906103298,0.02594033722438388,0.018361398724922096,0.9363057324840764,0.7050139361083039
+4,4,0.00891,0.991498126363632,0.9906960341305132,0.11267605633802846,0.022913964548205767,0.018315850934662314,0.9363057324840764,0.505222212012618
+1,16,0.00765,0.9917190463414914,0.9907019128309899,0.04694835680751197,0.0077821011673151474,0.008025086855298125,0.9808917197452227,0.6034181751355323
+16,16,0.0098,0.9945893217480061,0.9907225914353243,0.13145539906103298,0.02594033722438388,0.018432973823901855,0.9363057324840764,0.7194094765536461
+7,12,0.01,0.9922759627589501,0.9906983375395585,0.1220657276995305,0.02464332036316469,0.01842993730455117,0.9363057324840764,0.5616711078440382
+16,20,0.01,0.9925663039968178,0.9907006239234066,0.1220657276995305,0.02464332036316469,0.018432973823901855,0.9363057324840764,0.5340745505222211
+7,4,0.01013,0.9920678724637745,0.9907009283739935,0.1220657276995305,0.02421098140942496,0.01843384140085913,0.9363057324840764,0.6002327789518818
+13,16,0.00959,0.9943063269787792,0.9907201608380403,0.13145539906103298,0.02550799827064415,0.018432973823901855,0.9363057324840764,0.7497626267266986
+13,20,0.01013,0.992835506037546,0.9907123042102312,0.1220657276995305,0.02464332036316469,0.018433407612380492,0.9363057324840764,0.727127936537106
+7,16,0.00817,0.9922335026836877,0.9907023514801907,0.1220657276995305,0.02421098140942496,0.018432973823901855,0.9363057324840764,0.5895126956415204
+10,16,0.00858,0.9928121265636176,0.9907073228377999,0.11737089201877948,0.02377864245568523,0.01841779122714854,0.9363057324840764,0.7073723544365826
+1,12,0.00722,0.9921777225236883,0.9907018727717021,0.05164319248826299,0.008646779074794608,0.008025086855298125,0.9808917197452227,0.625991607706208
+10,20,0.00862,0.9926018724889093,0.9907055161639227,0.11737089201877948,0.02377864245568523,0.018432973823901855,0.9363057324840764,0.573493828294894
+1,4,0.00998,0.9917730383781271,0.9906983956255258,0.04694835680751197,0.0077821011673151474,0.008025086855298125,0.9808917197452227,0.5903703023063489
+4,16,0.00973,0.9927516800709895,0.9907068040700236,0.12676056338028197,0.02507565931690442,0.018429503516072476,0.9363057324840764,0.6460228490918549
+13,24,0.01119,0.9928999194593174,0.990712903096583,0.1455399061032865,0.028102031993082532,0.018432973823901855,0.9363057324840764,0.9691874176850748
+13,12,0.00881,0.993316758472481,0.9907116582542163,0.07042253521126751,0.01599654128837008,0.01626706794992866,0.9808917197452227,0.6934056173236538
+10,24,0.01088,0.9953811803635915,0.990722791731763,0.15023474178403795,0.02896670990056205,0.018357494628614135,0.9363057324840764,0.8766577843119236
+10,12,0.00947,0.9928536659397607,0.9907028862716821,0.11267605633802846,0.022913964548205767,0.018433407612380492,0.9363057324840764,0.6325155441207997
+16,24,0.01142,0.9947641111483276,0.9907179325401594,0.14084507042253547,0.02723735408560307,0.018430371093029807,0.9363057324840764,0.9205488682654899
+16,12,0.0082,0.9941158815953612,0.9907185244161358,0.08450704225352146,0.018158236057068733,0.01626706794992866,0.9808917197452227,0.7482311862537907
diff --git a/datasets/norm_ext_kafka_32_real_saved_states.csv b/datasets/norm_ext_kafka_32_real_saved_states.csv
new file mode 100644
index 0000000..d01d19a
--- /dev/null
+++ b/datasets/norm_ext_kafka_32_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+1,24,0.01056,0.9865700870593417,0.9912530545206907,0.6009389671361505,0.9022913964548206,0.9016740331180151,0.3524416135881103,0.2537290575515323
+1,4,0.01044,0.46860033516726407,0.6112085887112928,0.5446009389671365,0.9035884133160398,0.9030738685386663,0.3121019108280254,0.2524120187448311
+13,8,0.00775,0.7777366756805935,0.8378480150622922,0.643192488262911,0.9563337656722871,0.9561305373641535,0.3673036093418258,0.2527183068394123
+4,20,0.012,0.7469629223263253,0.639923086167528,0.690140845070423,0.9416342412451361,0.9411865242741526,0.4033970276008494,0.2537596863609908
+13,4,0.00893,0.4413235992396173,0.19177182229699952,0.6760563380281694,0.9697362732382188,0.9694625924674365,0.3864118895966029,0.25299396612453684
+7,20,0.01103,0.6357577681597657,0.4768657613267636,0.6995305164319254,0.9437959360138347,0.9433290055702777,0.40764331210191074,0.2527489356488708
+10,8,0.01033,0.6861148191031134,0.5507030404999399,0.5446009389671365,0.9061824470384782,0.9058466444942916,0.3121019108280254,0.2524426475542896
+10,4,0.01045,0.9274090215399882,0.9045066698714097,0.615023474178404,0.9390402075226977,0.9387898429295296,0.3545647558386411,0.25262642041103867
+7,24,0.01067,0.9862422416755959,0.9907723430677403,0.6619718309859159,0.9282317336792044,0.9279629162905358,0.3864118895966029,0.25443352016907106
+7,4,0.00974,0.8169032708587528,0.7424748627969395,0.6197183098591554,0.9446606139213142,0.9444542528839341,0.3524416135881103,0.25464792183527774
+4,24,0.01253,0.9862811733149157,0.9908294275527781,0.6572769953051645,0.9265023778642455,0.9260364616567855,0.3842887473460721,0.2534227694569511
+4,4,0.01098,0.9863091767747774,0.9907603252814166,0.5774647887323949,0.9265023778642455,0.9262681047043926,0.3312101910828025,0.25495420992985984
+16,8,0.00962,0.9862039930474923,0.9906832111525057,0.6197183098591554,0.9455252918287936,0.9453626059582583,0.3524416135881103,0.2525651627921217
+1,20,0.00819,0.9864881257134053,0.9908915194487842,0.4694835680751175,0.8439256376999568,0.8431989124055264,0.2760084925690023,0.25333088302857654
+16,4,0.0104,0.54483531506761,0.34354845170852866,0.690140845070423,0.9736273238218763,0.9733350222164769,0.39278131634819546,0.2525957916015802
+16,12,0.01012,0.24059479895155056,0.44404919280535193,0.7323943661971835,0.9974059662775615,0.9972319957176401,0.41825902335456466,0.253361511838035
+16,24,0.01299,0.9863125918308581,0.9908754957336858,0.7605633802816905,0.9718979680069174,0.9716315348607603,0.4437367303609341,0.255076725167692
+4,8,0.01187,0.3105351474839779,0.0,0.5962441314553995,0.9312581063553825,0.9308740707708552,0.3418259023354564,0.2533921406474926
+7,8,0.01052,0.5861001207017422,0.6973520810799985,0.5962441314553995,0.9355814958927798,0.9352371152892653,0.33970276008492584,0.253361511838035
+10,12,0.00915,0.0,0.26766013700276414,0.746478873239437,0.9654128837008215,0.9650448906007145,0.43524416135881117,0.25262642041103867
+10,24,0.01309,0.9867872846260732,0.9915715258582702,0.666666666666667,0.9295287505404236,0.9292395557832462,0.38853503184713367,0.2523813899353726
+13,12,0.01041,0.9862067250923569,0.990685214116893,0.591549295774648,0.9360138348465196,0.9358609031215852,0.33757961783439483,0.25498483873931743
+13,24,0.01119,0.6427518030130084,0.48712093898970477,0.6995305164319254,0.9455252918287936,0.9452897294938425,0.4097664543524415,0.25296333731507836
+1,8,0.00987,0.9863583535823393,0.9907963786403878,0.5117370892018784,0.8979680069174233,0.8976801425949488,0.29299363057324834,0.25250390517320564
+4,16,0.01235,0.6399541890717113,0.4830188679245283,0.6338028169014085,0.9165585819282317,0.9164050560649919,0.3715498938428876,0.25235076112591415
+10,20,0.00912,0.5937935590403092,0.4153346953491167,0.7042253521126765,0.9476869865974923,0.9472075083580196,0.4118895966029723,0.2532696254096596
+1,12,0.01053,0.9106233378922056,0.9352722028602332,0.7089201877934275,0.9801124081279723,0.9800830357905859,0.40552016985137995,0.25415786088394743
+10,16,0.00944,0.987189578232378,0.9921613988703281,0.6854460093896715,0.9381755296152182,0.9379938410711799,0.3991507430997876,0.2540966032650305
+7,16,0.00999,0.9864184585693593,0.9910307254737011,0.6760563380281694,0.9342844790315606,0.9340489686462023,0.394904458598726,0.25424974731232197
+13,20,0.01159,0.6350583646744414,0.4758402435604695,0.666666666666667,0.9299610894941633,0.9294560162341001,0.38853503184713367,0.25253453398266323
+13,16,0.01176,0.9197155832014211,0.8932259744421744,0.826291079812207,0.9999999999999999,1.0,0.4819532908704882,0.25513798278660893
+16,20,0.0109,0.9868029938840445,0.9915945599487241,0.6244131455399065,0.9126675313445741,0.9122953440181221,0.3673036093418258,0.2527795644583293
+7,12,0.01076,0.9863993342553075,0.9908264231061972,0.727699530516432,0.9900562040639861,0.9901169970905805,0.4161358811040339,0.25464792183527774
+16,16,0.01074,0.6259661193652258,0.462508512598646,0.7323943661971835,0.9584954604409858,0.9580886585568464,0.4267515923566878,0.25247327636374717
+1,16,0.00903,0.6994034853242747,0.7804190201498218,0.690140845070423,0.9412019022913963,0.9409783058043935,0.4033970276008494,0.2535146558853256
+4,12,0.00932,0.8113080429761585,0.862460441453351,0.5962441314553995,0.9303934284479031,0.930140534453433,0.3418259023354564,0.2545560354069032
diff --git a/datasets/norm_ext_kafka_4_real_saved_states.csv b/datasets/norm_ext_kafka_4_real_saved_states.csv
new file mode 100644
index 0000000..30b17aa
--- /dev/null
+++ b/datasets/norm_ext_kafka_4_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+1,4,0.00832,0.993527785715886,0.9906765412810961,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.46981530827896734
+4,4,0.00994,0.9963286781110205,0.9906865681208188,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.4529388342675116
+7,4,0.01153,0.9972373562329692,0.9906898209349838,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.5092039572421818
+10,4,0.01063,0.9965043485958109,0.9906871960501542,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.45627737449845274
+10,8,0.0095,0.9978640873248965,0.9906920642550976,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.6272780177034516
+7,20,0.01,0.9987077427790689,0.9906950837239114,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.6981530827896716
+13,4,0.01154,0.9957177928793076,0.9906843808837079,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.4560017152133291
+4,20,0.01109,0.9972026592631894,0.9906896967511918,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.5762810499555879
+13,8,0.00918,0.99880090550895,0.9906954172174819,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.6234494165211792
+1,24,0.01233,0.9973583858204687,0.9906902535752914,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.5726055928206071
+16,4,0.0099,0.996134976130124,0.9906858740936586,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.6363441453030712
+1,20,0.01184,0.9986528286772914,0.9906948874334014,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.6124536739256943
+16,8,0.01106,0.997791688135986,0.9906918048712094,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.5109497993812973
+4,24,0.0106,0.9972870794495039,0.9906899981973321,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.5392201905111946
+7,24,0.01324,0.997785131228311,0.9906917818371189,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.681705412110631
+13,20,0.00908,0.9951697446794793,0.9906824189800906,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.463842690434622
+13,16,0.01034,0.9976173836736277,0.9906911809478027,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.6174155410579187
+10,20,0.00971,0.9974510021413768,0.9906905850658976,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.5593126895157585
+10,16,0.00965,1.0,0.9906997105716461,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.714171950136298
+16,20,0.00995,0.9996481126214463,0.9906984507070464,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.5536769885754538
+16,16,0.01067,0.9988380613191078,0.9906955504146137,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.6571717357346314
+7,8,0.0102,0.9957989346117847,0.9906846713135441,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.5123893534258315
+7,16,0.01029,0.9969412025696521,0.9906887603653407,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.48191368801494594
+16,12,0.00967,0.9969024075325756,0.9906886211593158,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.47091794541946186
+1,12,0.00888,0.9960786960059144,0.9906856727957377,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.4889583141903273
+4,8,0.01048,0.9966843903523847,0.990687841004687,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.5132469600906608
+4,16,0.01037,0.9964120054793892,0.9906868655610304,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.5203834726944159
+16,24,0.0108,0.9955820102495395,0.990683895164844,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.47649238874084965
+13,12,0.00936,0.9982588678078237,0.9906934773464727,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.527642500536003
+4,12,0.01104,0.9981553233074573,0.9906931067980611,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.5820086373242663
+1,8,0.00981,0.9968625196775532,0.9906884789488443,0.807511737089202,0.3069606571552097,0.3079898198519827,1.0,0.5475512266838178
+1,16,0.00921,0.9982725280321464,0.9906935264191002,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.6710772152286442
+13,24,0.00991,0.9968559627698783,0.9906884549132716,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.5715948421084862
+10,12,0.00895,0.9967925793290208,0.9906882285782959,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.5231094367361937
+7,12,0.01015,0.9971133213961187,0.9906893762768898,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.49131673251860697
+10,24,0.01101,0.9989101873035319,0.9906958087970196,0.7417840375586859,0.3069606571552097,0.3079898198519827,0.9214437367303607,0.6954883763668107
diff --git a/datasets/norm_ext_kafka_8_real_saved_states.csv b/datasets/norm_ext_kafka_8_real_saved_states.csv
new file mode 100644
index 0000000..d58f894
--- /dev/null
+++ b/datasets/norm_ext_kafka_8_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+1,8,0.0107,0.9863139578532903,0.9908774986980732,0.9061032863849765,0.735408560311284,0.737983083116909,0.6433121019108281,0.0004288033324142404
+7,24,0.01116,0.5609215952300683,0.3671353603332933,0.892018779342723,0.730652831820147,0.7333007702782015,0.6348195329087047,0.0008269778553700036
+16,8,0.0087,0.9490905295850407,0.9362977206265273,0.995305164319249,0.7661046260268051,0.7688371562388978,0.6985138004246283,0.0011638947594105886
+1,20,0.0099,0.7056981166921932,0.5794175379561751,0.8403755868544605,0.712926934716818,0.7155197805377329,0.602972399150743,0.0016539557107417835
+16,4,0.01132,0.9898517278271337,0.9987721828305893,0.8732394366197189,0.7237354085603113,0.7262256801911793,0.6220806794055203,0.24597996875861394
+4,24,0.01018,0.5819036997897965,0.39790089332211676,0.938967136150235,0.7470817120622567,0.7497569700048281,0.664543524416136,0.0006738338080793937
+13,8,0.01169,0.9962169374760605,0.9906717652125145,0.7934272300469489,0.696498054474708,0.6990557726184903,0.5732484076433122,0.6567429324022171
+4,20,0.01165,0.7763378687099449,0.6829948323518809,0.835680751173709,0.7120622568093385,0.7144110171862658,0.6008492569002124,9.188642837365535e-05
+13,4,0.01212,0.9900434272191445,0.9991938068341145,0.915492957746479,0.7392996108949416,0.7418212435761349,0.6496815286624202,0.2455511654261997
+7,8,0.00824,0.9865673550144771,0.9912490485919161,0.8779342723004699,0.7263294422827496,0.729009300858771,0.6263269639065818,0.001408925235075742
+1,24,0.01001,0.6805195912205193,0.542498898369587,0.8638497652582164,0.7211413748378729,0.7238519896359257,0.6178343949044585,0.0005206897607887839
+7,20,0.0115,0.9863180559205872,0.990883507591235,0.8685446009389675,0.7228707306528318,0.7256014585703807,0.6220806794055203,0.0011332659499521114
+10,8,0.01245,0.9899933392746203,0.9990836437928133,0.7934272300469489,0.696498054474708,0.69898116100016,0.5732484076433122,0.24533676375999214
+10,4,0.01172,0.9904099761164639,1.0,0.8450704225352115,0.7146562905317769,0.717165574025787,0.605095541401274,0.31517044932463456
+4,8,0.00834,0.9862531698550542,0.9907883667828387,0.9201877934272304,0.740164288802421,0.7427092085919618,0.651804670912951,0.0005819473797048502
+7,12,0.0095,0.9862647810457285,0.9908053919801306,0.9483568075117375,0.7509727626459143,0.7537465226431079,0.6709129511677281,0.0015314404729078746
+16,12,0.00973,0.8924388472737744,0.853230781556704,0.9201877934272304,0.740164288802421,0.7426215833192713,0.651804670912951,0.0011026371404945223
+16,24,0.00879,0.46020749334337274,0.21946080198694073,0.9530516431924885,0.751405101599654,0.7538727550903992,0.6730360934182589,0.0007657202364539373
+4,12,0.00997,0.9987481770430642,0.9906681889196011,0.9718309859154934,0.7574578469520102,0.7599878712741366,0.6836518046709128,0.00030628809458121964
+1,16,0.00928,0.9819624933952816,0.9844970556423507,0.9577464788732399,0.7539991353220924,0.7567813068398463,0.6772823779193204,0.0018070997580323933
+1,12,0.01132,0.9862763922364028,0.9908224171774226,0.934272300469484,0.7453523562472978,0.7481372038254939,0.662420382165605,0.00039817452295576317
+10,12,0.01505,0.9953190058525866,0.9906698373592917,0.9530516431924885,0.7522697795071335,0.7547628890486193,0.6730360934182589,0.6218873472388129
+4,16,0.01336,0.9902838471672247,0.9997225894323599,0.8215962441314555,0.706441850410722,0.7089925652992641,0.5902335456475585,0.27256577536831106
+10,24,0.02002,0.9880107858399209,0.9987962184032368,0.7934272300469489,0.6977950713359272,0.7004148319221472,0.5753715498938428,0.24879781922876631
+13,12,0.01002,0.41264805634132207,0.1497255938789408,1.0,0.767833981841764,0.7703185438935378,0.7027600849256899,0.001072008331036045
+7,16,0.01165,0.8994328821270172,0.8634859592196451,0.835680751173709,0.7120622568093385,0.7146296465795127,0.6008492569002124,0.0015008116634502855
+13,24,0.00901,0.5217550000519089,0.30970636542082286,0.915492957746479,0.7384349329874621,0.7410117942749463,0.6496815286624202,0.0016539557107417835
+10,20,0.00962,0.9864000172665236,0.9910036854544726,0.8967136150234749,0.7332468655425853,0.7358939578036594,0.6390658174097663,0.0007963490459124145
+4,4,0.00896,0.98670122521284,0.9914453391018708,0.9061032863849765,0.7349762213575443,0.7376859380090235,0.6433121019108281,0.00018377285674908705
+10,16,0.00966,0.5637192091713654,0.37123743139846976,0.938967136150235,0.7475140510159964,0.7500098686878895,0.664543524416136,0.0011945235688681777
+13,20,0.00906,0.9866575124950072,0.9913812442414774,0.854460093896714,0.717682663207955,0.7204259282314314,0.6114649681528663,0.001072008331036045
+7,4,0.01149,0.9901449677646027,0.9994171373632977,0.910798122065728,0.7375702550799826,0.7401286009323849,0.6475583864118897,0.24567368066403183
+13,16,0.00984,0.9840607038512544,0.987573608941233,0.934272300469484,0.7457846952010375,0.7486195766137691,0.662420382165605,0.0004288033324142404
+16,20,0.01022,0.6301625402771714,0.4686616191964107,0.8638497652582164,0.7215737137916126,0.724140025185759,0.6178343949044585,0.00039817452295576317
+16,16,0.01099,0.9861944308904663,0.990702239314185,0.854460093896714,0.7181150021616948,0.7207326166858473,0.6114649681528663,0.0017152133296569616
+1,4,0.01028,0.9455935121584194,0.9311701317950567,0.7981220657276995,0.698227410289667,0.7007310637230937,0.5753715498938428,0.0011638947594105886
diff --git a/datasets/norm_ext_kafka_real_saved_states.csv b/datasets/norm_ext_kafka_real_saved_states.csv
new file mode 100644
index 0000000..d0cf21a
--- /dev/null
+++ b/datasets/norm_ext_kafka_real_saved_states.csv
@@ -0,0 +1,37 @@
+MaxTenuringThreshold,ParallelGCThreads,avgGCPause,avgPromotion,promotionTotal,totalHeapUsedMaxpc,totalHeapUsedMax,totalYoungUsedMax,totalYoungUsedMaxpc,totalTenuredUsedMax
+10,12,0.02917,0.9999989364615451,0.9999985132665885,0.9252873563218391,0.928395061728395,0.9263209260597306,0.925343811394892,2.3067374411080144e-05
+10,8,0.0274,0.9999984332584332,0.9999978065957857,0.9770114942528738,0.978835978835979,0.9781394505509832,0.9783889980353635,1.3150559243703397e-05
+7,20,0.03037,0.999999386927213,0.9999991425903382,0.9310344827586208,0.934920634920635,0.9330853846938297,0.9332023575638508,1.9402464457932145e-06
+10,4,0.03058,0.9999987079326209,0.9999981933310509,0.9827586206896552,0.9871252204585538,0.9866984062178318,0.9862475442043221,1.9402464457918267e-05
+10,24,0.03323,0.9999989430537256,0.9999985224954983,0.9827586206896552,0.9869488536155203,0.9864975283325669,0.9862475442043221,1.9186881519493715e-05
+13,12,0.03009,0.9999987628674585,0.9999982702386321,0.9022988505747127,0.9022927689594357,0.8995971030836839,0.8998035363457761,4.74282464527076e-06
+4,20,0.03266,0.9999994550464116,0.9999992366373232,0.8793103448275863,0.8807760141093476,0.8774827845478718,0.8781925343811396,2.3067374411080144e-05
+13,8,0.02878,0.9999990507260073,0.9999986723554135,0.913793103448276,0.9178130511463846,0.9154836637735301,0.9155206286836934,9.701232228959134e-06
+13,4,0.03171,0.9999989870015957,0.9999985818242036,0.9770114942528738,0.9793650793650793,0.9787598353634558,0.9783889980353635,6.467488152639422e-06
+1,24,0.03256,0.9999992528862094,0.9999989553753121,0.9425287356321841,0.946384479717813,0.9448067632631479,0.9449901768172888,1.3150559243703397e-05
+13,24,0.03018,0.9999998593668159,0.9999998026771204,0.9827586206896552,0.9850088183421518,0.9846407211171927,0.9842829076620825,1.9186881519493715e-05
+16,12,0.03385,0.9999989672250542,0.9999985554558901,0.9770114942528738,0.980599647266314,0.9800045899419411,0.9803536345776032,6.467488152639422e-06
+1,20,0.02915,0.9999994462568376,0.9999992269689415,0.8620689655172415,0.8666666666666668,0.862938790932492,0.8624754420432219,1.8324549765809384e-05
+16,8,0.03115,0.9999986881560794,0.9999981638864341,0.9770114942528738,0.9811287477954146,0.980513033786791,0.9803536345776032,1.3150559243703397e-05
+16,4,0.02861,0.9999992397018485,0.9999989373569645,0.9597701149425288,0.9624338624338625,0.961442132950005,0.9607072691552063,4.3116587684216556e-07
+4,24,0.02787,0.9999992946366859,0.9999990133856019,0.9310344827586208,0.9320987654320988,0.9302519015926592,0.9292730844793713,1.0779146921088834e-06
+16,24,0.03204,0.9999993583610975,0.999999102598396,0.9310344827586208,0.9313932980599647,0.9294396956075125,0.9292730844793713,1.7677800950549605e-05
+7,24,0.03193,0.9999994836125271,0.9999992775082092,0.9770114942528738,0.9820105820105821,0.9815013022647036,0.982318271119843,0.0
+16,20,0.03056,0.9999996418248592,0.999999498562571,0.9712643678160919,0.9763668430335098,0.9756780172030445,0.9764243614931236,1.897129858108304e-05
+1,4,0.02897,0.9999987255117689,0.9999982161835893,0.9482758620689657,0.9495590828924162,0.9480758742399381,0.9489194499017684,1.5521971566331838e-05
+16,16,0.03027,0.9999989342641517,0.9999985093113415,0.9425287356321841,0.9432098765432099,0.9415541355032734,0.9410609037328095,7.545402844748306e-06
+10,20,0.03255,0.9999994572438051,0.999999241471514,0.9195402298850577,0.924867724867725,0.9228067404402324,0.9233791748526523,4.958407583695312e-06
+7,4,0.02989,0.9999990968712708,0.9999987356393659,1.0,1.0,1.0,1.0,1.1857061613169961e-05
+10,16,0.02917,0.9999996506144333,0.999999510428312,0.9425287356321841,0.9449735449735449,0.9434051464225895,0.9430255402750491,2.0695962088444764e-05
+13,20,0.03337,0.9999999626443106,0.9999999472633729,0.9367816091954022,0.9377425044091711,0.9360324389708895,0.9351669941060905,1.2072644551594514e-05
+4,4,0.02805,0.9999989166850036,0.999998482943028,0.9482758620689657,0.9506172839506174,0.9491809743102725,0.9489194499017684,2.198945971897126e-05
+13,16,0.0307,0.9999993583610975,0.9999991017194522,0.9655172413793103,0.970899470899471,0.9700413004207568,0.9705304518664046,2.0049213273184985e-05
+7,16,0.02677,0.999998756275278,0.9999982588123629,0.9770114942528738,0.9820105820105821,0.981392983982117,0.982318271119843,1.2503810428436679e-05
+4,8,0.02824,0.9999989891989892,0.9999985870978664,0.9827586206896552,0.9853615520282187,0.9848934033984772,0.9842829076620825,1.509080568951049e-06
+1,12,0.02957,0.9999987672622455,0.9999982741938791,0.9827586206896552,0.9869488536155203,0.9865285022896276,0.9862475442043221,1.0779146921088834e-06
+4,16,0.02815,0.9999995231656101,0.9999993328816675,0.9655172413793103,0.9659611992945326,0.9650617387040606,0.9646365422396856,2.1558293842177667e-06
+7,8,0.02848,0.9999992550836029,0.9999989575726715,0.9195402298850577,0.9201058201058202,0.9178250051125142,0.9174852652259333,2.134271090371148e-05
+4,12,0.02978,0.9999992902418989,0.9999990063540516,0.9655172413793103,0.970194003527337,0.9693582431571556,0.9685658153241652,2.0695962088444764e-05
+1,16,0.02857,0.9999998351954874,0.9999997688377846,0.9655172413793103,0.970194003527337,0.9694080550764052,0.9685658153241652,1.3797308058970115e-05
+7,12,0.03281,0.9999995539291192,0.9999993772683287,0.9655172413793103,0.9693121693121695,0.9684806477071032,0.9685658153241652,2.0049213273184985e-05
+1,8,0.02813,1.0,1.0,0.9597701149425288,0.9606701940035273,0.9596478170515076,0.9587426326129667,1.2719393366861231e-05
diff --git a/draft.ipynb b/draft.ipynb
new file mode 100644
index 0000000..ef5d33f
--- /dev/null
+++ b/draft.ipynb
@@ -0,0 +1,1253 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import glob\n",
+    "import seaborn as sns\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "skip_cols=['avgFullGCPauseIsSig', 'avgGCPauseIsSig', 'avgPauseIsSig', 'avgFreedMemoryByGCisSig',\n",
+    "           'avgfootprintAfterGCisSig', 'avgFreedMemoryByFullGCisSig', 'avgfootprintAfterFullGCisSig', '*σ']\n",
+    "\n",
+    "include_cols = [\n",
+    "    \"totalHeapAllocMax\",\n",
+    "    \"totalHeapUsedMax\",\n",
+    "    \"totalHeapUsedMaxpc\",\n",
+    "    \"totalTenuredAllocMax\",\n",
+    "    \"totalTenuredUsedMax\",\n",
+    "    \"totalTenuredUsedMaxpc\",\n",
+    "    \"totalYoungAllocMax\",\n",
+    "    \"totalYoungUsedMax\",\n",
+    "    \"totalYoungUsedMaxpc\",\n",
+    "    \"avgPromotion\",\n",
+    "    \"promotionTotal\",\n",
+    "    \"avgGCPause\",  # Goal.\n",
+    "    # \"gcPerformance\",  # Goal.\n",
+    "]\n",
+    "\n",
+    "all_dfs = []\n",
+    "\n",
+    "def get_processed_df(csv_file):\n",
+    "    processed_df = pd.read_csv(csv_file, sep=';', skiprows=1)\n",
+    "    processed_df = processed_df.replace(',','', regex=True)\n",
+    "    processed_df = processed_df.replace('n.a.','NaN', regex=True)\n",
+    "    processed_df = processed_df[processed_df.iloc[:, 0].isin(include_cols)]\n",
+    "    processed_df.index = processed_df.iloc[:, 0]\n",
+    "    processed_df = processed_df.transpose().iloc[1:2, :] # .astype(float).values \n",
+    "    return processed_df\n",
+    "\n",
+    "for summary in glob.glob(\"summaries_avrora/*.csv\"): # glob.glob(\"summaries_avrora/*.csv\") + \n",
+    "    df = get_processed_df(summary)\n",
+    "    \n",
+    "    all_dfs.append(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th>totalHeapAllocMax</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalTenuredAllocMax</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "      <th>totalTenuredUsedMaxpc</th>\n",
+       "      <th>totalYoungAllocMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1832</td>\n",
+       "      <td>5.6</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4747</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1828.775</td>\n",
+       "      <td>16.9</td>\n",
+       "      <td>-439501</td>\n",
+       "      <td>-2197504</td>\n",
+       "      <td>0.01203</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4773</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-306176</td>\n",
+       "      <td>-1530880</td>\n",
+       "      <td>0.00983</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4724</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-419430</td>\n",
+       "      <td>-2097152</td>\n",
+       "      <td>0.01115</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1832</td>\n",
+       "      <td>5.6</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4720</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1828.775</td>\n",
+       "      <td>16.9</td>\n",
+       "      <td>-280576</td>\n",
+       "      <td>-1402880</td>\n",
+       "      <td>0.00665</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4800</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-270541</td>\n",
+       "      <td>-1352704</td>\n",
+       "      <td>0.00989</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1832</td>\n",
+       "      <td>5.6</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4747</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1828.775</td>\n",
+       "      <td>16.9</td>\n",
+       "      <td>-169574</td>\n",
+       "      <td>-847872</td>\n",
+       "      <td>0.00954</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4720</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-127590</td>\n",
+       "      <td>-637952</td>\n",
+       "      <td>0.00755</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1832</td>\n",
+       "      <td>5.6</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4720</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1828.775</td>\n",
+       "      <td>16.9</td>\n",
+       "      <td>-445030</td>\n",
+       "      <td>-2225152</td>\n",
+       "      <td>0.01032</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1832</td>\n",
+       "      <td>5.6</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4751</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1828.775</td>\n",
+       "      <td>16.9</td>\n",
+       "      <td>-216269</td>\n",
+       "      <td>-1081344</td>\n",
+       "      <td>0.01006</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4804</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-338330</td>\n",
+       "      <td>-1691648</td>\n",
+       "      <td>0.0078</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4720</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-366797</td>\n",
+       "      <td>-1833984</td>\n",
+       "      <td>0.01106</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4720</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-365158</td>\n",
+       "      <td>-1825792</td>\n",
+       "      <td>0.01081</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4752</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-137421</td>\n",
+       "      <td>-687104</td>\n",
+       "      <td>0.00627</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4768</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-307405</td>\n",
+       "      <td>-1537024</td>\n",
+       "      <td>0.00939</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1832</td>\n",
+       "      <td>5.6</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4804</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1828.775</td>\n",
+       "      <td>16.9</td>\n",
+       "      <td>-276275</td>\n",
+       "      <td>-1381376</td>\n",
+       "      <td>0.01077</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4755</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-187187</td>\n",
+       "      <td>-935936</td>\n",
+       "      <td>0.00937</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1832</td>\n",
+       "      <td>5.6</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4804</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1828.775</td>\n",
+       "      <td>16.9</td>\n",
+       "      <td>-311091</td>\n",
+       "      <td>-1555456</td>\n",
+       "      <td>0.00817</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1832</td>\n",
+       "      <td>5.6</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4724</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1828.775</td>\n",
+       "      <td>16.9</td>\n",
+       "      <td>-140493</td>\n",
+       "      <td>-702464</td>\n",
+       "      <td>0.00832</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4804</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-273408</td>\n",
+       "      <td>-1367040</td>\n",
+       "      <td>0.00863</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4804</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-455066</td>\n",
+       "      <td>-2275328</td>\n",
+       "      <td>0.01444</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1832</td>\n",
+       "      <td>5.6</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4724</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1828.775</td>\n",
+       "      <td>16.9</td>\n",
+       "      <td>-127386</td>\n",
+       "      <td>-636928</td>\n",
+       "      <td>0.00722</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4720</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-201933</td>\n",
+       "      <td>-1009664</td>\n",
+       "      <td>0.00742</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4720</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-396902</td>\n",
+       "      <td>-1984512</td>\n",
+       "      <td>0.00832</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4799</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-33178</td>\n",
+       "      <td>-165888</td>\n",
+       "      <td>0.01179</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4805</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-285901</td>\n",
+       "      <td>-1429504</td>\n",
+       "      <td>0.0061</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4804</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-349389</td>\n",
+       "      <td>-1746944</td>\n",
+       "      <td>0.00843</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4755</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-363520</td>\n",
+       "      <td>-1817600</td>\n",
+       "      <td>0.01022</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1832</td>\n",
+       "      <td>5.6</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4777</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1828.775</td>\n",
+       "      <td>16.9</td>\n",
+       "      <td>-329318</td>\n",
+       "      <td>-1646592</td>\n",
+       "      <td>0.01047</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4720</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-181862</td>\n",
+       "      <td>-909312</td>\n",
+       "      <td>0.00792</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4804</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-382566</td>\n",
+       "      <td>-1912832</td>\n",
+       "      <td>0.009</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4804</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-222618</td>\n",
+       "      <td>-1113088</td>\n",
+       "      <td>0.01116</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1832</td>\n",
+       "      <td>5.6</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4751</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1828.775</td>\n",
+       "      <td>16.9</td>\n",
+       "      <td>-345088</td>\n",
+       "      <td>-1725440</td>\n",
+       "      <td>0.00762</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4720</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-299827</td>\n",
+       "      <td>-1499136</td>\n",
+       "      <td>0.01112</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4752</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-301261</td>\n",
+       "      <td>-1506304</td>\n",
+       "      <td>0.00969</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4746</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-311706</td>\n",
+       "      <td>-1558528</td>\n",
+       "      <td>0.00692</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32,685</th>\n",
+       "      <td>1993</td>\n",
+       "      <td>6.1</td>\n",
+       "      <td>21845.5</td>\n",
+       "      <td>4804</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10840</td>\n",
+       "      <td>1990.138</td>\n",
+       "      <td>18.4</td>\n",
+       "      <td>-244531</td>\n",
+       "      <td>-1222656</td>\n",
+       "      <td>0.00889</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "totalHeapAllocMax totalHeapUsedMax totalHeapUsedMaxpc totalTenuredAllocMax  \\\n",
+       " 32,685                       1832                5.6              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1832                5.6              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1832                5.6              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1832                5.6              21845.5   \n",
+       " 32,685                       1832                5.6              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1832                5.6              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1832                5.6              21845.5   \n",
+       " 32,685                       1832                5.6              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1832                5.6              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1832                5.6              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1832                5.6              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       " 32,685                       1993                6.1              21845.5   \n",
+       "\n",
+       "totalHeapAllocMax totalTenuredUsedMax totalTenuredUsedMaxpc  \\\n",
+       " 32,685                          4747                   0.0   \n",
+       " 32,685                          4773                   0.0   \n",
+       " 32,685                          4724                   0.0   \n",
+       " 32,685                          4720                   0.0   \n",
+       " 32,685                          4800                   0.0   \n",
+       " 32,685                          4747                   0.0   \n",
+       " 32,685                          4720                   0.0   \n",
+       " 32,685                          4720                   0.0   \n",
+       " 32,685                          4751                   0.0   \n",
+       " 32,685                          4804                   0.0   \n",
+       " 32,685                          4720                   0.0   \n",
+       " 32,685                          4720                   0.0   \n",
+       " 32,685                          4752                   0.0   \n",
+       " 32,685                          4768                   0.0   \n",
+       " 32,685                          4804                   0.0   \n",
+       " 32,685                          4755                   0.0   \n",
+       " 32,685                          4804                   0.0   \n",
+       " 32,685                          4724                   0.0   \n",
+       " 32,685                          4804                   0.0   \n",
+       " 32,685                          4804                   0.0   \n",
+       " 32,685                          4724                   0.0   \n",
+       " 32,685                          4720                   0.0   \n",
+       " 32,685                          4720                   0.0   \n",
+       " 32,685                          4799                   0.0   \n",
+       " 32,685                          4805                   0.0   \n",
+       " 32,685                          4804                   0.0   \n",
+       " 32,685                          4755                   0.0   \n",
+       " 32,685                          4777                   0.0   \n",
+       " 32,685                          4720                   0.0   \n",
+       " 32,685                          4804                   0.0   \n",
+       " 32,685                          4804                   0.0   \n",
+       " 32,685                          4751                   0.0   \n",
+       " 32,685                          4720                   0.0   \n",
+       " 32,685                          4752                   0.0   \n",
+       " 32,685                          4746                   0.0   \n",
+       " 32,685                          4804                   0.0   \n",
+       "\n",
+       "totalHeapAllocMax totalYoungAllocMax totalYoungUsedMax totalYoungUsedMaxpc  \\\n",
+       " 32,685                        10840          1828.775                16.9   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1828.775                16.9   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1828.775                16.9   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1828.775                16.9   \n",
+       " 32,685                        10840          1828.775                16.9   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1828.775                16.9   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1828.775                16.9   \n",
+       " 32,685                        10840          1828.775                16.9   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1828.775                16.9   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1828.775                16.9   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1828.775                16.9   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       " 32,685                        10840          1990.138                18.4   \n",
+       "\n",
+       "totalHeapAllocMax avgPromotion promotionTotal avgGCPause  \n",
+       " 32,685                -439501       -2197504    0.01203  \n",
+       " 32,685                -306176       -1530880    0.00983  \n",
+       " 32,685                -419430       -2097152    0.01115  \n",
+       " 32,685                -280576       -1402880    0.00665  \n",
+       " 32,685                -270541       -1352704    0.00989  \n",
+       " 32,685                -169574        -847872    0.00954  \n",
+       " 32,685                -127590        -637952    0.00755  \n",
+       " 32,685                -445030       -2225152    0.01032  \n",
+       " 32,685                -216269       -1081344    0.01006  \n",
+       " 32,685                -338330       -1691648     0.0078  \n",
+       " 32,685                -366797       -1833984    0.01106  \n",
+       " 32,685                -365158       -1825792    0.01081  \n",
+       " 32,685                -137421        -687104    0.00627  \n",
+       " 32,685                -307405       -1537024    0.00939  \n",
+       " 32,685                -276275       -1381376    0.01077  \n",
+       " 32,685                -187187        -935936    0.00937  \n",
+       " 32,685                -311091       -1555456    0.00817  \n",
+       " 32,685                -140493        -702464    0.00832  \n",
+       " 32,685                -273408       -1367040    0.00863  \n",
+       " 32,685                -455066       -2275328    0.01444  \n",
+       " 32,685                -127386        -636928    0.00722  \n",
+       " 32,685                -201933       -1009664    0.00742  \n",
+       " 32,685                -396902       -1984512    0.00832  \n",
+       " 32,685                 -33178        -165888    0.01179  \n",
+       " 32,685                -285901       -1429504     0.0061  \n",
+       " 32,685                -349389       -1746944    0.00843  \n",
+       " 32,685                -363520       -1817600    0.01022  \n",
+       " 32,685                -329318       -1646592    0.01047  \n",
+       " 32,685                -181862        -909312    0.00792  \n",
+       " 32,685                -382566       -1912832      0.009  \n",
+       " 32,685                -222618       -1113088    0.01116  \n",
+       " 32,685                -345088       -1725440    0.00762  \n",
+       " 32,685                -299827       -1499136    0.01112  \n",
+       " 32,685                -301261       -1506304    0.00969  \n",
+       " 32,685                -311706       -1558528    0.00692  \n",
+       " 32,685                -244531       -1222656    0.00889  "
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "frame = pd.concat(all_dfs,)\n",
+    "frame"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Total number of selected parameters: 12\n",
+      "Number of filtered parameters: 8\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Transpose.\n",
+    "# frame = frame.T\n",
+    "\n",
+    "# Remove constant values.\n",
+    "frame = frame.loc[:, (frame != frame.iloc[0]).any()]\n",
+    "\n",
+    "print(\"Total number of selected parameters:\", len(include_cols))\n",
+    "print(\"Number of filtered parameters:\", len(frame.columns))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th>totalHeapAllocMax</th>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <th>avgGCPause</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>totalHeapAllocMax</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>totalHeapUsedMax</th>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.163403</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>0.033075</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>totalHeapUsedMaxpc</th>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.163403</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>0.033075</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>totalTenuredUsedMax</th>\n",
+       "      <td>0.163403</td>\n",
+       "      <td>0.163403</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.163403</td>\n",
+       "      <td>0.163403</td>\n",
+       "      <td>-0.047795</td>\n",
+       "      <td>-0.047794</td>\n",
+       "      <td>0.146599</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>totalYoungUsedMax</th>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.163403</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>0.033075</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>totalYoungUsedMaxpc</th>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.163403</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>0.033075</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>avgPromotion</th>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>-0.047795</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.361351</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>promotionTotal</th>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>-0.047794</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>-0.023649</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.361351</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>avgGCPause</th>\n",
+       "      <td>0.033075</td>\n",
+       "      <td>0.033075</td>\n",
+       "      <td>0.146599</td>\n",
+       "      <td>0.033075</td>\n",
+       "      <td>0.033075</td>\n",
+       "      <td>-0.361351</td>\n",
+       "      <td>-0.361351</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "totalHeapAllocMax    totalHeapUsedMax  totalHeapUsedMaxpc  \\\n",
+       "totalHeapAllocMax                                           \n",
+       "totalHeapUsedMax             1.000000            1.000000   \n",
+       "totalHeapUsedMaxpc           1.000000            1.000000   \n",
+       "totalTenuredUsedMax          0.163403            0.163403   \n",
+       "totalYoungUsedMax            1.000000            1.000000   \n",
+       "totalYoungUsedMaxpc          1.000000            1.000000   \n",
+       "avgPromotion                -0.023649           -0.023649   \n",
+       "promotionTotal              -0.023649           -0.023649   \n",
+       "avgGCPause                   0.033075            0.033075   \n",
+       "\n",
+       "totalHeapAllocMax    totalTenuredUsedMax  totalYoungUsedMax  \\\n",
+       "totalHeapAllocMax                                             \n",
+       "totalHeapUsedMax                0.163403           1.000000   \n",
+       "totalHeapUsedMaxpc              0.163403           1.000000   \n",
+       "totalTenuredUsedMax             1.000000           0.163403   \n",
+       "totalYoungUsedMax               0.163403           1.000000   \n",
+       "totalYoungUsedMaxpc             0.163403           1.000000   \n",
+       "avgPromotion                   -0.047795          -0.023649   \n",
+       "promotionTotal                 -0.047794          -0.023649   \n",
+       "avgGCPause                      0.146599           0.033075   \n",
+       "\n",
+       "totalHeapAllocMax    totalYoungUsedMaxpc  avgPromotion  promotionTotal  \\\n",
+       "totalHeapAllocMax                                                        \n",
+       "totalHeapUsedMax                1.000000     -0.023649       -0.023649   \n",
+       "totalHeapUsedMaxpc              1.000000     -0.023649       -0.023649   \n",
+       "totalTenuredUsedMax             0.163403     -0.047795       -0.047794   \n",
+       "totalYoungUsedMax               1.000000     -0.023649       -0.023649   \n",
+       "totalYoungUsedMaxpc             1.000000     -0.023649       -0.023649   \n",
+       "avgPromotion                   -0.023649      1.000000        1.000000   \n",
+       "promotionTotal                 -0.023649      1.000000        1.000000   \n",
+       "avgGCPause                      0.033075     -0.361351       -0.361351   \n",
+       "\n",
+       "totalHeapAllocMax    avgGCPause  \n",
+       "totalHeapAllocMax                \n",
+       "totalHeapUsedMax       0.033075  \n",
+       "totalHeapUsedMaxpc     0.033075  \n",
+       "totalTenuredUsedMax    0.146599  \n",
+       "totalYoungUsedMax      0.033075  \n",
+       "totalYoungUsedMaxpc    0.033075  \n",
+       "avgPromotion          -0.361351  \n",
+       "promotionTotal        -0.361351  \n",
+       "avgGCPause             1.000000  "
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "frame.corr()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='totalHeapAllocMax', ylabel='totalHeapAllocMax'>"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fig, ax = plt.subplots() # figsize=(8, 8)\n",
+    "\n",
+    "# Generate a mask for the upper triangle\n",
+    "mask = np.triu(np.ones_like(frame.corr(), dtype=bool))\n",
+    "\n",
+    "sns.heatmap(frame.corr(), ax=ax, fmt=\".2f\", annot=True, mask=mask)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of correlated parameters: 7\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "totalHeapAllocMax\n",
+       "avgPromotion          -0.361351\n",
+       "promotionTotal        -0.361351\n",
+       "totalHeapUsedMaxpc     0.033075\n",
+       "totalHeapUsedMax       0.033075\n",
+       "totalYoungUsedMax      0.033075\n",
+       "totalYoungUsedMaxpc    0.033075\n",
+       "totalTenuredUsedMax    0.146599\n",
+       "avgGCPause             1.000000\n",
+       "Name: avgGCPause, dtype: float64"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Correlation with output variable\n",
+    "cor_target = frame.corr()[\"avgGCPause\"].sort_values()\n",
+    "# cor_target = frame.corr()[\"gcPerformance\"].sort_values()\n",
+    "print(\"Number of correlated parameters:\", len(cor_target) - 1)\n",
+    "cor_target"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Extra parameters (Avrora)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Initial list of parameters:\n",
+      " totalHeapAllocMax\n",
+      "totalHeapUsedMax\n",
+      "totalHeapUsedMaxpc\n",
+      "totalTenuredAllocMax\n",
+      "totalTenuredUsedMax\n",
+      "totalTenuredUsedMaxpc\n",
+      "totalYoungAllocMax\n",
+      "totalYoungUsedMax\n",
+      "totalYoungUsedMaxpc\n",
+      "avgPromotion\n",
+      "promotionTotal\n",
+      "avgGCPause\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"Initial list of parameters:\\n\", \"\\n\".join(include_cols))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The following parameters did not change over time and were excluded from the list.\n",
+    "- totalHeapAllocMax\n",
+    "- totalYoungAllocMax\n",
+    "- totalTenuredUsedMaxpc\n",
+    "- totalTenuredAllocMax\n",
+    "\n",
+    "\n",
+    "1. avgPromotion (-0.36, negative correlation)\n",
+    "2. promotionTotal (-0.36, negative correlation)\n",
+    "3. totalHeapUsedMaxpc (0.033075)\n",
+    "4. totalHeapUsedMax (0.033075)\n",
+    "5. totalYoungUsedMax (0.033075)\n",
+    "6. totalYoungUsedMaxpc (0.033075)\n",
+    "7. totalTenuredUsedMax (0.146599)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Extra parameters (Kafka)\n",
+    "\n",
+    "1. avgPromotion           0.183438\n",
+    "2. promotionTotal         0.183791\n",
+    "3. totalHeapUsedMaxpc    -0.021756\n",
+    "4. totalHeapUsedMax      -0.011937\n",
+    "5. totalYoungUsedMax     -0.011882\n",
+    "6. totalYoungUsedMaxpc   -0.007519\n",
+    "7. totalTenuredUsedMax    0.080765"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Random"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "flags = {\n",
+    "    \"MaxTenuringThreshold\": {\"min\": 1, \"max\": 16, \"step\": 3},\n",
+    "    \"ParallelGCThreads\": {\"min\": 4, \"max\": 24, \"step\": 4},\n",
+    "}\n",
+    "\n",
+    "flags_min_values = [flags[i][\"min\"] for i in flags.keys()]\n",
+    "flags_max_values = [flags[i][\"max\"] for i in flags.keys()]\n",
+    "flags_step_values = [flags[i][\"step\"] for i in flags.keys()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "_num_variables=2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[4, 12]"
+      ]
+     },
+     "execution_count": 48,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import random\n",
+    "\n",
+    "random_state = []\n",
+    "for i in range(_num_variables):\n",
+    "    random_state.append(\n",
+    "        random.randrange(flags_min_values[i], flags_max_values[i], flags_step_values[i])\n",
+    "    )\n",
+    "random_state\n",
+    "# [random.randint(flags_min_values[i], flags_max_values[i]) for i in range(_num_variables)]\n",
+    "# random.randint(flags_min_values[0], flags_max_values[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "[]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[1, 4]"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "flags_min_values"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "gc-ml-env",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.17"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/env/PyEnvironmentsTest.py b/env/PyEnvironmentsTest.py
index afdd15c..72d8aff 100644
--- a/env/PyEnvironmentsTest.py
+++ b/env/PyEnvironmentsTest.py
@@ -1,14 +1,14 @@
 import os
 import re
 import copy
+import random
 import subprocess
 import logging
+
 import numpy as np
 import pandas as pd
-from constraint import *
 from typing import Any, Dict, List
 from tf_agents.typing import types
-from tf_agents.trajectories import TimeStep
 from tf_agents.specs import array_spec
 from tf_agents.environments import py_environment
 from tf_agents.trajectories import time_step as ts
@@ -48,8 +48,8 @@ def __init__(
         self._num_variables = 2
         self._goal_idx = self._num_variables
         self._flags = {
-            "MaxTenuringThreshold": {"min": 1, "max": 16},
-            "ParallelGCThreads": {"min": 4, "max": 24},
+            "MaxTenuringThreshold": {"min": 1, "max": 16, "step": 3},
+            "ParallelGCThreads": {"min": 4, "max": 24, "step": 4},
         }
 
         self._action_mapping = {
@@ -64,6 +64,7 @@ def __init__(
 
         self._flags_min_values = [self._flags[i]["min"] for i in self._flags.keys()]
         self._flags_max_values = [self._flags[i]["max"] for i in self._flags.keys()]
+        self._flags_step_values = [self._flags[i]["step"] for i in self._flags.keys()]
 
         self._action_spec = array_spec.BoundedArraySpec(
             shape=(),
@@ -76,18 +77,15 @@ def __init__(
         self._observation_spec = array_spec.BoundedArraySpec(
             shape=(self._num_variables + 1 + 7,),  # 1 goal, {X} external vars
             dtype=np.float32,
-            # minimum=self._flags_min_values,
-            # maximum=self._flags_max_values,
-            # minimum=[1, 4, 0.0, 0.0, 0.0, 0.0, 0.0],
-            # maximum=[16, 24, 3.0, 200.0, 5.0, 30.0, 30.0],
             name='observation'
         )
 
         # For offline RL: if you already have a dataset file with trajectories.
         self._new_df = pd.read_csv(
-            f"datasets/ext_{self._bm}_real_saved_states.csv")
+            f"datasets/norm_ext_{self._bm}_real_saved_states.csv")
         
-        self._default_state = self._get_default_state(mode="default")
+        # self._default_state = self._get_default_state(mode="default")
+        self._default_state = self._get_default_state(mode="random")
 
         self._perf_states = {}
         self._perf_states[0] = {
@@ -158,6 +156,7 @@ def _reset(self):
         self._episode_ended = False
         
         # To ensure all elements within an object array are copied, use `copy.deepcopy`
+        self._default_state = self._get_default_state(mode="random")
         self._state = copy.deepcopy(self._default_state)
 
         logging.debug(f"[RESET] {self._get_info()}, target: {self._state[self._goal_idx]}")
@@ -325,15 +324,22 @@ def _get_default_state(self, mode: str = "default"):
         (np.array) The initial state of the Agent which stores the default
         JVM_OPTS and its performance measurement.
         """
+        assert mode in ["default", "random"], f"Unknown mode: {mode}"
         
-        state = self._synthetic_run([7, 12])
-        # if self._bm == "avrora":
-        #     return np.array([[7, 12], 0.47], dtype=object)
-        # elif self._bm == "kafka":
-        #     return np.array([[7, 12], 0.34], dtype=object)
-        # elif self._bm == "test":
-        #     return np.array([[7, 12], 0.57], dtype=object)
-        return state  # array([])
+        if mode == "default":
+            state = self._synthetic_run([7, 12])
+        if mode == "random":
+            rand_flags = []
+            for i in range(self._num_variables):
+                rand_flags.append(
+                    random.randrange(
+                        start=self._flags_min_values[i],
+                        stop=self._flags_max_values[i],
+                        step=self._flags_step_values[i]
+                    )
+                )
+            state = self._synthetic_run(rand_flags)
+        return state
     
     def _get_goal_value(self, jvm_opts: List[str] = []):
         """
diff --git a/img/ppo_vis.png b/img/ppo_vis.png
new file mode 100644
index 0000000..64be6e8
Binary files /dev/null and b/img/ppo_vis.png differ
diff --git a/main_ppo.ipynb b/main_ppo.ipynb
index 7a6922f..dfd6a17 100644
--- a/main_ppo.ipynb
+++ b/main_ppo.ipynb
@@ -44,14 +44,14 @@
     "\n",
     "\n",
     "logger = logging.getLogger()\n",
-    "# logger.setLevel(logging.DEBUG)\n",
+    "logger.setLevel(logging.DEBUG)\n",
     "# logger.setLevel(logging.INFO)\n",
     "# logger.error(\"test\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -63,7 +63,7 @@
     "from tqdm import tqdm\n",
     "\n",
     "from tf_agents.agents import PPOAgent\n",
-    "from tf_agents.environments import tf_py_environment\n",
+    "from tf_agents.environments import tf_py_environment, BatchedPyEnvironment\n",
     "from tf_agents.networks import sequential\n",
     "from tf_agents.policies import random_tf_policy, policy_saver\n",
     "from tf_agents.replay_buffers import tf_uniform_replay_buffer\n",
@@ -75,15 +75,19 @@
     "from tf_agents.networks.value_network import ValueNetwork\n",
     "from tf_agents.drivers.dynamic_episode_driver import DynamicEpisodeDriver\n",
     "\n",
+    "\n",
     "# from env.PyEnvironments import CurveEnv, CurveMultipleEnv, JVMEnv\n",
     "# from env.PyEnvironments import JVMEnv\n",
     "from env.PyEnvironmentsTest import JVMEnv # !!!\n",
-    "from util.plots_util import plot_dataset, plot_goal_heatmap\n"
+    "from util.plots_util import plot_dataset, plot_goal_heatmap\n",
+    "\n",
+    "tf.random.set_seed(42)\n",
+    "np.random.seed(42) "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -92,23 +96,118 @@
      "text": [
       "Successfully initialized a JVM Environment!\n",
       " JDK: jdk-11.0.20.1.jdk/bin,\n",
-      " Benchmark: avrora (dacapo-bench.jar),\n",
+      " Benchmark: kafka_2 (dacapo-bench.jar),\n",
       " Number of iterations: 5,\n",
       " Goal: avgGCPause,\n",
       " Number of JVM options: 2,\n",
-      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16}, 'ParallelGCThreads': {'min': 4, 'max': 24}},\n",
-      " Env. default state: [7, 12, 0.01047, 4777.0, 0.05264, 3072.0, -329318.0],\n",
-      " Env. default goal value: 0.01047,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [1, 20, 0.00875, 0.9944960907170034, 0.9907217902495694, 0.0751173708920189, 0.0172935581495892, 0.0161681641767931, 0.9808917197452228, 1.0],\n",
+      " Env. default goal value: 0.00875,\n",
+      "\n",
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: kafka_4 (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [7, 8, 0.0102, 0.9957989346117848, 0.990684671313544, 0.7417840375586859, 0.3069606571552097, 0.3079898198519827, 0.9214437367303608, 0.5123893534258315],\n",
+      " Env. default goal value: 0.0102,\n",
+      "\n",
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: kafka_8 (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [10, 4, 0.01172, 0.990409976116464, 1.0, 0.8450704225352115, 0.7146562905317769, 0.717165574025787, 0.605095541401274, 0.3151704493246345],\n",
+      " Env. default goal value: 0.01172,\n",
+      "\n",
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: kafka_16 (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [4, 12, 0.01354, 0.990032042788194, 0.9991687697792734, 0.0751173708920189, 0.7276264591439688, 0.7303392963343571, 0.0403397027600849, 0.2466844313761527],\n",
+      " Env. default goal value: 0.01354,\n",
+      "\n",
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: kafka_32 (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [1, 12, 0.01053, 0.9106233378922056, 0.9352722028602332, 0.7089201877934275, 0.9801124081279724, 0.980083035790586, 0.4055201698513799, 0.2541578608839474],\n",
+      " Env. default goal value: 0.01053,\n",
+      "\n",
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: avrora_2 (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [7, 4, 0.00693, 0.9744866328328492, 0.9954249526515152, 0.5714285714285716, 0.5660377358490565, 0.5714176215843327, 0.5769230769230766, 0.0151724137931035],\n",
+      " Env. default goal value: 0.00693,\n",
+      "\n",
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: avrora_4 (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [10, 8, 0.00647, 0.5760536635598197, 0.5884297520661157, 0.1428571428571428, 0.150943396226415, 0.1428544053960831, 0.1442307692307691, 0.000689655172414],\n",
+      " Env. default goal value: 0.00647,\n",
+      "\n",
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: avrora_8 (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [10, 8, 0.00674, 0.7783191422679543, 0.7950413223140496, 0.4285714285714284, 0.4339622641509431, 0.42856321618825, 0.4326923076923075, 0.0372413793103452],\n",
+      " Env. default goal value: 0.00674,\n",
+      "\n",
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: avrora_16 (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [4, 12, 0.00928, 0.4859770502424289, 0.4964187327823691, 0.4285714285714284, 0.4339622641509431, 0.42856321618825, 0.4326923076923075, 0.0372413793103452],\n",
+      " Env. default goal value: 0.00928,\n",
+      "\n",
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: avrora_32 (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [7, 12, 0.00918, 0.8527517849665129, 0.8710743801652892, 0.8571428571428572, 0.8679245283018866, 0.8571455946039168, 0.8653846153846145, 0.96],\n",
+      " Env. default goal value: 0.00918,\n",
+      "\n",
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: h2 (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [1, 20, 0.18954, 0.999979412534938, 0.9884644586588516, 1.0, 1.0, 0.9999987792999906, 1.0, 0.1472500455957914],\n",
+      " Env. default goal value: 0.18954,\n",
       "\n"
      ]
     }
    ],
    "source": [
-    "# TEST_JDK_PATH = \"/Users/ellkrauze/projects/gc-ml/jdk-11.0.20.1.jdk\"\n",
-    "# BM = \"avrora\"\n",
-    "# BM_TEST = \"kafka\"\n",
-    "# BM_PATH = \"/Users/ellkrauze/projects/gc-ml/dacapo-bench.jar\"\n",
-    "# CALLBACK_PATH = \"/home/vsakovskaya/gc-ml/dacapo/DacapoCallback/DacapoChopin/VMStatCallback.java\"\n",
     "dataset_path = \"dataset/data\"\n",
     "tempdir = \"tmp\"\n",
     "checkpoint_dir = os.path.join(tempdir, 'checkpoint')\n",
@@ -129,10 +228,16 @@
     "    tf_env = tf_py_environment.TFPyEnvironment(env, isolation=True) \n",
     "    return tf_env\n",
     "\n",
-    "# env_train_1 = JVMEnv(bm_name=\"avrora\", **env_args)\n",
-    "# env_train_2 = JVMEnv(bm_name=\"kafka\", **env_args)\n",
+    "# Batch together multiple py environments and act as a single batch.\n",
+    "names = [\"kafka_2\", \"kafka_4\", \"kafka_8\", \"kafka_16\", \"kafka_32\",\n",
+    "         \"avrora_2\", \"avrora_4\", \"avrora_8\", \"avrora_16\", \"avrora_32\"]\n",
     "\n",
-    "train_env = get_tf_env(name=\"avrora\", args=env_args)\n",
+    "envs = [JVMEnv(bm_name=name, **env_args) for name in names]\n",
+    "\n",
+    "batched_env = BatchedPyEnvironment(envs)\n",
+    "train_env = tf_py_environment.TFPyEnvironment(batched_env)\n",
+    "\n",
+    "test_env = get_tf_env(name=\"h2\", args=env_args)\n",
     "\n",
     "action_spec = from_spec(train_env.action_spec())\n",
     "observation_spec = from_spec(train_env.observation_spec())\n",
@@ -142,7 +247,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -203,7 +308,14 @@
     "def restore_rb(replay_buffer, path):\n",
     "    tf.train.Checkpoint(rb = replay_buffer).restore(path)\n",
     "\n",
-    "def get_dataset(replay_buffer, size, batch_size, collect_data_spec, n_step_update, create: bool = True, save: bool = False):\n",
+    "def get_dataset(\n",
+    "    replay_buffer, \n",
+    "    size, \n",
+    "    batch_size, \n",
+    "    collect_data_spec, \n",
+    "    n_step_update, \n",
+    "    create: bool = True, \n",
+    "    save: bool = False):\n",
     "    \n",
     "    replay_buffer = tf_uniform_replay_buffer.TFUniformReplayBuffer(\n",
     "        data_spec=collect_data_spec, # agent.collect_data_spec\n",
@@ -244,7 +356,12 @@
     "    avg_return = total_return / num_episodes\n",
     "    return avg_return.numpy()[0]\n",
     "\n",
-    "def compute_avg_return_episodic(environment, policy, num_episodes=10, patience=100):\n",
+    "def get_env_state(environment):\n",
+    "    return environment.current_time_step().observation.numpy().squeeze()[:3]\n",
+    "\n",
+    "def compute_avg_return_episodic(\n",
+    "    environment, policy, num_episodes=10, patience=100,\n",
+    "    print_info=False):\n",
     "    \"\"\"\n",
     "    Computes the average return of a policy, \n",
     "    given the policy, environment, and a number of episodes.\n",
@@ -252,26 +369,25 @@
     "    Note: for episodic tasks.\n",
     "    \"\"\"\n",
     "    total_return = 0.0\n",
-    "    for _ in tqdm(range(num_episodes)):\n",
-    "\n",
+    "    environment.reset()\n",
+    "    # default_state = get_env_state(environment)\n",
+    "    \n",
+    "    for _ in range(num_episodes):\n",
     "        time_step = environment.reset()\n",
     "        episode_return = 0.0\n",
     "        i = 0\n",
-    "\n",
     "        while not time_step.is_last():\n",
     "            if i >= patience:\n",
     "                break\n",
     "            action_step = policy.action(time_step)\n",
     "            time_step = environment.step(action_step.action)\n",
-    "            # print(\"time step:\", action_step)\n",
-    "            # print(\"action:\", action_step.action)\n",
     "            obs = time_step.observation.numpy()[0]\n",
     "            rwd = time_step.reward.numpy()[0]\n",
-    "            # logger.debug(f\"[COMPUTE AVERAGE RETURN EPISODIC] action: {action_step.action}, obs: {obs}, reward: {rwd}\")\n",
     "            episode_return += time_step.reward\n",
     "            i += 1\n",
     "        total_return += episode_return / i\n",
-    "\n",
+    "    \n",
+    "    # if print_info: print(\"default:\", default_state, \"current:\", get_env_state(environment))\n",
     "    avg_return = total_return / num_episodes\n",
     "    return avg_return.numpy()[0]\n",
     "\n",
@@ -312,35 +428,59 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
-    "def get_dataset_iter(envs, size, _agent):\n",
+    "def get_dataset_iter(envs, size, _agent, _train_episodes_per_iteration):\n",
+    "    \"\"\"Get a dataset iterator with trajectories\n",
+    "    collected from environments from list `envs`\n",
+    "    using `_agent` collect policy. \n",
+    "\n",
+    "    Args:\n",
+    "        envs (list(PyEnvironment)): List of PyEnvironments \n",
+    "        to collect data from.\n",
+    "        size (int):   A dataset size (number of trajectories\n",
+    "        to collect.)\n",
+    "        _agent (_type_): A Tensorflow Agent.\n",
+    "        _train_episodes_per_iteration (int): \n",
+    "            A number of trajectories per batch.\n",
+    "\n",
+    "    Returns:\n",
+    "        iterator: A dataset iterator.\n",
+    "    \"\"\"\n",
     "    from random import randrange\n",
     "    assert len(envs) >= 1, \"Environment list is empty!\"\n",
-    "    \n",
+    "    num_iterations_to_reset = 50\n",
     "    replay_buffer = tf_uniform_replay_buffer.TFUniformReplayBuffer(\n",
     "        data_spec=_agent.collect_data_spec, # agent.collect_data_spec\n",
     "        batch_size=envs[0].batch_size, # train_env.batch_size\n",
     "        max_length=size) # capacity\n",
-    "\n",
+    "    \n",
+    "    i = 0\n",
     "    for _ in tqdm(range(size)):\n",
-    "        indx = randrange(len(envs))\n",
-    "        traj = collect_step(envs[indx], _agent.collect_policy, replay_buffer)\n",
+    "        # Select a random environment from list.\n",
+    "        indx = randrange(len(envs)) \n",
+    "        env = envs[indx]\n",
+    "        \n",
+    "        if i >= num_iterations_to_reset:\n",
+    "            env.reset()\n",
+    "            \n",
+    "        traj = collect_step(env, _agent.collect_policy, replay_buffer)\n",
     "        replay_buffer.add_batch(traj)\n",
+    "        i += 1\n",
     "            \n",
     "    dataset = replay_buffer.as_dataset(\n",
     "        sample_batch_size=batch_size,\n",
     "        num_steps=train_episodes_per_iteration+1,\n",
-    "        num_parallel_calls=train_episodes_per_iteration).prefetch(train_episodes_per_iteration)\n",
+    "        num_parallel_calls=_train_episodes_per_iteration).prefetch(_train_episodes_per_iteration)\n",
     "    dataset_iter = iter(dataset)\n",
     "    return dataset_iter"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -372,22 +512,15 @@
     "    # \"train_step_counter\": global_step,\n",
     "    # \"importance_ratio_clipping\": 0.1,\n",
     "    # \"num_epochs\": 20,\n",
+    "    \"entropy_regularization\": 0.01,\n",
     "}"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:absl:Only tf.keras.optimizers.Optimiers are well supported, got a non-TF2 optimizer: <tensorflow.python.training.adam.AdamOptimizer object at 0x1740ebfd0>\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "agent = PPOAgent(\n",
     "  time_step_spec,\n",
@@ -406,11 +539,11 @@
     "  emit_log_probability=True\n",
     ")\n",
     "\n",
-    "def get_rb_and_cd(_env, _agent):\n",
+    "def get_cd_and_rb(_env, _agent, size, n_steps):\n",
     "  replay_buffer = tf_uniform_replay_buffer.TFUniformReplayBuffer(\n",
     "      data_spec=_agent.collect_data_spec, # agent.collect_data_spec\n",
     "      batch_size=_env.batch_size, # train_env.batch_size\n",
-    "      max_length=dataset_size) # capacity\n",
+    "      max_length=size) # capacity\n",
     "\n",
     "  replay_buffer_observer = replay_buffer.add_batch\n",
     "\n",
@@ -418,14 +551,14 @@
     "      _env,\n",
     "      _agent.collect_policy,\n",
     "      observers=[replay_buffer_observer], # + train_metrics,\n",
-    "      num_episodes=train_episodes_per_iteration)\n",
+    "      num_episodes=n_steps)\n",
     "  \n",
-    "  return replay_buffer, collect_driver\n"
+    "  return collect_driver, replay_buffer\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -442,11 +575,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
-    "def train(_agent, _env_train, _env_val, replay_buffer, collect_driver,\n",
+    "def train(_agent, _env_train, _env_val, \n",
+    "          collect_driver, \n",
+    "          replay_buffer, \n",
     "          steps: int = 5000, \n",
     "          use_wandb: bool = False,\n",
     "          eval_interval: int=100):\n",
@@ -458,7 +593,7 @@
     "    _env_train.reset()\n",
     "    _env_val.reset()\n",
     "    _agent.train_step_counter.assign(0)\n",
-    "\n",
+    "    _agent.train = common.function(_agent.train)\n",
     "    time_step = None\n",
     "    policy_state = _agent.collect_policy.get_initial_state(_env_train.batch_size)\n",
     "\n",
@@ -470,7 +605,7 @@
     "        time_step, policy_state = collect_driver.run(\n",
     "            time_step=time_step,\n",
     "            policy_state=policy_state,\n",
-    "            maximum_iterations=200,\n",
+    "            maximum_iterations=50,\n",
     "        )\n",
     "\n",
     "        experience = replay_buffer.gather_all()\n",
@@ -503,7 +638,8 @@
     "    _env_train.reset()\n",
     "    _env_val.reset()\n",
     "    _agent.train_step_counter.assign(0)\n",
-    "\n",
+    "    _agent.train = common.function(_agent.train)\n",
+    "    \n",
     "    time_step = None\n",
     "    policy_state = _agent.collect_policy.get_initial_state(_env_train.batch_size)\n",
     "\n",
@@ -540,7 +676,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -553,9 +689,9 @@
       " Number of iterations: 5,\n",
       " Goal: avgGCPause,\n",
       " Number of JVM options: 2,\n",
-      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16}, 'ParallelGCThreads': {'min': 4, 'max': 24}},\n",
-      " Env. default state: [7, 12, 0.01047, 4777.0, 0.05264, 3072.0, -329318.0],\n",
-      " Env. default goal value: 0.01047,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [4, 8, 0.00762, 0.2416649425551018, 0.241660319886844, 0.0, 0.0, 0.0, 0.0, 0.9883585213252486],\n",
+      " Env. default goal value: 0.00762,\n",
       "\n",
       "Successfully initialized a JVM Environment!\n",
       " JDK: jdk-11.0.20.1.jdk/bin,\n",
@@ -563,9 +699,9 @@
       " Number of iterations: 5,\n",
       " Goal: avgGCPause,\n",
       " Number of JVM options: 2,\n",
-      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16}, 'ParallelGCThreads': {'min': 4, 'max': 24}},\n",
-      " Env. default state: [7, 12, 0.03281, 166.507, 0.1767, 29.0, 18.423],\n",
-      " Env. default goal value: 0.03281,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [1, 4, 0.02897, 0.9999987255117688, 0.9999982161835892, 0.9482758620689656, 0.9495590828924162, 0.948075874239938, 0.9489194499017684, 1.5521971566331838e-05],\n",
+      " Env. default goal value: 0.02897,\n",
       "\n",
       "Successfully initialized a JVM Environment!\n",
       " JDK: jdk-11.0.20.1.jdk/bin,\n",
@@ -573,15 +709,15 @@
       " Number of iterations: 5,\n",
       " Goal: avgGCPause,\n",
       " Number of JVM options: 2,\n",
-      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16}, 'ParallelGCThreads': {'min': 4, 'max': 24}},\n",
-      " Env. default state: [7, 12, 0.03281, 166.507, 0.1767, 29.0, 18.423],\n",
-      " Env. default goal value: 0.03281,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [10, 8, 0.0274, 0.9999984332584332, 0.9999978065957856, 0.9770114942528738, 0.978835978835979, 0.9781394505509832, 0.9783889980353636, 1.3150559243703395e-05],\n",
+      " Env. default goal value: 0.0274,\n",
       "\n"
      ]
     }
    ],
    "source": [
-    "num_steps = 3000\n",
+    "num_steps = 5000\n",
     "\n",
     "train_env_copy = get_tf_env(\"avrora\", env_args)\n",
     "\n",
@@ -594,2041 +730,6890 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "  0%|          | 0/3000 [00:00<?, ?it/s]"
+      "  0%|          | 0/5000 [00:00<?, ?it/s]"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\n",
-      "/Users/ellkrauze/projects/gc-ml/gc-ml-env/lib/python3.8/site-packages/tf_agents/utils/common.py:1443: SyntaxWarning: \"is not\" with a literal. Did you mean \"!=\"?\n",
-      "  return state is not None and state is not () and state is not []\n",
-      "/Users/ellkrauze/projects/gc-ml/gc-ml-env/lib/python3.8/site-packages/tf_agents/utils/common.py:1443: SyntaxWarning: \"is not\" with a literal. Did you mean \"!=\"?\n",
-      "  return state is not None and state is not () and state is not []\n"
+      "100%|██████████| 20/20 [00:12<00:00,  1.66it/s]\n",
+      "  0%|          | 1/5000 [00:28<39:46:25, 28.64s/it]"
      ]
     },
     {
-     "ename": "ValueError",
-     "evalue": "Received a mix of batched and unbatched Tensors, or Tensors are not compatible with Specs.  num_outer_dims: 1.\nSaw tensor_shapes:\n   TimeStep(\n{'discount': TensorShape([1]),\n 'observation': TensorShape([1]),\n 'reward': TensorShape([1]),\n 'step_type': TensorShape([1])})\nAnd spec_shapes:\n   TimeStep(\n{'discount': TensorShape([]),\n 'observation': TensorShape([7]),\n 'reward': TensorShape([]),\n 'step_type': TensorShape([])})",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
-      "\u001b[1;32m/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb Cell 15\u001b[0m line \u001b[0;36m3\n\u001b[1;32m      <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=0'>1</a>\u001b[0m \u001b[39m# Train on first\u001b[39;00m\n\u001b[1;32m      <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=1'>2</a>\u001b[0m collect_driver, replay_buffer \u001b[39m=\u001b[39m get_rb_and_cd(train_env, agent)\n\u001b[0;32m----> <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=2'>3</a>\u001b[0m loss, observations, rewards \u001b[39m=\u001b[39m train(\n\u001b[1;32m      <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=3'>4</a>\u001b[0m     agent, train_env, train_env_copy, collect_driver, replay_buffer, steps \u001b[39m=\u001b[39;49m num_steps, eval_interval\u001b[39m=\u001b[39;49m\u001b[39m100\u001b[39;49m)\n\u001b[1;32m      <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=5'>6</a>\u001b[0m \u001b[39mprint\u001b[39m(\u001b[39m\"\u001b[39m\u001b[39mAVG RETURN - KAFKA:\u001b[39m\u001b[39m\"\u001b[39m, \n\u001b[1;32m      <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=6'>7</a>\u001b[0m       compute_avg_return_episodic(train_env_2, agent\u001b[39m.\u001b[39mpolicy, num_episodes\u001b[39m=\u001b[39m\u001b[39m50\u001b[39m))\n",
-      "\u001b[1;32m/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb Cell 15\u001b[0m line \u001b[0;36m2\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=18'>19</a>\u001b[0m rewards \u001b[39m=\u001b[39m []\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=19'>20</a>\u001b[0m \u001b[39mfor\u001b[39;00m step \u001b[39min\u001b[39;00m tqdm(\u001b[39mrange\u001b[39m(steps)):\n\u001b[0;32m---> <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=21'>22</a>\u001b[0m     time_step, policy_state \u001b[39m=\u001b[39m collect_driver\u001b[39m.\u001b[39;49mrun(\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=22'>23</a>\u001b[0m         time_step\u001b[39m=\u001b[39;49mtime_step,\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=23'>24</a>\u001b[0m         policy_state\u001b[39m=\u001b[39;49mpolicy_state,\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=24'>25</a>\u001b[0m         maximum_iterations\u001b[39m=\u001b[39;49m\u001b[39m200\u001b[39;49m,\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=25'>26</a>\u001b[0m     )\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=27'>28</a>\u001b[0m     experience \u001b[39m=\u001b[39m replay_buffer\u001b[39m.\u001b[39mgather_all()\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/ellkrauze/projects/gc-ml/main_ppo.ipynb#Y434sZmlsZQ%3D%3D?line=28'>29</a>\u001b[0m     train_loss \u001b[39m=\u001b[39m _agent\u001b[39m.\u001b[39mtrain(experience)\n",
-      "File \u001b[0;32m~/projects/gc-ml/gc-ml-env/lib/python3.8/site-packages/tf_agents/drivers/dynamic_episode_driver.py:211\u001b[0m, in \u001b[0;36mDynamicEpisodeDriver.run\u001b[0;34m(self, time_step, policy_state, num_episodes, maximum_iterations)\u001b[0m\n\u001b[1;32m    175\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mrun\u001b[39m(\u001b[39mself\u001b[39m,\n\u001b[1;32m    176\u001b[0m         time_step\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m,\n\u001b[1;32m    177\u001b[0m         policy_state\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m,\n\u001b[1;32m    178\u001b[0m         num_episodes\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m,\n\u001b[1;32m    179\u001b[0m         maximum_iterations\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m):\n\u001b[1;32m    180\u001b[0m \u001b[39m  \u001b[39m\u001b[39m\"\"\"Takes episodes in the environment using the policy and update observers.\u001b[39;00m\n\u001b[1;32m    181\u001b[0m \n\u001b[1;32m    182\u001b[0m \u001b[39m  If `time_step` and `policy_state` are not provided, `run` will reset the\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    209\u001b[0m \u001b[39m    policy_state: Tensor with final step policy state.\u001b[39;00m\n\u001b[1;32m    210\u001b[0m \u001b[39m  \"\"\"\u001b[39;00m\n\u001b[0;32m--> 211\u001b[0m   \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_run_fn(\n\u001b[1;32m    212\u001b[0m       time_step\u001b[39m=\u001b[39;49mtime_step,\n\u001b[1;32m    213\u001b[0m       policy_state\u001b[39m=\u001b[39;49mpolicy_state,\n\u001b[1;32m    214\u001b[0m       num_episodes\u001b[39m=\u001b[39;49mnum_episodes,\n\u001b[1;32m    215\u001b[0m       maximum_iterations\u001b[39m=\u001b[39;49mmaximum_iterations)\n",
-      "File \u001b[0;32m~/projects/gc-ml/gc-ml-env/lib/python3.8/site-packages/tf_agents/utils/common.py:188\u001b[0m, in \u001b[0;36mfunction_in_tf1.<locals>.maybe_wrap.<locals>.with_check_resource_vars\u001b[0;34m(*fn_args, **fn_kwargs)\u001b[0m\n\u001b[1;32m    184\u001b[0m check_tf1_allowed()\n\u001b[1;32m    185\u001b[0m \u001b[39mif\u001b[39;00m has_eager_been_enabled():\n\u001b[1;32m    186\u001b[0m   \u001b[39m# We're either in eager mode or in tf.function mode (no in-between); so\u001b[39;00m\n\u001b[1;32m    187\u001b[0m   \u001b[39m# autodep-like behavior is already expected of fn.\u001b[39;00m\n\u001b[0;32m--> 188\u001b[0m   \u001b[39mreturn\u001b[39;00m fn(\u001b[39m*\u001b[39;49mfn_args, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mfn_kwargs)\n\u001b[1;32m    189\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m resource_variables_enabled():\n\u001b[1;32m    190\u001b[0m   \u001b[39mraise\u001b[39;00m \u001b[39mRuntimeError\u001b[39;00m(MISSING_RESOURCE_VARIABLES_ERROR)\n",
-      "File \u001b[0;32m~/projects/gc-ml/gc-ml-env/lib/python3.8/site-packages/tf_agents/drivers/dynamic_episode_driver.py:231\u001b[0m, in \u001b[0;36mDynamicEpisodeDriver._run\u001b[0;34m(self, time_step, policy_state, num_episodes, maximum_iterations)\u001b[0m\n\u001b[1;32m    227\u001b[0m   policy_state \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpolicy\u001b[39m.\u001b[39mget_initial_state(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39menv\u001b[39m.\u001b[39mbatch_size)\n\u001b[1;32m    229\u001b[0m \u001b[39m# Batch dim should be first index of tensors during data\u001b[39;00m\n\u001b[1;32m    230\u001b[0m \u001b[39m# collection.\u001b[39;00m\n\u001b[0;32m--> 231\u001b[0m batch_dims \u001b[39m=\u001b[39m nest_utils\u001b[39m.\u001b[39;49mget_outer_shape(time_step,\n\u001b[1;32m    232\u001b[0m                                         \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49menv\u001b[39m.\u001b[39;49mtime_step_spec())\n\u001b[1;32m    233\u001b[0m counter \u001b[39m=\u001b[39m tf\u001b[39m.\u001b[39mzeros(batch_dims, tf\u001b[39m.\u001b[39mint32)\n\u001b[1;32m    235\u001b[0m num_episodes \u001b[39m=\u001b[39m num_episodes \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_num_episodes\n",
-      "File \u001b[0;32m~/projects/gc-ml/gc-ml-env/lib/python3.8/site-packages/tf_agents/utils/nest_utils.py:831\u001b[0m, in \u001b[0;36mget_outer_shape\u001b[0;34m(nested_tensor, spec)\u001b[0m\n\u001b[1;32m    829\u001b[0m \u001b[39m# Check tensors have same batch shape.\u001b[39;00m\n\u001b[1;32m    830\u001b[0m num_outer_dims \u001b[39m=\u001b[39m (\u001b[39mlen\u001b[39m(first_tensor\u001b[39m.\u001b[39mshape) \u001b[39m-\u001b[39m \u001b[39mlen\u001b[39m(first_spec\u001b[39m.\u001b[39mshape))\n\u001b[0;32m--> 831\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m is_batched_nested_tensors(\n\u001b[1;32m    832\u001b[0m     nested_tensor, spec, num_outer_dims\u001b[39m=\u001b[39;49mnum_outer_dims, check_dtypes\u001b[39m=\u001b[39;49m\u001b[39mFalse\u001b[39;49;00m):\n\u001b[1;32m    833\u001b[0m   \u001b[39mreturn\u001b[39;00m tf\u001b[39m.\u001b[39mconstant([], dtype\u001b[39m=\u001b[39mtf\u001b[39m.\u001b[39mint32)\n\u001b[1;32m    835\u001b[0m \u001b[39mreturn\u001b[39;00m tf\u001b[39m.\u001b[39mshape(\u001b[39minput\u001b[39m\u001b[39m=\u001b[39mfirst_tensor)[:num_outer_dims]\n",
-      "File \u001b[0;32m~/projects/gc-ml/gc-ml-env/lib/python3.8/site-packages/tf_agents/utils/nest_utils.py:546\u001b[0m, in \u001b[0;36mis_batched_nested_tensors\u001b[0;34m(tensors, specs, num_outer_dims, allow_extra_fields, check_dtypes)\u001b[0m\n\u001b[1;32m    541\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mall\u001b[39m(\n\u001b[1;32m    542\u001b[0m     discrepancy \u001b[39m==\u001b[39m tensor_ndims_discrepancy[\u001b[39m0\u001b[39m]\n\u001b[1;32m    543\u001b[0m     \u001b[39mfor\u001b[39;00m discrepancy \u001b[39min\u001b[39;00m tensor_ndims_discrepancy) \u001b[39mand\u001b[39;00m \u001b[39mall\u001b[39m(tensor_matches_spec):\n\u001b[1;32m    544\u001b[0m   \u001b[39mreturn\u001b[39;00m \u001b[39mFalse\u001b[39;00m\n\u001b[0;32m--> 546\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\n\u001b[1;32m    547\u001b[0m     \u001b[39m'\u001b[39m\u001b[39mReceived a mix of batched and unbatched Tensors, or Tensors\u001b[39m\u001b[39m'\u001b[39m\n\u001b[1;32m    548\u001b[0m     \u001b[39m'\u001b[39m\u001b[39m are not compatible with Specs.  num_outer_dims: \u001b[39m\u001b[39m%d\u001b[39;00m\u001b[39m.\u001b[39m\u001b[39m\\n\u001b[39;00m\u001b[39m'\u001b[39m\n\u001b[1;32m    549\u001b[0m     \u001b[39m'\u001b[39m\u001b[39mSaw tensor_shapes:\u001b[39m\u001b[39m\\n\u001b[39;00m\u001b[39m   \u001b[39m\u001b[39m%s\u001b[39;00m\u001b[39m\\n\u001b[39;00m\u001b[39m'\u001b[39m\n\u001b[1;32m    550\u001b[0m     \u001b[39m'\u001b[39m\u001b[39mAnd spec_shapes:\u001b[39m\u001b[39m\\n\u001b[39;00m\u001b[39m   \u001b[39m\u001b[39m%s\u001b[39;00m\u001b[39m'\u001b[39m \u001b[39m%\u001b[39m\n\u001b[1;32m    551\u001b[0m     (num_outer_dims, tf\u001b[39m.\u001b[39mnest\u001b[39m.\u001b[39mpack_sequence_as(specs, tensor_shapes),\n\u001b[1;32m    552\u001b[0m      tf\u001b[39m.\u001b[39mnest\u001b[39m.\u001b[39mpack_sequence_as(specs, spec_shapes)))\n",
-      "\u001b[0;31mValueError\u001b[0m: Received a mix of batched and unbatched Tensors, or Tensors are not compatible with Specs.  num_outer_dims: 1.\nSaw tensor_shapes:\n   TimeStep(\n{'discount': TensorShape([1]),\n 'observation': TensorShape([1]),\n 'reward': TensorShape([1]),\n 'step_type': TensorShape([1])})\nAnd spec_shapes:\n   TimeStep(\n{'discount': TensorShape([]),\n 'observation': TensorShape([7]),\n 'reward': TensorShape([]),\n 'step_type': TensorShape([])})"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 0: loss = 28.902631759643555, reward = 0.009563921019434929\n"
      ]
-    }
-   ],
-   "source": [
-    "# Train on first\n",
-    "collect_driver, replay_buffer = get_rb_and_cd(train_env, agent)\n",
-    "loss, observations, rewards = train(\n",
-    "    agent, train_env, train_env_copy, collect_driver, replay_buffer, steps = num_steps, eval_interval=100)\n",
-    "\n",
-    "print(\"AVG RETURN - KAFKA:\", \n",
-    "      compute_avg_return_episodic(train_env_2, agent.policy, num_episodes=50))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "metadata": {},
-   "outputs": [
+    },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.75it/s]\n",
-      "  0%|          | 1/3000 [00:12<10:45:41, 12.92s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.67it/s]/s] \n",
+      "  2%|▏         | 101/5000 [01:19<5:27:18,  4.01s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 0: loss = 0.23992592096328735, reward = -1.094357967376709\n"
+      "step = 100: loss = -0.12217696011066437, reward = 0.10741065442562103\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:12<00:00,  1.65it/s]s/it]\n",
-      "  3%|▎         | 101/3000 [02:48<4:07:08,  5.12s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.69it/s]/s]  \n",
+      "  4%|▍         | 201/5000 [02:11<5:17:22,  3.97s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 100: loss = -0.04756331071257591, reward = -1.095718264579773\n"
+      "step = 200: loss = -0.12155486643314362, reward = -0.054414473474025726\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:12<00:00,  1.56it/s]s/it]\n",
-      "  7%|▋         | 201/3000 [05:32<4:20:18,  5.58s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.64it/s]/s]  \n",
+      "  6%|▌         | 301/5000 [03:05<5:19:49,  4.08s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 200: loss = 0.01569918729364872, reward = -1.095718264579773\n"
+      "step = 300: loss = -0.14047378301620483, reward = -0.1808028370141983\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.78it/s]s/it]\n",
-      " 10%|█         | 301/3000 [08:14<3:35:36,  4.79s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]/s]  \n",
+      "  8%|▊         | 401/5000 [03:55<4:51:41,  3.81s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 300: loss = 0.027913261204957962, reward = -1.095718264579773\n"
+      "step = 400: loss = -0.12208157032728195, reward = 0.13025769591331482\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.78it/s]s/it]\n",
-      " 13%|█▎        | 401/3000 [10:51<3:28:08,  4.81s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.67it/s]/s]  \n",
+      " 10%|█         | 501/5000 [04:46<4:57:33,  3.97s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 400: loss = 0.026388660073280334, reward = -1.095718264579773\n"
+      "step = 500: loss = -0.12516961991786957, reward = -0.047113142907619476\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]s/it]\n",
-      " 17%|█▋        | 501/3000 [13:29<3:30:47,  5.06s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.66it/s]/s]  \n",
+      " 12%|█▏        | 601/5000 [05:40<4:58:12,  4.07s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 500: loss = 0.050847191363573074, reward = -1.095718264579773\n"
+      "step = 600: loss = -0.13263054192066193, reward = 0.023856637999415398\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.71it/s]it]  \n",
-      " 20%|██        | 601/3000 [16:08<3:19:06,  4.98s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.73it/s]/s]  \n",
+      " 14%|█▍        | 701/5000 [06:31<4:36:40,  3.86s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 600: loss = 0.05089189484715462, reward = -1.095718264579773\n"
+      "step = 700: loss = -0.12135445326566696, reward = -0.09978403896093369\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.78it/s]it]  \n",
-      " 23%|██▎       | 701/3000 [18:43<3:06:54,  4.88s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.71it/s]/s]  \n",
+      " 16%|█▌        | 801/5000 [07:22<4:32:15,  3.89s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 700: loss = 0.05062983185052872, reward = -1.095718264579773\n"
+      "step = 800: loss = -0.12417945265769958, reward = -0.12913194298744202\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.71it/s]it]  \n",
-      " 27%|██▋       | 801/3000 [21:22<3:01:49,  4.96s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.74it/s]/s]  \n",
+      " 18%|█▊        | 901/5000 [08:13<4:21:34,  3.83s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 800: loss = 0.05028387904167175, reward = -1.095718264579773\n"
+      "step = 900: loss = -0.12012037634849548, reward = -0.0812155231833458\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.78it/s]it]  \n",
-      " 30%|███       | 901/3000 [23:59<2:47:50,  4.80s/it]"
+      "100%|██████████| 20/20 [00:13<00:00,  1.51it/s]t/s] \n",
+      " 20%|██        | 1001/5000 [09:06<4:55:30,  4.43s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 900: loss = 0.04961911588907242, reward = -1.095718264579773\n"
+      "step = 1000: loss = -0.12780579924583435, reward = 0.04057605192065239\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]/it] \n",
-      " 33%|███▎      | 1001/3000 [26:36<2:39:13,  4.78s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.68it/s]t/s]  \n",
+      " 22%|██▏       | 1101/5000 [09:57<4:17:19,  3.96s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1000: loss = 0.04881724342703819, reward = -1.095718264579773\n"
+      "step = 1100: loss = -0.15671901404857635, reward = -0.04562435299158096\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]/it]  \n",
-      " 37%|███▋      | 1101/3000 [29:08<2:30:42,  4.76s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.67it/s]t/s]  \n",
+      " 24%|██▍       | 1201/5000 [10:53<4:18:10,  4.08s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1100: loss = 0.04760364443063736, reward = -1.095718264579773\n"
+      "step = 1200: loss = -0.12041907012462616, reward = 0.04573701694607735\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]/it]  \n",
-      " 40%|████      | 1201/3000 [31:42<2:22:38,  4.76s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.70it/s]t/s]  \n",
+      " 26%|██▌       | 1301/5000 [11:46<4:03:05,  3.94s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1200: loss = 0.04574316367506981, reward = -1.095718264579773\n"
+      "step = 1300: loss = -0.11761971563100815, reward = -0.0033242765348404646\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]/it]  \n",
-      " 43%|████▎     | 1301/3000 [34:14<2:21:03,  4.98s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.71it/s]t/s]  \n",
+      " 28%|██▊       | 1401/5000 [12:39<3:53:54,  3.90s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1300: loss = 0.04151776432991028, reward = -1.095718264579773\n"
+      "step = 1400: loss = -0.11471748352050781, reward = 0.0010996530763804913\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]/it]  \n",
-      " 47%|████▋     | 1401/3000 [36:47<2:07:11,  4.77s/it]"
+      "100%|██████████| 20/20 [00:17<00:00,  1.13it/s]t/s]  \n",
+      " 30%|███       | 1501/5000 [13:38<5:33:23,  5.72s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1400: loss = 0.0467989556491375, reward = -1.095718264579773\n"
+      "step = 1500: loss = -0.11971862614154816, reward = -0.04055100679397583\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.73it/s]/it]  \n",
-      " 50%|█████     | 1501/3000 [39:21<2:02:05,  4.89s/it]"
+      "100%|██████████| 20/20 [00:18<00:00,  1.05it/s]t/s]  \n",
+      " 32%|███▏      | 1601/5000 [14:42<5:44:22,  6.08s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1500: loss = 0.047061603516340256, reward = -1.095718264579773\n"
+      "step = 1600: loss = -0.11644572764635086, reward = -0.15625840425491333\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]/it]  \n",
-      " 53%|█████▎    | 1601/3000 [41:54<1:51:30,  4.78s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.71it/s]t/s]  \n",
+      " 34%|███▍      | 1701/5000 [15:34<3:33:43,  3.89s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1600: loss = 0.04712197184562683, reward = -1.095718264579773\n"
+      "step = 1700: loss = -0.11681109666824341, reward = -0.21186129748821259\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]/it]  \n",
-      " 57%|█████▋    | 1701/3000 [44:27<1:43:34,  4.78s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.67it/s]t/s]  \n",
+      " 36%|███▌      | 1801/5000 [16:26<3:33:53,  4.01s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1700: loss = 0.04722379893064499, reward = -1.095718264579773\n"
+      "step = 1800: loss = -0.1096460372209549, reward = -0.12031445652246475\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:12<00:00,  1.63it/s]/it]  \n",
-      " 60%|██████    | 1801/3000 [47:01<1:42:02,  5.11s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.71it/s]t/s]  \n",
+      " 38%|███▊      | 1901/5000 [17:18<3:20:41,  3.89s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1800: loss = 0.046851687133312225, reward = -1.095718264579773\n"
+      "step = 1900: loss = -0.07287707179784775, reward = -0.1658892035484314\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.70it/s]/it]  \n",
-      " 63%|██████▎   | 1901/3000 [49:56<1:30:36,  4.95s/it]"
+      "100%|██████████| 20/20 [00:14<00:00,  1.34it/s]t/s]  \n",
+      " 40%|████      | 2001/5000 [18:16<4:03:25,  4.87s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1900: loss = 0.04698016494512558, reward = -1.095718264579773\n"
+      "step = 2000: loss = -0.11350805312395096, reward = -0.08294306695461273\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]/it]  \n",
-      " 67%|██████▋   | 2001/3000 [52:29<1:18:55,  4.74s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]t/s]  \n",
+      " 42%|████▏     | 2101/5000 [19:07<3:02:34,  3.78s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2000: loss = 0.046965342015028, reward = -1.095718264579773\n"
+      "step = 2100: loss = -0.11182614415884018, reward = -0.20583422482013702\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]/it]  \n",
-      " 70%|███████   | 2101/3000 [55:04<1:11:31,  4.77s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]t/s]  \n",
+      " 44%|████▍     | 2201/5000 [19:57<2:56:22,  3.78s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2100: loss = 0.04709947854280472, reward = -1.095718264579773\n"
+      "step = 2200: loss = -0.11087335646152496, reward = -0.12639972567558289\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]/it]  \n",
-      " 73%|███████▎  | 2201/3000 [57:36<1:03:22,  4.76s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.58it/s]t/s]  \n",
+      " 46%|████▌     | 2301/5000 [20:49<3:13:17,  4.30s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2200: loss = 0.034701552242040634, reward = -1.095718264579773\n"
+      "step = 2300: loss = -0.09479192644357681, reward = -0.05476980656385422\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.75it/s]3s/it]\n",
-      " 77%|███████▋  | 2301/3000 [1:00:13<57:22,  4.93s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.66it/s]t/s]  \n",
+      " 48%|████▊     | 2401/5000 [21:41<2:54:56,  4.04s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2300: loss = 0.0582413375377655, reward = -1.095718264579773\n"
+      "step = 2400: loss = -0.0014683204935863614, reward = -0.16155274212360382\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.71it/s]3s/it]\n",
-      " 80%|████████  | 2401/3000 [1:02:56<49:52,  5.00s/it]"
+      "100%|██████████| 20/20 [00:13<00:00,  1.46it/s]t/s]  \n",
+      " 50%|█████     | 2501/5000 [22:37<3:08:39,  4.53s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2400: loss = 0.0011234291596338153, reward = -1.095718264579773\n"
+      "step = 2500: loss = -0.03699420019984245, reward = -0.20467133820056915\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:10<00:00,  1.83it/s]9s/it]    \n",
-      " 83%|████████▎ | 2501/3000 [1:41:12<43:19,  5.21s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.75it/s]t/s]  \n",
+      " 52%|█████▏    | 2601/5000 [23:29<2:36:24,  3.91s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2500: loss = 0.059934187680482864, reward = -1.095718264579773\n"
+      "step = 2600: loss = -0.10927896946668625, reward = -0.31928008794784546\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.68it/s]1s/it]  \n",
-      " 87%|████████▋ | 2601/3000 [1:45:04<33:39,  5.06s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]t/s]  \n",
+      " 54%|█████▍    | 2701/5000 [24:19<2:24:42,  3.78s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2600: loss = -0.014887774363160133, reward = -1.095718264579773\n"
+      "step = 2700: loss = -0.10431338846683502, reward = -0.15599094331264496\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]0s/it]\n",
-      " 90%|█████████ | 2701/3000 [1:47:42<23:39,  4.75s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]t/s]  \n",
+      " 56%|█████▌    | 2801/5000 [25:09<2:18:55,  3.79s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2700: loss = 0.013810863718390465, reward = -0.7224888801574707\n"
+      "step = 2800: loss = -0.11629707366228104, reward = -0.24302449822425842\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.71it/s]8s/it]\n",
-      " 93%|█████████▎| 2801/3000 [1:50:18<16:30,  4.98s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.70it/s]t/s]  \n",
+      " 58%|█████▊    | 2901/5000 [26:01<2:17:37,  3.93s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2800: loss = 0.017519423738121986, reward = -0.7224825620651245\n"
+      "step = 2900: loss = -0.09800298511981964, reward = -0.4591086804866791\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]9s/it]\n",
-      " 97%|█████████▋| 2901/3000 [1:52:50<07:49,  4.74s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.72it/s]t/s]  \n",
+      " 60%|██████    | 3001/5000 [26:51<2:09:36,  3.89s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2900: loss = 0.020173329859972, reward = -0.7224825620651245\n"
+      "step = 3000: loss = -0.10718017816543579, reward = -0.2882995009422302\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 3000/3000 [1:55:14<00:00,  2.30s/it]\n",
-      "100%|██████████| 50/50 [00:35<00:00,  1.42it/s]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.78it/s]t/s]  \n",
+      " 62%|██████▏   | 3101/5000 [27:41<1:59:01,  3.76s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "AVG RETURN - KAFKA: -0.72248244\n"
+      "step = 3100: loss = -0.10472153127193451, reward = -0.29563093185424805\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\n"
+      "100%|██████████| 20/20 [00:14<00:00,  1.41it/s]t/s]  \n",
+      " 64%|██████▍   | 3201/5000 [28:37<2:20:58,  4.70s/it]"
      ]
-    }
-   ],
-   "source": [
-    "# Train on second\n",
-    "collect_driver, replay_buffer = get_rb_and_cd(train_env_2, agent)\n",
-    "loss, observations, rewards = train(\n",
-    "    agent, train_env_2, train_env_2_copy, collect_driver, replay_buffer, steps = num_steps, eval_interval=100)\n",
-    "\n",
-    "print(\"AVG RETURN - KAFKA:\", \n",
-    "      compute_avg_return_episodic(train_env_2, agent.policy, num_episodes=50))\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "metadata": {},
-   "outputs": [
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3200: loss = -0.11518708616495132, reward = -0.15007063746452332\n"
+     ]
+    },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 50/50 [00:28<00:00,  1.75it/s]\n"
+      "100%|██████████| 20/20 [00:14<00:00,  1.39it/s]t/s]  \n",
+      " 66%|██████▌   | 3301/5000 [29:41<2:15:06,  4.77s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "AVG RETURN - TEST: -0.09791789\n"
+      "step = 3300: loss = -0.08996358513832092, reward = -0.20825421810150146\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.69it/s]\n",
-      "  0%|          | 1/3000 [00:13<11:13:44, 13.48s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.73it/s]t/s]  \n",
+      " 68%|██████▊   | 3401/5000 [30:35<1:42:30,  3.85s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 0: loss = -0.04970337077975273, reward = -0.06765811145305634\n"
+      "step = 3400: loss = -0.06932719796895981, reward = -0.09602121263742447\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.69it/s]s/it]\n",
-      "  3%|▎         | 101/3000 [02:58<3:59:28,  4.96s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.75it/s]t/s]  \n",
+      " 70%|███████   | 3501/5000 [31:26<1:35:16,  3.81s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 100: loss = -0.002319173188880086, reward = -0.11809100955724716\n"
+      "step = 3500: loss = 0.08029784262180328, reward = -0.14908118546009064\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.72it/s]s/it]\n",
-      "  7%|▋         | 201/3000 [05:34<3:49:03,  4.91s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.69it/s]t/s]  \n",
+      " 72%|███████▏  | 3601/5000 [32:17<1:31:52,  3.94s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 200: loss = -0.001999561209231615, reward = -0.11809100955724716\n"
+      "step = 3600: loss = -0.10365701466798782, reward = -0.21505753695964813\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.73it/s]/s]  \n",
-      " 10%|█         | 301/3000 [07:57<2:55:25,  3.90s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.72it/s]t/s]  \n",
+      " 74%|███████▍  | 3701/5000 [33:07<1:23:31,  3.86s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 300: loss = 0.637097179889679, reward = -0.11809100955724716\n"
+      "step = 3700: loss = -0.09262917190790176, reward = -0.19250598549842834\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.67it/s]/s]  \n",
-      " 13%|█▎        | 401/3000 [08:48<2:53:10,  4.00s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.75it/s]t/s]  \n",
+      " 76%|███████▌  | 3801/5000 [33:57<1:16:11,  3.81s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 400: loss = 0.3378632962703705, reward = 0.1518501341342926\n"
+      "step = 3800: loss = -0.09590969979763031, reward = -0.17102284729480743\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.78it/s]/s]  \n",
-      " 17%|█▋        | 501/3000 [09:44<2:40:10,  3.85s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.71it/s]t/s]  \n",
+      " 78%|███████▊  | 3901/5000 [34:47<1:11:16,  3.89s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 500: loss = 0.29114043712615967, reward = 0.1518501341342926\n"
+      "step = 3900: loss = -0.09566880762577057, reward = -0.2066037952899933\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.72it/s]/s]  \n",
-      " 20%|██        | 601/3000 [10:46<2:37:43,  3.94s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.78it/s]t/s]  \n",
+      " 80%|████████  | 4001/5000 [35:37<1:02:21,  3.75s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 600: loss = 0.27805569767951965, reward = 0.1518501341342926\n"
+      "step = 4000: loss = -0.09816298633813858, reward = -0.24682223796844482\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]/s]  \n",
-      " 23%|██▎       | 701/3000 [11:45<2:25:07,  3.79s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.74it/s]t/s]  \n",
+      " 82%|████████▏ | 4101/5000 [36:29<57:54,  3.86s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 700: loss = 0.2481951117515564, reward = 0.1518501341342926\n"
+      "step = 4100: loss = -0.10664721578359604, reward = -0.08116856217384338\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.80it/s]/s]  \n",
-      " 27%|██▋       | 801/3000 [12:51<2:23:01,  3.90s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.72it/s]t/s]\n",
+      " 84%|████████▍ | 4201/5000 [37:21<51:33,  3.87s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 800: loss = 0.26682373881340027, reward = 0.1518501341342926\n"
+      "step = 4200: loss = -0.07868582010269165, reward = -0.04766662418842316\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:12<00:00,  1.63it/s]/s]  \n",
-      " 30%|███       | 901/3000 [13:55<2:25:32,  4.16s/it]"
+      "100%|██████████| 20/20 [00:13<00:00,  1.46it/s]t/s]\n",
+      " 86%|████████▌ | 4301/5000 [38:15<52:52,  4.54s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 900: loss = 0.2887151837348938, reward = 0.1518501341342926\n"
+      "step = 4300: loss = -0.07521019876003265, reward = -0.09636393934488297\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.81it/s]t/s] \n",
-      " 33%|███▎      | 1001/3000 [15:00<2:04:19,  3.73s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.68it/s]t/s]\n",
+      " 88%|████████▊ | 4401/5000 [39:07<40:02,  4.01s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1000: loss = 0.24205642938613892, reward = 0.1518501341342926\n"
+      "step = 4400: loss = -0.10130394250154495, reward = -0.1365879327058792\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]t/s]  \n",
-      " 37%|███▋      | 1101/3000 [16:01<2:01:58,  3.85s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.69it/s]t/s]\n",
+      " 90%|█████████ | 4501/5000 [39:59<32:47,  3.94s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1100: loss = 0.23392656445503235, reward = 0.1518501341342926\n"
+      "step = 4500: loss = -0.10128697752952576, reward = -0.011847374960780144\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.80it/s]t/s]  \n",
-      " 40%|████      | 1201/3000 [17:02<1:54:06,  3.81s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.72it/s]t/s]\n",
+      " 92%|█████████▏| 4601/5000 [40:49<25:52,  3.89s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1200: loss = 0.20439070463180542, reward = 0.1518501341342926\n"
+      "step = 4600: loss = -0.10102717578411102, reward = -0.12869268655776978\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.70it/s]t/s]  \n",
-      " 43%|████▎     | 1301/3000 [18:01<1:53:04,  3.99s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.72it/s]t/s]\n",
+      " 94%|█████████▍| 4701/5000 [41:42<19:20,  3.88s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1300: loss = 0.2279774695634842, reward = 0.1518501341342926\n"
+      "step = 4700: loss = -0.10895377397537231, reward = 0.032198309898376465\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.81it/s]t/s]  \n",
-      " 47%|████▋     | 1401/3000 [19:05<1:41:22,  3.80s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.63it/s]t/s]\n",
+      " 96%|█████████▌| 4801/5000 [42:33<13:27,  4.06s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1400: loss = 0.2342691570520401, reward = 0.1518501341342926\n"
+      "step = 4800: loss = -0.10902483761310577, reward = -0.06275109946727753\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.80it/s]t/s]  \n",
-      " 50%|█████     | 1501/3000 [20:05<1:33:27,  3.74s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.74it/s]t/s]\n",
+      " 98%|█████████▊| 4901/5000 [43:26<06:18,  3.82s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1500: loss = 0.23698203265666962, reward = 0.1518501341342926\n"
+      "step = 4900: loss = -0.12051510065793991, reward = -0.05913602560758591\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]t/s]  \n",
-      " 53%|█████▎    | 1601/3000 [21:05<1:29:33,  3.84s/it]"
+      "100%|██████████| 5000/5000 [44:05<00:00,  1.89it/s]\n",
+      "100%|██████████| 50/50 [00:28<00:00,  1.77it/s]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1600: loss = 0.21993388235569, reward = 0.1518501341342926\n"
+      "AVG RETURN - KAFKA: 0.0030280044\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.75it/s]t/s]  \n",
-      " 57%|█████▋    | 1701/3000 [22:06<1:26:33,  4.00s/it]"
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Train on first\n",
+    "collect_driver, replay_buffer = get_cd_and_rb(train_env, agent)\n",
+    "loss, observations, rewards = train(\n",
+    "    agent, train_env, train_env_copy, collect_driver, replay_buffer, steps = num_steps, eval_interval=100)\n",
+    "\n",
+    "print(\"AVG RETURN - KAFKA:\", \n",
+    "      compute_avg_return_episodic(train_env_2, agent.policy, num_episodes=50))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plot_training(loss, rewards, num_steps, 100)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 20/20 [00:13<00:00,  1.51it/s]\n",
+      "  0%|          | 1/5000 [00:18<26:03:03, 18.76s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1700: loss = 0.239291712641716, reward = 0.1518501341342926\n"
+      "step = 0: loss = 2.3935961723327637, reward = -0.08524542301893234\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.81it/s]t/s]  \n",
-      " 60%|██████    | 1801/3000 [23:04<1:15:58,  3.80s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.71it/s]/s] \n",
+      "  2%|▏         | 101/5000 [01:09<5:17:43,  3.89s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1800: loss = 0.19207340478897095, reward = 0.1518501341342926\n"
+      "step = 100: loss = -0.12164812535047531, reward = -0.09026005119085312\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.75it/s]t/s]  \n",
-      " 63%|██████▎   | 1901/3000 [24:04<1:09:45,  3.81s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.73it/s]/s]  \n",
+      "  4%|▍         | 201/5000 [01:59<5:08:48,  3.86s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1900: loss = 0.19634351134300232, reward = 0.1518501341342926\n"
+      "step = 200: loss = -0.12125816941261292, reward = -0.02092362567782402\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.71it/s]t/s]  \n",
-      " 67%|██████▋   | 2001/3000 [25:05<1:06:28,  3.99s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.73it/s]/s]  \n",
+      "  6%|▌         | 301/5000 [02:51<5:02:07,  3.86s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2000: loss = 0.18686339259147644, reward = 0.1518501341342926\n"
+      "step = 300: loss = -0.12100689858198166, reward = -0.019010009244084358\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]t/s]  \n",
-      " 70%|███████   | 2101/3000 [26:08<57:38,  3.85s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.66it/s]/s]  \n",
+      "  8%|▊         | 401/5000 [03:42<5:07:32,  4.01s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2100: loss = 0.20166490972042084, reward = 0.1518501341342926\n"
+      "step = 400: loss = -0.12203968316316605, reward = -0.1057734340429306\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.78it/s]t/s]\n",
-      " 73%|███████▎  | 2201/3000 [27:07<51:20,  3.86s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.64it/s]/s]  \n",
+      " 10%|█         | 501/5000 [04:35<5:10:42,  4.14s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2200: loss = 0.18926644325256348, reward = 0.1518501341342926\n"
+      "step = 500: loss = 0.5449185967445374, reward = 0.20654818415641785\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.78it/s]t/s]\n",
-      " 77%|███████▋  | 2301/3000 [28:06<44:31,  3.82s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.73it/s]/s]  \n",
+      " 12%|█▏        | 601/5000 [05:27<4:42:49,  3.86s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2300: loss = 0.20836588740348816, reward = 0.1518501341342926\n"
+      "step = 600: loss = 0.12020786851644516, reward = -0.08972353488206863\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.78it/s]t/s]\n",
-      " 80%|████████  | 2401/3000 [29:06<38:39,  3.87s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.73it/s]/s]  \n",
+      " 14%|█▍        | 701/5000 [06:17<4:36:43,  3.86s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2400: loss = 0.13284115493297577, reward = 0.1518501341342926\n"
+      "step = 700: loss = 0.1178484857082367, reward = 0.04620600491762161\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]t/s]\n",
-      " 83%|████████▎ | 2501/3000 [30:08<33:17,  4.00s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.63it/s]/s]  \n",
+      " 16%|█▌        | 801/5000 [07:09<4:44:21,  4.06s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2500: loss = 0.16821995377540588, reward = 0.1518501341342926\n"
+      "step = 800: loss = 0.11423169821500778, reward = 0.05797123908996582\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:12<00:00,  1.66it/s]t/s]\n",
-      " 87%|████████▋ | 2601/3000 [31:07<27:03,  4.07s/it]"
+      "100%|██████████| 20/20 [00:13<00:00,  1.50it/s]/s]  \n",
+      " 18%|█▊        | 901/5000 [08:09<5:00:31,  4.40s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2600: loss = 0.14804477989673615, reward = 0.1518501341342926\n"
+      "step = 900: loss = 0.11202795803546906, reward = 0.08857231587171555\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.81it/s]t/s]\n",
-      " 90%|█████████ | 2701/3000 [32:06<18:35,  3.73s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.61it/s]t/s] \n",
+      " 20%|██        | 1001/5000 [09:05<4:46:14,  4.29s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2700: loss = 0.10050634294748306, reward = 0.1518501341342926\n"
+      "step = 1000: loss = 0.1183023676276207, reward = 0.06645048409700394\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.74it/s]t/s]\n",
-      " 93%|█████████▎| 2801/3000 [33:07<12:46,  3.85s/it]"
+      "100%|██████████| 20/20 [00:27<00:00,  1.38s/it]3s/it]\n",
+      " 22%|██▏       | 1101/5000 [10:26<10:29:55,  9.69s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2800: loss = 0.07741110026836395, reward = 0.1518501341342926\n"
+      "step = 1100: loss = 0.11778132617473602, reward = 0.084475576877594\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]t/s]\n",
-      " 97%|█████████▋| 2901/3000 [34:07<06:22,  3.87s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.68it/s]t/s]   \n",
+      " 24%|██▍       | 1201/5000 [11:28<4:33:47,  4.32s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2900: loss = 0.2126760482788086, reward = 0.1518501341342926\n"
+      "step = 1200: loss = 0.11349839717149734, reward = 0.23287606239318848\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 3000/3000 [34:52<00:00,  1.43it/s]\n",
-      "100%|██████████| 50/50 [00:28<00:00,  1.77it/s]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.64it/s]t/s]  \n",
+      " 26%|██▌       | 1301/5000 [12:21<4:08:57,  4.04s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "AVG RETURN - TEST: 0.15185018\n"
+      "step = 1300: loss = 0.09798666089773178, reward = 0.15252044796943665\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\n"
+      "100%|██████████| 20/20 [00:11<00:00,  1.73it/s]t/s]  \n",
+      " 28%|██▊       | 1401/5000 [13:14<3:51:58,  3.87s/it]"
      ]
-    }
-   ],
-   "source": [
-    "\n",
-    "print(\"AVG RETURN - TEST:\", \n",
-    "      compute_avg_return_episodic(test_env, agent.policy, num_episodes=50))\n",
-    "\n",
-    "# Test environment\n",
-    "collect_driver, replay_buffer = get_rb_and_cd(test_env, agent)\n",
-    "loss, observations, rewards = train(\n",
-    "    agent, test_env, test_env_copy, collect_driver, replay_buffer, steps = num_steps, eval_interval=100)\n",
-    "\n",
-    "print(\"AVG RETURN - TEST:\", \n",
-    "      compute_avg_return_episodic(test_env, agent.policy, num_episodes=50))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Final results."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "metadata": {},
-   "outputs": [
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1400: loss = 0.10044006258249283, reward = 0.2212250679731369\n"
+     ]
+    },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 50/50 [00:00<00:00, 74.34it/s]\n"
+      "100%|██████████| 20/20 [00:11<00:00,  1.68it/s]t/s]  \n",
+      " 30%|███       | 1501/5000 [14:09<3:53:43,  4.01s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "AVG RETURN - AVRORA: 1.2897495\n"
+      "step = 1500: loss = 0.08438204228878021, reward = 0.21633855998516083\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 50/50 [00:28<00:00,  1.78it/s]\n"
+      "100%|██████████| 20/20 [00:15<00:00,  1.27it/s]t/s]  \n",
+      " 32%|███▏      | 1601/5000 [15:05<4:49:45,  5.11s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "AVG RETURN - KAFKA: -0.6872998\n"
+      "step = 1600: loss = 0.06959390640258789, reward = 0.2215852439403534\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 50/50 [00:27<00:00,  1.79it/s]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.68it/s]t/s]  \n",
+      " 34%|███▍      | 1701/5000 [15:59<3:39:43,  4.00s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "AVG RETURN - TEST: 0.15185018\n"
+      "step = 1700: loss = 0.07805465906858444, reward = 0.2126867026090622\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\n"
+      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]t/s]  \n",
+      " 36%|███▌      | 1801/5000 [16:50<3:21:09,  3.77s/it]"
      ]
-    }
-   ],
-   "source": [
-    "print(\"AVG RETURN - AVRORA:\", \n",
-    "      compute_avg_return_episodic(train_env, agent.policy, num_episodes=50))\n",
-    "\n",
-    "print(\"AVG RETURN - KAFKA:\", \n",
-    "      compute_avg_return_episodic(train_env_2, agent.policy, num_episodes=50))\n",
-    "\n",
-    "print(\"AVG RETURN - TEST:\", \n",
-    "      compute_avg_return_episodic(test_env, agent.policy, num_episodes=50))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 32,
-   "metadata": {},
-   "outputs": [
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1800: loss = 0.11215945333242416, reward = 0.13990293443202972\n"
+     ]
+    },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]\n",
-      "  0%|          | 1/3000 [00:12<10:40:12, 12.81s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.67it/s]t/s]  \n",
+      " 38%|███▊      | 1901/5000 [17:42<3:25:01,  3.97s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 0: loss = 1.0708450078964233, reward = -0.6872997283935547\n"
+      "step = 1900: loss = 0.1106598749756813, reward = 0.24889183044433594\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.69it/s]s/it]\n",
-      "  3%|▎         | 101/3000 [02:49<4:07:36,  5.12s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.75it/s]t/s]  \n",
+      " 40%|████      | 2001/5000 [18:31<3:10:37,  3.81s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 100: loss = 0.01032012328505516, reward = -0.7224825620651245\n"
+      "step = 2000: loss = 0.07175104320049286, reward = 0.22520026564598083\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.75it/s]s/it]\n",
-      "  7%|▋         | 201/3000 [05:24<3:54:44,  5.03s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.73it/s]t/s]  \n",
+      " 42%|████▏     | 2101/5000 [19:21<3:05:44,  3.84s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 200: loss = 0.008337455801665783, reward = -0.7224825620651245\n"
+      "step = 2100: loss = 0.05647712200880051, reward = 0.2317294329404831\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:12<00:00,  1.65it/s]s/it]\n",
-      " 10%|█         | 301/3000 [08:04<3:49:26,  5.10s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]t/s]  \n",
+      " 44%|████▍     | 2201/5000 [20:11<2:56:22,  3.78s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 300: loss = 0.015153888612985611, reward = -0.7224825620651245\n"
+      "step = 2200: loss = -0.12164752930402756, reward = 0.2467513382434845\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]it]  \n",
-      " 13%|█▎        | 401/3000 [10:41<3:25:02,  4.73s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]t/s]  \n",
+      " 46%|████▌     | 2301/5000 [21:01<2:50:55,  3.80s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 400: loss = 0.04072941467165947, reward = -0.7224825620651245\n"
+      "step = 2300: loss = 0.05813376232981682, reward = 0.2371426820755005\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.82it/s]it]  \n",
-      " 17%|█▋        | 501/3000 [13:13<3:16:34,  4.72s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.74it/s]t/s]  \n",
+      " 48%|████▊     | 2401/5000 [21:50<2:46:00,  3.83s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 500: loss = 0.025839729234576225, reward = -0.7224825620651245\n"
+      "step = 2400: loss = 0.10486495494842529, reward = 0.28368085622787476\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.70it/s]it]  \n",
-      " 20%|██        | 601/3000 [15:49<3:18:07,  4.96s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]t/s]  \n",
+      " 50%|█████     | 2501/5000 [22:40<2:39:08,  3.82s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 600: loss = 0.04873916134238243, reward = -0.7224825620651245\n"
+      "step = 2500: loss = 0.10581547021865845, reward = 0.21570351719856262\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]it]  \n",
-      " 23%|██▎       | 701/3000 [18:24<3:02:58,  4.78s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.72it/s]t/s]  \n",
+      " 52%|█████▏    | 2601/5000 [23:30<2:34:59,  3.88s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 700: loss = 0.0132971853017807, reward = -0.7224825620651245\n"
+      "step = 2600: loss = 0.03669300675392151, reward = 0.2747664451599121\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]it]  \n",
-      " 27%|██▋       | 801/3000 [21:03<2:57:36,  4.85s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.75it/s]t/s]  \n",
+      " 54%|█████▍    | 2701/5000 [24:20<2:26:09,  3.81s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 800: loss = 0.025136852636933327, reward = -0.7224825620651245\n"
+      "step = 2700: loss = 0.049320586025714874, reward = 0.26521965861320496\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]it]  \n",
-      " 30%|███       | 901/3000 [23:40<2:49:57,  4.86s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.70it/s]t/s]  \n",
+      " 56%|█████▌    | 2801/5000 [25:10<2:23:52,  3.93s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 900: loss = 0.04865988716483116, reward = -0.7224825620651245\n"
+      "step = 2800: loss = 0.10751616209745407, reward = 0.03046208620071411\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]/it] \n",
-      " 33%|███▎      | 1001/3000 [26:15<2:41:14,  4.84s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]t/s]  \n",
+      " 58%|█████▊    | 2901/5000 [26:00<2:12:47,  3.80s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1000: loss = -0.060474611818790436, reward = -0.1822998821735382\n"
+      "step = 2900: loss = 0.028574436902999878, reward = -0.078873410820961\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.68it/s]/it]  \n",
-      " 37%|███▋      | 1101/3000 [28:50<2:38:56,  5.02s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]t/s]  \n",
+      " 60%|██████    | 3001/5000 [26:49<2:06:03,  3.78s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1100: loss = 0.001056360430084169, reward = -0.1822998821735382\n"
+      "step = 3000: loss = 0.11305896937847137, reward = -0.0822506695985794\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.74it/s]/it]  \n",
-      " 40%|████      | 1201/3000 [31:31<2:26:28,  4.89s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.72it/s]t/s]  \n",
+      " 62%|██████▏   | 3101/5000 [27:39<2:02:51,  3.88s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1200: loss = 0.0018581876065582037, reward = -0.1822998821735382\n"
+      "step = 3100: loss = 0.10693422704935074, reward = -0.13296742737293243\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.75it/s]/it]  \n",
-      " 43%|████▎     | 1301/3000 [34:09<2:17:57,  4.87s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]t/s]  \n",
+      " 64%|██████▍   | 3201/5000 [28:29<1:53:45,  3.79s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1300: loss = -0.0023872079327702522, reward = -0.1822998821735382\n"
+      "step = 3200: loss = 0.1026078313589096, reward = -0.054457150399684906\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.75it/s]/it]  \n",
-      " 47%|████▋     | 1401/3000 [36:44<2:10:01,  4.88s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.70it/s]t/s]  \n",
+      " 66%|██████▌   | 3301/5000 [29:21<1:50:31,  3.90s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1400: loss = 0.01805002987384796, reward = -0.1822998821735382\n"
+      "step = 3300: loss = 0.09237673878669739, reward = -0.13591960072517395\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]/it]  \n",
-      " 50%|█████     | 1501/3000 [39:19<1:58:40,  4.75s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.74it/s]t/s]  \n",
+      " 68%|██████▊   | 3401/5000 [30:11<1:42:14,  3.84s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1500: loss = -0.055307794362306595, reward = -0.1822998821735382\n"
+      "step = 3400: loss = 0.10058660060167313, reward = -0.06709173321723938\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.79it/s]/it]  \n",
-      " 53%|█████▎    | 1601/3000 [41:51<1:50:34,  4.74s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]t/s]  \n",
+      " 70%|███████   | 3501/5000 [31:00<1:34:43,  3.79s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1600: loss = 0.0010385647183284163, reward = -0.1822998821735382\n"
+      "step = 3500: loss = 0.0451681949198246, reward = -0.06473610550165176\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]/it]  \n",
-      " 57%|█████▋    | 1701/3000 [44:23<1:44:25,  4.82s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.71it/s]t/s]  \n",
+      " 72%|███████▏  | 3601/5000 [31:50<1:30:36,  3.89s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1700: loss = -0.05765068158507347, reward = -0.1822998821735382\n"
+      "step = 3600: loss = 0.11888808757066727, reward = -0.14535395801067352\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]/it]  \n",
-      " 60%|██████    | 1801/3000 [46:57<1:36:52,  4.85s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]t/s]  \n",
+      " 74%|███████▍  | 3701/5000 [32:40<1:22:02,  3.79s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1800: loss = 0.0410073883831501, reward = -0.1822998821735382\n"
+      "step = 3700: loss = 0.022169478237628937, reward = -0.06088108569383621\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]/it]  \n",
-      " 63%|██████▎   | 1901/3000 [49:31<1:27:47,  4.79s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]t/s]  \n",
+      " 76%|███████▌  | 3801/5000 [33:30<1:15:42,  3.79s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1900: loss = -0.022543426603078842, reward = -0.1822998821735382\n"
+      "step = 3800: loss = -0.11868000030517578, reward = -0.07580452412366867\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]/it]  \n",
-      " 67%|██████▋   | 2001/3000 [52:04<1:20:01,  4.81s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]t/s]  \n",
+      " 78%|███████▊  | 3901/5000 [34:20<1:09:30,  3.79s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2000: loss = -0.03834795951843262, reward = -0.1822998821735382\n"
+      "step = 3900: loss = -0.10230109095573425, reward = -0.07970742881298065\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]/it]  \n",
-      " 70%|███████   | 2101/3000 [54:39<1:12:04,  4.81s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.71it/s]t/s]  \n",
+      " 80%|████████  | 4001/5000 [35:10<1:04:59,  3.90s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2100: loss = 0.038611143827438354, reward = -0.1822998821735382\n"
+      "step = 4000: loss = 0.07089538872241974, reward = -0.0261381808668375\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]/it]  \n",
-      " 73%|███████▎  | 2201/3000 [57:13<1:04:08,  4.82s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]t/s]  \n",
+      " 82%|████████▏ | 4101/5000 [36:00<56:37,  3.78s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2200: loss = 0.015484925359487534, reward = -0.1822998821735382\n"
+      "step = 4100: loss = -0.022438040003180504, reward = -0.09630493819713593\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]/it]  \n",
-      " 77%|███████▋  | 2301/3000 [59:46<55:41,  4.78s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]t/s]\n",
+      " 84%|████████▍ | 4201/5000 [36:50<50:22,  3.78s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2300: loss = 0.0068712797947227955, reward = -0.1822998821735382\n"
+      "step = 4200: loss = 0.07430949807167053, reward = -0.061931073665618896\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.78it/s]4s/it]\n",
-      " 80%|████████  | 2401/3000 [1:02:20<48:12,  4.83s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.73it/s]t/s]\n",
+      " 86%|████████▌ | 4301/5000 [37:40<45:08,  3.88s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2400: loss = -0.011624114587903023, reward = -0.1822998821735382\n"
+      "step = 4300: loss = 0.012303875759243965, reward = -0.1478734314441681\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]1s/it]\n",
-      " 83%|████████▎ | 2501/3000 [1:04:53<39:50,  4.79s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]t/s]\n",
+      " 88%|████████▊ | 4401/5000 [38:29<37:45,  3.78s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2500: loss = 0.06061023101210594, reward = -0.1822998821735382\n"
+      "step = 4400: loss = -0.11188575625419617, reward = -0.1391969472169876\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]2s/it]\n",
-      " 87%|████████▋ | 2601/3000 [1:07:27<31:59,  4.81s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.66it/s]t/s]\n",
+      " 90%|█████████ | 4501/5000 [39:20<33:38,  4.04s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2600: loss = -0.005472162738442421, reward = -0.1822998821735382\n"
+      "step = 4500: loss = -0.055052660405635834, reward = -0.1591639518737793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.76it/s]2s/it]\n",
-      " 90%|█████████ | 2701/3000 [1:10:00<24:03,  4.83s/it]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.72it/s]t/s]\n",
+      " 92%|█████████▏| 4601/5000 [40:12<25:47,  3.88s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2700: loss = 0.0006865133182145655, reward = -0.1822998821735382\n"
+      "step = 4600: loss = -0.0020119748078286648, reward = -0.11100932210683823\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.77it/s]1s/it]\n",
-      " 93%|█████████▎| 2801/3000 [1:12:35<15:55,  4.80s/it]"
+      "100%|██████████| 20/20 [00:12<00:00,  1.60it/s]t/s]\n",
+      " 94%|█████████▍| 4701/5000 [41:04<20:39,  4.14s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2800: loss = 0.0014395256293937564, reward = -0.1822998821735382\n"
+      "step = 4700: loss = -0.008959325030446053, reward = -0.08426783978939056\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:11<00:00,  1.78it/s]2s/it]\n",
-      " 97%|█████████▋| 2901/3000 [1:15:08<07:56,  4.81s/it]"
+      "100%|██████████| 20/20 [00:16<00:00,  1.25it/s]t/s]\n",
+      " 96%|█████████▌| 4801/5000 [42:03<18:24,  5.55s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 2900: loss = 0.004877780564129353, reward = -0.1822998821735382\n"
+      "step = 4800: loss = 0.004117509815841913, reward = -0.03693928197026253\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 3000/3000 [1:17:28<00:00,  1.55s/it]\n",
-      "100%|██████████| 50/50 [00:28<00:00,  1.77it/s]"
+      "100%|██████████| 20/20 [00:11<00:00,  1.67it/s]t/s]\n",
+      " 98%|█████████▊| 4901/5000 [42:54<06:33,  3.97s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "AVG RETURN - KAFKA: -0.18229994\n"
+      "step = 4900: loss = 0.05862385034561157, reward = -0.06138558313250542\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\n"
+      "100%|██████████| 5000/5000 [43:33<00:00,  1.91it/s]\n"
      ]
     }
    ],
    "source": [
-    "# Continue to train on second\n",
-    "collect_driver, replay_buffer = get_rb_and_cd(train_env_2, agent)\n",
     "loss, observations, rewards = train(\n",
-    "    agent, train_env_2, train_env_2_copy, collect_driver, replay_buffer, steps = num_steps, eval_interval=100)\n",
-    "\n",
-    "print(\"AVG RETURN - KAFKA:\", \n",
-    "      compute_avg_return_episodic(train_env_2, agent.policy, num_episodes=50))\n"
+    "    agent, train_env, train_env_copy, collect_driver, replay_buffer, steps = num_steps, eval_interval=100)\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
+     "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Successfully initialized a JVM Environment!\n",
-      " JDK: jdk-11.0.20.1.jdk/bin,\n",
-      " Benchmark: kafka (dacapo-bench.jar),\n",
-      " Number of iterations: 5,\n",
-      " Goal: avgGCPause,\n",
-      " Number of JVM options: 2,\n",
-      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16}, 'ParallelGCThreads': {'min': 4, 'max': 24}},\n",
-      " Env. default state: [list([7, 12]) 0.34],\n",
-      " Env. default goal value: 0.34,\n",
-      "\n",
-      "Successfully initialized a JVM Environment!\n",
-      " JDK: jdk-11.0.20.1.jdk/bin,\n",
-      " Benchmark: avrora (dacapo-bench.jar),\n",
-      " Number of iterations: 5,\n",
-      " Goal: avgGCPause,\n",
-      " Number of JVM options: 2,\n",
-      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16}, 'ParallelGCThreads': {'min': 4, 'max': 24}},\n",
-      " Env. default state: [list([7, 12]) 0.47],\n",
-      " Env. default goal value: 0.47,\n",
-      "\n",
-      "Successfully initialized a JVM Environment!\n",
-      " JDK: jdk-11.0.20.1.jdk/bin,\n",
-      " Benchmark: kafka (dacapo-bench.jar),\n",
-      " Number of iterations: 5,\n",
-      " Goal: avgGCPause,\n",
-      " Number of JVM options: 2,\n",
-      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16}, 'ParallelGCThreads': {'min': 4, 'max': 24}},\n",
-      " Env. default state: [list([7, 12]) 0.34],\n",
-      " Env. default goal value: 0.34,\n",
-      "\n"
+      "100%|██████████| 50/50 [00:32<00:00,  1.55it/s]"
      ]
     },
     {
-     "name": "stderr",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
-      "  0%|          | 0/10000 [00:00<?, ?it/s]"
+      "AVG RETURN - KAFKA: -0.026877487\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 10000/10000 [00:39<00:00, 253.52it/s]\n"
+      "\n"
+     ]
+    },
+    {
+     "ename": "",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31mThe Kernel crashed while executing code in the the current cell or a previous cell. Please review the code in the cell(s) to identify a possible cause of the failure. Click <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. View Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
      ]
     }
    ],
    "source": [
-    "# num_steps = 5000\n",
-    "num_steps = 2000\n",
-    "\n",
-    "train_env_2 = get_tf_env(\"kafka\", env_args)\n",
-    "\n",
-    "train_env_copy = get_tf_env(\"avrora\", env_args)\n",
-    "train_env_2_copy = get_tf_env(\"kafka\", env_args)\n",
-    "\n",
-    "dataset_iter = get_dataset_iter([train_env, train_env_2], dataset_size, agent)\n"
+    "print(\"AVG RETURN - KAFKA:\", \n",
+    "      compute_avg_return_episodic(train_env_2, agent.policy, num_episodes=50))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:00<00:00, 41.36it/s]\n",
-      "  0%|          | 7/2000 [00:08<28:40,  1.16it/s]  "
+      "100%|██████████| 20/20 [00:07<00:00,  2.78it/s]\n",
+      "  0%|          | 1/2000 [00:11<6:11:57, 11.16s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 0: loss = 51.2379150390625, reward = 0.8695311546325684\n"
+      "step = 0: loss = 9.476568222045898, reward = 0.08902159333229065\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:00<00:00, 127.49it/s]]\n",
-      "  5%|▌         | 105/2000 [00:10<01:03, 29.61it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.82it/s]/s]\n",
+      "  5%|▌         | 101/2000 [01:47<1:35:29,  3.02s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 100: loss = 0.33366167545318604, reward = 1.280665636062622\n"
+      "step = 100: loss = 0.059642937034368515, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  3.06it/s]/s]\n",
-      " 10%|█         | 204/2000 [00:20<12:04,  2.48it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.81it/s]/s]  \n",
+      " 10%|█         | 201/2000 [03:26<1:31:07,  3.04s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 200: loss = 0.4499567747116089, reward = -0.05940203741192818\n"
+      "step = 200: loss = 0.0535656213760376, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  3.06it/s]/s]\n",
-      " 15%|█▌        | 307/2000 [00:29<10:35,  2.67it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.81it/s]/s]  \n",
+      " 15%|█▌        | 301/2000 [05:03<1:25:42,  3.03s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 300: loss = 0.7108945846557617, reward = -0.05940203741192818\n"
+      "step = 300: loss = 0.04861774295568466, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:00<00:00, 137.44it/s]s]\n",
-      " 20%|██        | 404/2000 [00:33<01:05, 24.52it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.68it/s]/s]  \n",
+      " 20%|██        | 401/2000 [06:41<1:23:49,  3.15s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 400: loss = 0.44231095910072327, reward = 1.2897497415542603\n"
+      "step = 400: loss = 0.04700877517461777, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  2.93it/s]/s]\n",
-      " 25%|██▌       | 506/2000 [00:43<10:35,  2.35it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.76it/s]/s]  \n",
+      " 25%|██▌       | 501/2000 [08:21<1:17:13,  3.09s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 500: loss = 0.4197642207145691, reward = -0.05940203741192818\n"
+      "step = 500: loss = 0.02722451649606228, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  2.89it/s]/s]\n",
-      " 30%|███       | 606/2000 [00:53<10:51,  2.14it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.79it/s]/s]  \n",
+      " 30%|███       | 601/2000 [10:00<1:11:00,  3.05s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 600: loss = 0.5538969039916992, reward = -0.05940203741192818\n"
+      "step = 600: loss = 0.047364652156829834, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  2.90it/s]/s]\n",
-      " 35%|███▌      | 704/2000 [01:04<11:52,  1.82it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.80it/s]/s]  \n",
+      " 35%|███▌      | 701/2000 [11:37<1:05:47,  3.04s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 700: loss = 0.5397571921348572, reward = -0.05940203741192818\n"
+      "step = 700: loss = 0.04358407109975815, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:00<00:00, 74.12it/s] s]\n",
-      " 40%|████      | 806/2000 [01:07<00:58, 20.24it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.63it/s]/s]  \n",
+      " 40%|████      | 801/2000 [13:19<1:03:25,  3.17s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 800: loss = 0.5251133441925049, reward = 1.2897497415542603\n"
+      "step = 800: loss = 0.035567134618759155, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  3.06it/s]/s]\n",
-      " 45%|████▌     | 904/2000 [01:17<09:35,  1.90it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.64it/s]/s]  \n",
+      " 45%|████▌     | 901/2000 [15:03<59:11,  3.23s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 900: loss = 0.7585784792900085, reward = -0.05940203741192818\n"
+      "step = 900: loss = 0.04098467528820038, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  3.03it/s]/s]\n",
-      " 50%|█████     | 1007/2000 [01:27<06:17,  2.63it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.56it/s]t/s]\n",
+      " 50%|█████     | 1001/2000 [16:45<54:24,  3.27s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1000: loss = 0.395091712474823, reward = 0.2897500693798065\n"
+      "step = 1000: loss = 0.0423898883163929, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  2.93it/s]t/s]\n",
-      " 55%|█████▌    | 1105/2000 [01:37<05:50,  2.56it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.76it/s]t/s]\n",
+      " 55%|█████▌    | 1101/2000 [18:25<45:51,  3.06s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1100: loss = 0.4739944338798523, reward = -0.05940203741192818\n"
+      "step = 1100: loss = 0.0068428427912294865, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:07<00:00,  2.84it/s]t/s]\n",
-      " 60%|██████    | 1206/2000 [01:48<06:09,  2.15it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.76it/s]t/s]\n",
+      " 60%|██████    | 1201/2000 [20:06<41:46,  3.14s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1200: loss = 0.6102819442749023, reward = -0.05940203741192818\n"
+      "step = 1200: loss = 0.006304117850959301, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  2.92it/s]t/s]\n",
-      " 65%|██████▌   | 1306/2000 [01:58<04:35,  2.52it/s]"
+      "100%|██████████| 20/20 [00:08<00:00,  2.42it/s]t/s]\n",
+      " 65%|██████▌   | 1301/2000 [21:48<39:23,  3.38s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1300: loss = 0.5587815642356873, reward = 0.7054879665374756\n"
+      "step = 1300: loss = -0.049190741032361984, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  3.06it/s]t/s]\n",
-      " 70%|███████   | 1407/2000 [02:08<03:42,  2.66it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.65it/s]t/s]\n",
+      " 70%|███████   | 1401/2000 [23:27<31:34,  3.16s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1400: loss = 0.573989987373352, reward = -0.05940203741192818\n"
+      "step = 1400: loss = -0.05680543929338455, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  3.03it/s]t/s]\n",
-      " 75%|███████▌  | 1504/2000 [02:18<03:21,  2.46it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.77it/s]t/s]\n",
+      " 75%|███████▌  | 1501/2000 [25:04<25:30,  3.07s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1500: loss = 0.5030393600463867, reward = -0.05940203741192818\n"
+      "step = 1500: loss = 0.03054279275238514, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  3.06it/s]t/s]\n",
-      " 80%|████████  | 1605/2000 [02:28<02:28,  2.66it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.71it/s]t/s]\n",
+      " 80%|████████  | 1601/2000 [26:44<20:48,  3.13s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1600: loss = 0.5913358926773071, reward = -0.05940203741192818\n"
+      "step = 1600: loss = 0.005212224554270506, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  2.98it/s]t/s]\n",
-      " 85%|████████▌ | 1704/2000 [02:37<02:38,  1.86it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.79it/s]t/s]\n",
+      " 85%|████████▌ | 1701/2000 [28:25<15:17,  3.07s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1700: loss = 0.6082311272621155, reward = 0.2897500693798065\n"
+      "step = 1700: loss = -0.012469688430428505, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  3.02it/s]t/s]\n",
-      " 90%|█████████ | 1805/2000 [02:47<01:19,  2.45it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.71it/s]t/s]\n",
+      " 90%|█████████ | 1801/2000 [30:03<10:17,  3.10s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1800: loss = 0.3509940505027771, reward = -0.05940203741192818\n"
+      "step = 1800: loss = -0.022902732715010643, reward = 0.08900009095668793\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20/20 [00:06<00:00,  3.05it/s]t/s]\n",
-      " 95%|█████████▌| 1905/2000 [02:57<00:35,  2.65it/s]"
+      "100%|██████████| 20/20 [00:07<00:00,  2.75it/s]t/s]\n",
+      " 95%|█████████▌| 1901/2000 [31:42<05:06,  3.10s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1900: loss = -3.552382986526936e-05, reward = 0.08900009095668793\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 2000/2000 [33:16<00:00,  1.00it/s]\n",
+      "100%|██████████| 50/50 [00:19<00:00,  2.58it/s]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "step = 1900: loss = 0.3781909644603729, reward = -0.05940203741192818\n"
+      "AVG RETURN - KAFKA: 0.08900006\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 2000/2000 [03:00<00:00, 11.06it/s]\n"
+      "\n"
      ]
     }
    ],
    "source": [
+    "# Train on second\n",
+    "collect_driver, replay_buffer = get_cd_and_rb(train_env_2, agent)\n",
+    "loss, observations, rewards = train(\n",
+    "    agent, train_env_2, train_env_2_copy, collect_driver, replay_buffer, steps = num_steps, eval_interval=100)\n",
+    "\n",
+    "print(\"AVG RETURN - KAFKA:\", \n",
+    "      compute_avg_return_episodic(train_env_2, agent.policy, num_episodes=50))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(\"AVG RETURN - TEST:\", \n",
+    "      compute_avg_return_episodic(test_env, agent.policy, num_episodes=50))\n",
     "\n",
+    "# Test environment\n",
+    "collect_driver, replay_buffer = get_cd_and_rb(test_env, agent)\n",
     "loss, observations, rewards = train(\n",
-    "    agent, train_env, train_env_copy, dataset_iter, steps = num_steps, eval_interval=100)"
+    "    agent, test_env, test_env_copy, collect_driver, replay_buffer, steps = num_steps, eval_interval=100)\n",
+    "\n",
+    "print(\"AVG RETURN - TEST:\", \n",
+    "      compute_avg_return_episodic(test_env, agent.policy, num_episodes=50))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Final results."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/Users/ellkrauze/projects/gc-ml/gc-ml-env/lib/python3.8/site-packages/tensorflow/python/saved_model/nested_structure_coder.py:475: UserWarning: Encoding a StructuredValue with type tfp.distributions.Deterministic_ACTTypeSpec; loading this StructuredValue will require that this type be imported and registered.\n",
-      "  warnings.warn(\"Encoding a StructuredValue with type %s; loading this \"\n"
+      "100%|██████████| 50/50 [00:00<00:00, 74.34it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "AVG RETURN - AVRORA: 1.2897495\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 50/50 [00:28<00:00,  1.78it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "AVG RETURN - KAFKA: -0.6872998\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 50/50 [00:27<00:00,  1.79it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "AVG RETURN - TEST: 0.15185018\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
      ]
     }
    ],
    "source": [
-    "train_checkpointer.save(global_step)\n",
-    "tf_policy_saver.save(policy_dir)"
+    "print(\"AVG RETURN - AVRORA:\", \n",
+    "      compute_avg_return_episodic(train_env, agent.policy, num_episodes=50))\n",
+    "\n",
+    "print(\"AVG RETURN - KAFKA:\", \n",
+    "      compute_avg_return_episodic(train_env_2, agent.policy, num_episodes=50))\n",
+    "\n",
+    "print(\"AVG RETURN - TEST:\", \n",
+    "      compute_avg_return_episodic(test_env, agent.policy, num_episodes=50))"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 12,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 640x480 with 2 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
    "source": [
-    "plot_training(loss, rewards, num_steps, 100)"
+    "### Train on a single dataset"
    ]
   },
   {
-   "cell_type": "markdown",
+   "cell_type": "code",
+   "execution_count": 11,
    "metadata": {},
-   "source": [
-    "### Test"
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: avrora (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [13, 16, 0.01032, 0.0220530411853552, 0.0220509416656523, 0.0, 0.0, 0.0, 0.0, 0.9816754502341878],\n",
+      " Env. default goal value: 0.01032,\n",
+      "\n",
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: kafka (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [4, 20, 0.03266, 0.9999994550464116, 0.9999992366373232, 0.8793103448275863, 0.8807760141093476, 0.8774827845478718, 0.8781925343811396, 2.3067374411080144e-05],\n",
+      " Env. default goal value: 0.03266,\n",
+      "\n",
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: kafka (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [4, 12, 0.02978, 0.9999992902418988, 0.9999990063540516, 0.9655172413793104, 0.970194003527337, 0.9693582431571556, 0.9685658153241652, 2.0695962088444764e-05],\n",
+      " Env. default goal value: 0.02978,\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 50000/50000 [04:46<00:00, 174.50it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "num_steps = 5000\n",
+    "\n",
+    "\n",
+    "# Collect trajectories from both benchmarks.\n",
+    "dataset_iter = get_dataset_iter([train_env, train_env_2], 50000, agent, train_episodes_per_iteration)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0%|          | 0/20000 [00:00<?, ?it/s]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0%|          | 4/20000 [00:11<12:12:23,  2.20s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 0: loss = 0.24985742568969727, reward = 0.03627775236964226\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  1%|          | 104/20000 [00:22<3:04:36,  1.80it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 100: loss = 0.18949705362319946, reward = 0.03435734659433365\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  1%|          | 204/20000 [00:35<4:31:45,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 200: loss = 0.15754052996635437, reward = 0.02616189420223236\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  2%|▏         | 304/20000 [00:47<4:28:42,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 300: loss = 0.13620947301387787, reward = -0.019210290163755417\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  2%|▏         | 404/20000 [01:00<4:26:59,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 400: loss = 0.2568551301956177, reward = 0.023504946380853653\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  3%|▎         | 504/20000 [01:13<4:25:48,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 500: loss = 0.1418035924434662, reward = 0.018958551809191704\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  3%|▎         | 604/20000 [01:26<4:25:47,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 600: loss = 0.35291072726249695, reward = 0.029474308714270592\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  4%|▎         | 704/20000 [01:39<4:24:15,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 700: loss = 0.2931548058986664, reward = 0.017287787050008774\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  4%|▍         | 804/20000 [01:52<4:21:30,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 800: loss = 0.3352110981941223, reward = 0.03280129283666611\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  5%|▍         | 904/20000 [02:05<4:20:48,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 900: loss = 0.33797353506088257, reward = 0.026038503274321556\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  5%|▌         | 1004/20000 [02:18<4:21:05,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1000: loss = 0.35232457518577576, reward = -0.037331633269786835\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  6%|▌         | 1102/20000 [02:31<6:10:08,  1.18s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1100: loss = 0.3840436637401581, reward = 0.030994366854429245\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  6%|▌         | 1204/20000 [02:45<4:30:35,  1.16it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1200: loss = 0.2831926941871643, reward = 0.023907102644443512\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  7%|▋         | 1304/20000 [02:58<4:21:50,  1.19it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1300: loss = 0.32109829783439636, reward = 0.007971655577421188\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  7%|▋         | 1404/20000 [03:11<4:25:23,  1.17it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1400: loss = 0.2960289716720581, reward = -0.01567075029015541\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  8%|▊         | 1504/20000 [03:25<4:24:35,  1.17it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1500: loss = 0.1903543323278427, reward = 0.039607446640729904\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  8%|▊         | 1604/20000 [03:38<4:12:57,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1600: loss = 0.14620988070964813, reward = 0.026723291724920273\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  9%|▊         | 1704/20000 [03:51<4:22:07,  1.16it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1700: loss = 0.36498910188674927, reward = 0.02997639775276184\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  9%|▉         | 1804/20000 [04:04<4:10:39,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1800: loss = 0.2329278588294983, reward = 0.022604594007134438\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 10%|▉         | 1902/20000 [04:18<6:34:18,  1.31s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1900: loss = 0.37557756900787354, reward = 0.018153684213757515\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 10%|█         | 2002/20000 [04:34<6:46:35,  1.36s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2000: loss = 0.20745645463466644, reward = 0.047425199300050735\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 11%|█         | 2104/20000 [04:48<4:30:19,  1.10it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2100: loss = 0.12628722190856934, reward = 0.032698556780815125\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 11%|█         | 2204/20000 [05:02<4:04:21,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2200: loss = 0.28112223744392395, reward = 0.032847389578819275\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 12%|█▏        | 2304/20000 [05:15<3:59:44,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2300: loss = 0.23477435111999512, reward = 0.0321074053645134\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 12%|█▏        | 2404/20000 [05:28<3:58:34,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2400: loss = 0.26505008339881897, reward = 0.01781424880027771\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 13%|█▎        | 2502/20000 [05:41<5:29:08,  1.13s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2500: loss = 0.21987807750701904, reward = 0.02736610732972622\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 13%|█▎        | 2604/20000 [05:54<3:55:44,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2600: loss = 0.21958446502685547, reward = -0.05722207576036453\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 14%|█▎        | 2704/20000 [06:07<3:54:58,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2700: loss = 0.40489062666893005, reward = 0.033309366554021835\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 14%|█▍        | 2804/20000 [06:20<3:52:06,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2800: loss = 0.21243752539157867, reward = -0.0046446374617516994\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 15%|█▍        | 2904/20000 [06:34<3:51:48,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2900: loss = 0.24446099996566772, reward = 0.03422443941235542\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 15%|█▌        | 3004/20000 [06:47<3:48:46,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3000: loss = 0.28121286630630493, reward = 0.03498591110110283\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 16%|█▌        | 3104/20000 [07:00<3:48:32,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3100: loss = 0.2877977192401886, reward = -0.061251796782016754\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 16%|█▌        | 3204/20000 [07:13<3:48:54,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3200: loss = 0.14211082458496094, reward = 0.022305238991975784\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 17%|█▋        | 3304/20000 [07:26<3:49:13,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3300: loss = 0.25767552852630615, reward = 0.03099989891052246\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 17%|█▋        | 3404/20000 [07:40<3:44:06,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3400: loss = 0.32213884592056274, reward = 0.015603247098624706\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 18%|█▊        | 3504/20000 [07:53<3:42:42,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3500: loss = 0.20584708452224731, reward = 0.012885654345154762\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 18%|█▊        | 3604/20000 [08:06<3:43:10,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3600: loss = 0.16325877606868744, reward = 0.002983792219310999\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 19%|█▊        | 3704/20000 [08:19<3:42:41,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3700: loss = 0.13512112200260162, reward = 0.028231313452124596\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 19%|█▉        | 3804/20000 [08:32<3:41:42,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3800: loss = 0.2544684410095215, reward = 0.01989850588142872\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 20%|█▉        | 3904/20000 [08:46<3:49:47,  1.17it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3900: loss = 0.1507875770330429, reward = 0.042065300047397614\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 20%|██        | 4004/20000 [08:59<3:39:01,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4000: loss = 0.11149635910987854, reward = -0.008994200266897678\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 21%|██        | 4104/20000 [09:12<3:37:33,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4100: loss = 0.2606261074542999, reward = 0.047553565353155136\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 21%|██        | 4204/20000 [09:26<3:39:37,  1.20it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4200: loss = 0.3898237943649292, reward = 0.01164049468934536\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 22%|██▏       | 4304/20000 [09:39<3:32:44,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4300: loss = 0.2230168581008911, reward = 0.026527341455221176\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 22%|██▏       | 4404/20000 [09:52<3:30:50,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4400: loss = 0.1936362385749817, reward = 0.027814308181405067\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 23%|██▎       | 4504/20000 [10:05<3:29:42,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4500: loss = 0.2133648693561554, reward = 0.004976757802069187\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 23%|██▎       | 4604/20000 [10:18<3:30:23,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4600: loss = 0.3311423361301422, reward = 0.007316400296986103\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 24%|██▎       | 4702/20000 [10:32<4:53:40,  1.15s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4700: loss = 0.11626237630844116, reward = 0.038581907749176025\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 24%|██▍       | 4804/20000 [10:45<3:26:50,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4800: loss = 0.24157986044883728, reward = 0.022277645766735077\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 25%|██▍       | 4904/20000 [10:58<3:23:26,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4900: loss = 0.29611992835998535, reward = 0.04321884363889694\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 25%|██▌       | 5004/20000 [11:11<3:22:57,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5000: loss = 0.24908176064491272, reward = 0.023435909301042557\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 26%|██▌       | 5104/20000 [11:24<3:22:51,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5100: loss = 0.4302345812320709, reward = 0.03838800638914108\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 26%|██▌       | 5204/20000 [11:37<3:18:48,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5200: loss = 0.1361045390367508, reward = 0.010508047416806221\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 27%|██▋       | 5304/20000 [11:50<3:17:20,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5300: loss = 0.32617735862731934, reward = 0.001993041019886732\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 27%|██▋       | 5404/20000 [12:02<3:15:12,  1.25it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5400: loss = 0.2851839065551758, reward = 0.01948023959994316\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 28%|██▊       | 5504/20000 [12:15<3:15:47,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5500: loss = 0.43152138590812683, reward = 0.04435548558831215\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 28%|██▊       | 5604/20000 [12:28<3:14:49,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5600: loss = 0.29081177711486816, reward = 0.022282103076577187\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 29%|██▊       | 5704/20000 [12:41<3:12:57,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5700: loss = 0.25021618604660034, reward = -0.06722939759492874\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 29%|██▉       | 5803/20000 [12:53<3:10:59,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5800: loss = 0.38924163579940796, reward = -0.014260141178965569\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 30%|██▉       | 5903/20000 [13:06<3:08:58,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5900: loss = 0.21488197147846222, reward = 0.01917889341711998\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 30%|███       | 6003/20000 [13:19<3:10:57,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6000: loss = 0.3656989634037018, reward = 0.02787599340081215\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 31%|███       | 6103/20000 [13:31<3:06:15,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6100: loss = 0.24007469415664673, reward = 0.03764120116829872\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 31%|███       | 6203/20000 [13:44<3:06:48,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6200: loss = 0.16221477091312408, reward = 0.010355299338698387\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 32%|███▏      | 6303/20000 [13:57<3:04:38,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6300: loss = 0.22436459362506866, reward = 0.03099079802632332\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 32%|███▏      | 6403/20000 [14:10<3:03:19,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6400: loss = 0.24129751324653625, reward = 0.03142649307847023\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 33%|███▎      | 6503/20000 [14:22<3:01:36,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6500: loss = 0.25571560859680176, reward = 0.009862711653113365\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 33%|███▎      | 6603/20000 [14:35<3:02:35,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6600: loss = 0.2787809371948242, reward = 0.019480206072330475\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 34%|███▎      | 6703/20000 [14:48<3:00:37,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6700: loss = 0.2985495626926422, reward = 0.011412251740694046\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 34%|███▍      | 6803/20000 [15:01<2:56:37,  1.25it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6800: loss = 0.27407902479171753, reward = 0.036545880138874054\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 35%|███▍      | 6903/20000 [15:13<2:55:44,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6900: loss = 0.16550034284591675, reward = 0.030543338507413864\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 35%|███▌      | 7003/20000 [15:26<2:55:06,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7000: loss = 0.23837843537330627, reward = 0.0327099934220314\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 36%|███▌      | 7103/20000 [15:39<2:52:32,  1.25it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7100: loss = 0.3921396732330322, reward = -0.02555229887366295\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 36%|███▌      | 7203/20000 [15:51<2:53:59,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7200: loss = 0.32735878229141235, reward = 0.03397664800286293\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 37%|███▋      | 7303/20000 [16:04<2:50:02,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7300: loss = 0.3671906888484955, reward = 0.03368739038705826\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 37%|███▋      | 7403/20000 [16:17<2:50:00,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7400: loss = 0.26604023575782776, reward = 0.017673656344413757\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 38%|███▊      | 7503/20000 [16:30<2:47:31,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7500: loss = 0.24808797240257263, reward = 0.007826892659068108\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 38%|███▊      | 7603/20000 [16:42<2:46:10,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7600: loss = 0.120560422539711, reward = 0.02314900793135166\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 39%|███▊      | 7703/20000 [16:55<2:45:45,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7700: loss = 0.32504144310951233, reward = 0.04141543060541153\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 39%|███▉      | 7803/20000 [17:08<2:44:22,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7800: loss = 0.5370333790779114, reward = 0.028494015336036682\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 40%|███▉      | 7903/20000 [17:20<2:41:54,  1.25it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7900: loss = 0.1283600926399231, reward = 0.035373248159885406\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 40%|████      | 8003/20000 [17:33<2:40:32,  1.25it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8000: loss = 0.16220442950725555, reward = 0.016758259385824203\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 41%|████      | 8103/20000 [17:46<2:40:12,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8100: loss = 0.14994856715202332, reward = 0.021713051944971085\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 41%|████      | 8203/20000 [17:59<2:40:16,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8200: loss = 0.3100902736186981, reward = 0.02561871148645878\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 42%|████▏     | 8303/20000 [18:11<2:36:57,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8300: loss = 0.28485986590385437, reward = 0.03194400668144226\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 42%|████▏     | 8403/20000 [18:24<2:35:41,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8400: loss = 0.2703417241573334, reward = 0.0242760069668293\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 43%|████▎     | 8503/20000 [18:37<2:33:42,  1.25it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8500: loss = 0.20987364649772644, reward = 0.04921314865350723\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 43%|████▎     | 8603/20000 [18:50<2:34:43,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8600: loss = 0.30480578541755676, reward = 0.045444004237651825\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 44%|████▎     | 8703/20000 [19:03<2:33:21,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8700: loss = 0.24081099033355713, reward = 0.019481603056192398\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 44%|████▍     | 8803/20000 [19:16<2:30:44,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8800: loss = 0.2606129050254822, reward = 0.022872157394886017\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 45%|████▍     | 8903/20000 [19:30<2:34:57,  1.19it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8900: loss = 0.2125171720981598, reward = -0.03956236317753792\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 45%|████▌     | 9003/20000 [19:43<2:29:08,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9000: loss = 0.2571754455566406, reward = 0.050605904310941696\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 46%|████▌     | 9103/20000 [19:56<2:28:38,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9100: loss = 0.17493905127048492, reward = 0.048502154648303986\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 46%|████▌     | 9203/20000 [20:09<2:25:08,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9200: loss = 0.3369608223438263, reward = 0.029967159032821655\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 47%|████▋     | 9303/20000 [20:22<2:26:23,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9300: loss = 0.21062473952770233, reward = 0.02399105206131935\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 47%|████▋     | 9403/20000 [20:35<2:24:00,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9400: loss = 0.22874122858047485, reward = 0.022599248215556145\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 48%|████▊     | 9503/20000 [20:50<2:34:25,  1.13it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9500: loss = 0.17614218592643738, reward = 0.010355794802308083\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 48%|████▊     | 9603/20000 [21:03<2:23:57,  1.20it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9600: loss = 0.35222911834716797, reward = 0.03868580237030983\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 49%|████▊     | 9703/20000 [21:16<2:24:42,  1.19it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9700: loss = 0.17193174362182617, reward = 0.03527269884943962\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 49%|████▉     | 9803/20000 [21:30<2:18:52,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9800: loss = 0.29037564992904663, reward = -0.010149320587515831\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 50%|████▉     | 9903/20000 [21:43<2:15:56,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9900: loss = 0.12818235158920288, reward = 0.013634102419018745\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 50%|█████     | 10003/20000 [21:56<2:14:27,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 10000: loss = 0.18994712829589844, reward = 0.02275080420076847\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 51%|█████     | 10103/20000 [22:09<2:16:36,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 10100: loss = 0.16500890254974365, reward = 0.0206805020570755\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 51%|█████     | 10203/20000 [22:22<2:18:18,  1.18it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 10200: loss = 0.2985037863254547, reward = -0.014398030936717987\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 52%|█████▏    | 10303/20000 [22:36<2:11:03,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 10300: loss = 0.2481953501701355, reward = 0.034351855516433716\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 52%|█████▏    | 10403/20000 [22:49<2:10:27,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 10400: loss = 0.15936757624149323, reward = -0.010402058251202106\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 53%|█████▎    | 10503/20000 [23:02<2:08:55,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 10500: loss = 0.2935214042663574, reward = -0.018190553411841393\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 53%|█████▎    | 10603/20000 [23:15<2:06:43,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 10600: loss = 0.4175000488758087, reward = 0.02903285250067711\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 54%|█████▎    | 10703/20000 [23:28<2:06:07,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 10700: loss = 0.3340311646461487, reward = 0.03699815273284912\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 54%|█████▍    | 10803/20000 [23:41<2:05:04,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 10800: loss = 0.24288594722747803, reward = 0.01725880429148674\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 55%|█████▍    | 10903/20000 [23:55<2:02:40,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 10900: loss = 0.221414715051651, reward = 0.04057825356721878\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 55%|█████▌    | 11003/20000 [24:08<2:02:00,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 11000: loss = 0.35102277994155884, reward = 0.027450602501630783\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 56%|█████▌    | 11103/20000 [24:21<2:02:46,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 11100: loss = 0.2549188435077667, reward = 0.03528924658894539\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 56%|█████▌    | 11203/20000 [24:34<1:59:33,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 11200: loss = 0.1860245019197464, reward = 0.01647549495100975\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 57%|█████▋    | 11303/20000 [24:47<1:57:49,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 11300: loss = 0.42202672362327576, reward = 0.02129724994301796\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 57%|█████▋    | 11403/20000 [25:01<1:58:00,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 11400: loss = 0.3794873058795929, reward = 0.039244603365659714\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 58%|█████▊    | 11503/20000 [25:14<1:58:13,  1.20it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 11500: loss = 0.42235517501831055, reward = 0.016923243179917336\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 58%|█████▊    | 11603/20000 [25:28<1:59:05,  1.18it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 11600: loss = 0.31331300735473633, reward = -0.016771525144577026\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 59%|█████▊    | 11703/20000 [25:41<1:54:42,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 11700: loss = 0.21873454749584198, reward = 0.01584719866514206\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 59%|█████▉    | 11803/20000 [25:54<1:52:59,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 11800: loss = 0.339395135641098, reward = 0.031111741438508034\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 60%|█████▉    | 11903/20000 [26:08<1:50:02,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 11900: loss = 0.19148913025856018, reward = 0.011176547966897488\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 60%|██████    | 12003/20000 [26:21<1:49:57,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 12000: loss = 0.4209326505661011, reward = 0.024248290807008743\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 61%|██████    | 12103/20000 [26:34<1:47:50,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 12100: loss = 0.26758265495300293, reward = 0.04665274918079376\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 61%|██████    | 12203/20000 [26:48<1:49:44,  1.18it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 12200: loss = 0.26957276463508606, reward = 0.018956348299980164\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 62%|██████▏   | 12303/20000 [27:01<1:46:40,  1.20it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 12300: loss = 0.3854345977306366, reward = 0.028666352853178978\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 62%|██████▏   | 12403/20000 [27:15<1:45:22,  1.20it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 12400: loss = 0.19581261277198792, reward = 0.020709004253149033\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 63%|██████▎   | 12503/20000 [27:28<1:45:26,  1.19it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 12500: loss = 0.2152058482170105, reward = 0.030046189203858376\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 63%|██████▎   | 12603/20000 [27:42<1:45:17,  1.17it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 12600: loss = 0.2161836475133896, reward = 0.034942347556352615\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 64%|██████▎   | 12703/20000 [27:56<1:44:20,  1.17it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 12700: loss = 0.19305600225925446, reward = 0.018813790753483772\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 64%|██████▍   | 12803/20000 [28:09<1:39:23,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 12800: loss = 0.1213333010673523, reward = 0.013052955269813538\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 65%|██████▍   | 12903/20000 [28:23<1:37:50,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 12900: loss = 0.24266910552978516, reward = 0.004309503361582756\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 65%|██████▌   | 13003/20000 [28:36<1:37:32,  1.20it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 13000: loss = 0.20264410972595215, reward = 0.015783360227942467\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 66%|██████▌   | 13103/20000 [28:51<1:39:10,  1.16it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 13100: loss = 0.10965907573699951, reward = 0.02822929061949253\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 66%|██████▌   | 13203/20000 [29:04<1:33:21,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 13200: loss = 0.18908382952213287, reward = 0.020571347326040268\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 67%|██████▋   | 13303/20000 [29:18<1:35:55,  1.16it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 13300: loss = 0.29961344599723816, reward = 0.03018525242805481\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 67%|██████▋   | 13403/20000 [29:32<1:35:38,  1.15it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 13400: loss = 0.4527949094772339, reward = 0.05688738822937012\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 68%|██████▊   | 13503/20000 [29:46<1:29:30,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 13500: loss = 0.5011105537414551, reward = 0.010356593877077103\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 68%|██████▊   | 13603/20000 [29:59<1:27:36,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 13600: loss = 0.23930104076862335, reward = 0.022572344169020653\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 69%|██████▊   | 13703/20000 [30:13<1:26:53,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 13700: loss = 0.4600016474723816, reward = 0.03431164100766182\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 69%|██████▉   | 13803/20000 [30:26<1:24:48,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 13800: loss = 0.205466166138649, reward = 0.03564384579658508\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 70%|██████▉   | 13903/20000 [30:40<1:24:23,  1.20it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 13900: loss = 0.23823849856853485, reward = 0.024357499554753304\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 70%|███████   | 14003/20000 [30:53<1:22:08,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 14000: loss = 0.21844594180583954, reward = 0.03459470346570015\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 71%|███████   | 14103/20000 [31:07<1:20:15,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 14100: loss = 0.32898181676864624, reward = 0.01147269643843174\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 71%|███████   | 14203/20000 [31:20<1:19:29,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 14200: loss = 0.27995678782463074, reward = 0.017521541565656662\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 72%|███████▏  | 14303/20000 [31:34<1:18:04,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 14300: loss = 0.20431207120418549, reward = 0.015330428257584572\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 72%|███████▏  | 14403/20000 [31:47<1:19:58,  1.17it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 14400: loss = 0.35720497369766235, reward = 0.0158720463514328\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 73%|███████▎  | 14503/20000 [32:01<1:14:49,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 14500: loss = 0.13140425086021423, reward = 0.01639840006828308\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 73%|███████▎  | 14603/20000 [32:14<1:14:02,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 14600: loss = 0.15935814380645752, reward = -0.012200744822621346\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 74%|███████▎  | 14703/20000 [32:28<1:19:27,  1.11it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 14700: loss = 0.4161395728588104, reward = 0.013149097561836243\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 74%|███████▍  | 14803/20000 [32:42<1:10:40,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 14800: loss = 0.20379342138767242, reward = 0.03221284970641136\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 75%|███████▍  | 14903/20000 [32:55<1:10:30,  1.20it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 14900: loss = 0.30539557337760925, reward = 0.007336760871112347\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 75%|███████▌  | 15003/20000 [33:08<1:08:23,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 15000: loss = 0.2678513526916504, reward = 0.0048437402583658695\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 76%|███████▌  | 15103/20000 [33:22<1:07:52,  1.20it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 15100: loss = 0.2429802119731903, reward = -0.026663202792406082\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 76%|███████▌  | 15203/20000 [33:36<1:09:31,  1.15it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 15200: loss = 0.2407996654510498, reward = 0.04678025096654892\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 77%|███████▋  | 15303/20000 [33:49<1:04:09,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 15300: loss = 0.39074310660362244, reward = 0.009758999571204185\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 77%|███████▋  | 15403/20000 [34:04<1:08:39,  1.12it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 15400: loss = 0.29942965507507324, reward = 0.03654450923204422\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 78%|███████▊  | 15504/20000 [34:17<1:01:22,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 15500: loss = 0.36401963233947754, reward = 0.019089559093117714\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 78%|███████▊  | 15603/20000 [34:29<59:50,  1.22it/s]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 15600: loss = 0.2666255235671997, reward = 0.039123497903347015\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 79%|███████▊  | 15704/20000 [34:42<57:17,  1.25it/s]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 15700: loss = 0.30016130208969116, reward = 0.03198104351758957\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 79%|███████▉  | 15804/20000 [34:55<57:33,  1.22it/s]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 15800: loss = 0.4818044900894165, reward = 0.029416244477033615\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 80%|███████▉  | 15904/20000 [35:07<55:33,  1.23it/s]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 15900: loss = 0.5133304595947266, reward = 0.031092459335923195\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 80%|████████  | 16004/20000 [35:20<54:08,  1.23it/s]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 16000: loss = 0.15663743019104004, reward = 0.020326707512140274\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 81%|████████  | 16103/20000 [35:33<53:08,  1.22it/s]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 16100: loss = 0.2674199342727661, reward = 0.028164546936750412\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 81%|████████  | 16204/20000 [35:45<51:54,  1.22it/s]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 16200: loss = 0.33699843287467957, reward = 0.01498035341501236\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 82%|████████▏ | 16303/20000 [35:58<50:00,  1.23it/s]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 16300: loss = 0.48910778760910034, reward = 0.023824337869882584\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 82%|████████▏ | 16404/20000 [36:10<48:52,  1.23it/s]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 16400: loss = 0.37667104601860046, reward = 0.018844105303287506\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 83%|████████▎ | 16504/20000 [36:23<49:09,  1.19it/s]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 16500: loss = 0.2992458939552307, reward = 0.020283302292227745\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 83%|████████▎ | 16604/20000 [36:36<45:41,  1.24it/s]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 16600: loss = 0.22386230528354645, reward = 0.021562248468399048\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 84%|████████▎ | 16704/20000 [36:48<44:25,  1.24it/s]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 16700: loss = 0.31734248995780945, reward = 0.008787089958786964\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 84%|████████▍ | 16804/20000 [37:01<43:09,  1.23it/s]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 16800: loss = 0.3774816691875458, reward = -0.005967739969491959\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 85%|████████▍ | 16904/20000 [37:14<42:34,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 16900: loss = 0.2948073148727417, reward = -0.027173522859811783\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 85%|████████▌ | 17003/20000 [37:26<39:48,  1.25it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 17000: loss = 0.2935958504676819, reward = -0.016064997762441635\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 86%|████████▌ | 17103/20000 [37:39<39:13,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 17100: loss = 0.2580260634422302, reward = 0.009974196553230286\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 86%|████████▌ | 17204/20000 [37:52<38:21,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 17200: loss = 0.2459775060415268, reward = 0.031969159841537476\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 87%|████████▋ | 17303/20000 [38:04<36:14,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 17300: loss = 0.22677096724510193, reward = -0.0015499459113925695\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 87%|████████▋ | 17404/20000 [38:16<34:16,  1.26it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 17400: loss = 0.29247766733169556, reward = 0.024155784398317337\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 88%|████████▊ | 17503/20000 [38:29<32:16,  1.29it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 17500: loss = 0.2435913383960724, reward = 0.023485349491238594\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 88%|████████▊ | 17603/20000 [38:41<31:56,  1.25it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 17600: loss = 0.27358850836753845, reward = 0.033354613929986954\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 89%|████████▊ | 17704/20000 [38:54<30:25,  1.26it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 17700: loss = 0.36078697443008423, reward = 0.011208396404981613\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 89%|████████▉ | 17804/20000 [39:06<29:43,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 17800: loss = 0.2712183892726898, reward = 0.033273398876190186\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 90%|████████▉ | 17903/20000 [39:19<28:53,  1.21it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 17900: loss = 0.41096603870391846, reward = 0.04305361211299896\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 90%|█████████ | 18004/20000 [39:31<27:18,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 18000: loss = 0.19135867059230804, reward = 0.018954003229737282\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 91%|█████████ | 18103/20000 [39:44<25:22,  1.25it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 18100: loss = 0.203397735953331, reward = 0.03420184180140495\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 91%|█████████ | 18204/20000 [39:56<23:53,  1.25it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 18200: loss = 0.12625373899936676, reward = 0.037343043833971024\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 92%|█████████▏| 18303/20000 [40:09<22:59,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 18300: loss = 0.394363671541214, reward = 0.030170589685440063\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 92%|█████████▏| 18404/20000 [40:21<21:26,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 18400: loss = 0.35190069675445557, reward = 0.02852560579776764\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 93%|█████████▎| 18503/20000 [40:33<19:12,  1.30it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 18500: loss = 0.5232994556427002, reward = -0.0395599901676178\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 93%|█████████▎| 18603/20000 [40:46<18:45,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 18600: loss = 0.30945855379104614, reward = 0.03961283713579178\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 94%|█████████▎| 18703/20000 [40:58<17:18,  1.25it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 18700: loss = 0.3504294157028198, reward = 0.0208230409771204\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 94%|█████████▍| 18804/20000 [41:11<16:22,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 18800: loss = 0.141177698969841, reward = 0.008496701717376709\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 95%|█████████▍| 18904/20000 [41:23<14:40,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 18900: loss = 0.1896134912967682, reward = 0.032260406762361526\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 95%|█████████▌| 19003/20000 [41:36<13:32,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 19000: loss = 0.28229570388793945, reward = -0.037842459976673126\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 96%|█████████▌| 19104/20000 [41:49<12:30,  1.19it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 19100: loss = 0.375541090965271, reward = 0.023044347763061523\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 96%|█████████▌| 19203/20000 [42:01<10:45,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 19200: loss = 0.2777419686317444, reward = 0.023801807314157486\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 97%|█████████▋| 19304/20000 [42:14<10:05,  1.15it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 19300: loss = 0.21851059794425964, reward = 0.0218031108379364\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 97%|█████████▋| 19404/20000 [42:27<07:44,  1.28it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 19400: loss = 0.3905331790447235, reward = 0.024327492341399193\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 98%|█████████▊| 19504/20000 [42:40<06:27,  1.28it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 19500: loss = 0.2196487933397293, reward = 0.024008430540561676\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 98%|█████████▊| 19604/20000 [42:52<05:25,  1.22it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 19600: loss = 0.16009560227394104, reward = 0.03513675183057785\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 99%|█████████▊| 19704/20000 [43:05<03:59,  1.24it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 19700: loss = 0.30739906430244446, reward = 0.03955841436982155\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 99%|█████████▉| 19803/20000 [43:17<02:40,  1.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 19800: loss = 0.2997934818267822, reward = 0.026838252320885658\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|█████████▉| 19903/20000 [43:30<01:10,  1.37it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 19900: loss = 0.25723883509635925, reward = 0.03693921118974686\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 20000/20000 [43:35<00:00,  7.65it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Train on Avrora, Evaluate on Kafka\n",
+    "loss, observations, rewards = _train(\n",
+    "    agent, train_env, train_env_2, dataset_iter, steps = 20000, eval_interval=100)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: h2 (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [13, 8, 0.14861, 0.9999572476715284, 0.9883840216515078, 0.983277591973244, 0.9828115408225904, 0.999997114709069, 1.0, 0.1393387985045442],\n",
+      " Env. default goal value: 0.14861,\n",
+      "\n",
+      "Successfully initialized a JVM Environment!\n",
+      " JDK: jdk-11.0.20.1.jdk/bin,\n",
+      " Benchmark: h2 (dacapo-bench.jar),\n",
+      " Number of iterations: 5,\n",
+      " Goal: avgGCPause,\n",
+      " Number of JVM options: 2,\n",
+      " JVM options: {'MaxTenuringThreshold': {'min': 1, 'max': 16, 'step': 3}, 'ParallelGCThreads': {'min': 4, 'max': 24, 'step': 4}},\n",
+      " Env. default state: [1, 12, 0.15362, 0.999997745946094, 0.988448062333557, 0.983277591973244, 0.981379169224473, 0.9999992231909032, 1.0, 0.1402957711681965],\n",
+      " Env. default goal value: 0.15362,\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "test_env= get_tf_env(\"h2\", env_args)\n",
+    "test_env_copy = get_tf_env(\"h2\", env_args)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "default: [1.00e+01 1.60e+01 9.83e-03] current: [1.000e+00 1.600e+01 1.116e-02]\n",
+      "AVG RETURN - AVRORA: 0.11686779\n",
+      "default: [ 4.      12.       0.02978] current: [1.      4.      0.02897]\n",
+      "AVG RETURN - KAFKA: 0.020553958\n",
+      "default: [ 4.      16.       0.13649] current: [1.      4.      0.18607]\n",
+      "AVG RETURN - H2: 0.06736073\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"AVG RETURN - AVRORA:\", \n",
+    "      compute_avg_return_episodic(train_env, agent.policy, num_episodes=50, print_info=True))\n",
+    "\n",
+    "print(\"AVG RETURN - KAFKA:\", \n",
+    "      compute_avg_return_episodic(train_env_2, agent.policy, num_episodes=50, print_info=True))\n",
+    "\n",
+    "print(\"AVG RETURN - H2:\", \n",
+    "      compute_avg_return_episodic(test_env, agent.policy, num_episodes=50, print_info=True))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_checkpointer.save(global_step)\n",
+    "tf_policy_saver.save(policy_dir)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plot_training(loss, rewards, num_steps, 100)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Common collect driver"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "num_steps = 10000\n",
+    "collect_driver, replay_buffer = get_cd_and_rb(train_env, agent, dataset_size, train_episodes_per_iteration)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0%|          | 0/10000 [00:00<?, ?it/s]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0%|          | 1/10000 [00:18<50:22:50, 18.14s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 0: loss = 48.937225341796875, reward = -0.17753641307353973\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  1%|          | 101/10000 [01:01<7:09:21,  2.60s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 100: loss = -0.029841536656022072, reward = -0.4798048138618469\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  2%|▏         | 201/10000 [01:52<7:38:07,  2.81s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 200: loss = -0.04589027166366577, reward = 0.0646543949842453\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  3%|▎         | 301/10000 [02:54<8:11:22,  3.04s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 300: loss = -0.0024730374570935965, reward = 0.1006183847784996\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  4%|▍         | 401/10000 [03:46<7:03:52,  2.65s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 400: loss = 0.008433199487626553, reward = 0.0948130339384079\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  5%|▌         | 501/10000 [04:38<6:48:37,  2.58s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 500: loss = -0.005747173447161913, reward = 0.09036823362112045\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  6%|▌         | 601/10000 [05:30<6:52:01,  2.63s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 600: loss = -0.015521685592830181, reward = 0.06981039047241211\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  7%|▋         | 701/10000 [06:30<8:06:04,  3.14s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 700: loss = -0.0054346658289432526, reward = 0.07592859119176865\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  8%|▊         | 801/10000 [07:30<7:48:58,  3.06s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 800: loss = -0.009554612450301647, reward = 0.06064216047525406\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  9%|▉         | 901/10000 [08:27<7:47:50,  3.09s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 900: loss = -0.013438339345157146, reward = 0.13207818567752838\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 10%|█         | 1001/10000 [09:21<6:25:21,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1000: loss = -0.02279972843825817, reward = 0.07570149004459381\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 11%|█         | 1101/10000 [10:12<6:18:53,  2.55s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1100: loss = -0.02009693719446659, reward = 0.06107410043478012\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 12%|█▏        | 1201/10000 [11:01<6:13:26,  2.55s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1200: loss = -0.03956253081560135, reward = -0.14187034964561462\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 13%|█▎        | 1301/10000 [11:52<6:09:56,  2.55s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1300: loss = 0.006894805934280157, reward = -0.08655361086130142\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 14%|█▍        | 1401/10000 [12:41<6:05:52,  2.55s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1400: loss = -0.011612087488174438, reward = 0.08446063101291656\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 15%|█▌        | 1501/10000 [13:32<6:04:33,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1500: loss = 0.13603658974170685, reward = -0.004821706563234329\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 16%|█▌        | 1601/10000 [14:24<6:06:23,  2.62s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1600: loss = -0.026009418070316315, reward = 0.095827117562294\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 17%|█▋        | 1701/10000 [15:13<5:53:48,  2.56s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1700: loss = -0.002900458872318268, reward = 0.02800840511918068\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 18%|█▊        | 1801/10000 [16:02<5:48:56,  2.55s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1800: loss = -0.0037551005370914936, reward = 0.07382015883922577\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 19%|█▉        | 1901/10000 [16:53<6:16:09,  2.79s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 1900: loss = 0.003202388994395733, reward = 0.04558534920215607\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 20%|██        | 2001/10000 [17:45<5:43:12,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2000: loss = -0.01820695959031582, reward = 0.07326477766036987\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 21%|██        | 2101/10000 [18:38<5:53:28,  2.68s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2100: loss = -0.020956963300704956, reward = 0.05151586979627609\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 22%|██▏       | 2201/10000 [19:28<5:44:00,  2.65s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2200: loss = -0.02764793112874031, reward = 0.08506140112876892\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 23%|██▎       | 2301/10000 [20:18<5:59:03,  2.80s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2300: loss = 0.001491648145020008, reward = 0.10345141589641571\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 24%|██▍       | 2401/10000 [21:08<5:45:57,  2.73s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2400: loss = -0.0023741128388792276, reward = 0.05721893161535263\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 25%|██▌       | 2501/10000 [21:58<5:30:18,  2.64s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2500: loss = -0.026749931275844574, reward = -0.3260703980922699\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 26%|██▌       | 2601/10000 [22:49<5:48:27,  2.83s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2600: loss = -0.009807603433728218, reward = -0.4977230131626129\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 27%|██▋       | 2701/10000 [23:40<5:23:21,  2.66s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2700: loss = -0.003918954636901617, reward = -0.5366655588150024\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 28%|██▊       | 2801/10000 [24:32<5:22:57,  2.69s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2800: loss = -0.007426843512803316, reward = -0.515765368938446\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 29%|██▉       | 2901/10000 [25:23<5:12:43,  2.64s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 2900: loss = -0.027111032977700233, reward = -0.6060086488723755\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 30%|███       | 3001/10000 [26:14<5:01:33,  2.59s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3000: loss = -0.009513258934020996, reward = 0.05808001756668091\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 31%|███       | 3101/10000 [27:06<5:15:35,  2.74s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3100: loss = -0.09422209858894348, reward = -0.010376416146755219\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 32%|███▏      | 3201/10000 [28:00<5:23:22,  2.85s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3200: loss = -0.022492051124572754, reward = -0.1794758141040802\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 33%|███▎      | 3301/10000 [28:54<5:09:37,  2.77s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3300: loss = -0.03663545101881027, reward = -0.08150073885917664\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 34%|███▍      | 3401/10000 [29:49<4:57:58,  2.71s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3400: loss = -0.014627097174525261, reward = -0.14371761679649353\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 35%|███▌      | 3501/10000 [30:45<4:53:07,  2.71s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3500: loss = -0.006813403218984604, reward = -0.16940483450889587\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 36%|███▌      | 3601/10000 [31:53<11:02:02,  6.21s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3600: loss = -0.0007351728272624314, reward = -0.1557752788066864\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 37%|███▋      | 3701/10000 [32:53<5:00:30,  2.86s/it] "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3700: loss = 0.0016316949622705579, reward = -0.10929298400878906\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 38%|███▊      | 3801/10000 [33:48<4:42:03,  2.73s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3800: loss = -0.006584027782082558, reward = -0.1447393149137497\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 39%|███▉      | 3901/10000 [34:41<4:28:01,  2.64s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 3900: loss = -0.039411235600709915, reward = -0.12452354282140732\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 40%|████      | 4001/10000 [35:35<4:22:33,  2.63s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4000: loss = -0.014827650040388107, reward = -0.1095043420791626\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 41%|████      | 4101/10000 [36:29<4:50:42,  2.96s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4100: loss = -0.013007811270654202, reward = -0.14809484779834747\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 42%|████▏     | 4201/10000 [37:38<4:22:12,  2.71s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4200: loss = -0.006307572592049837, reward = -0.13430342078208923\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 43%|████▎     | 4301/10000 [38:30<4:16:43,  2.70s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4300: loss = 0.003515255870297551, reward = -0.12775585055351257\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 44%|████▍     | 4401/10000 [39:23<4:21:52,  2.81s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4400: loss = 0.004743673373013735, reward = -0.11923233419656754\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 45%|████▌     | 4501/10000 [40:19<4:01:43,  2.64s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4500: loss = 0.005955316126346588, reward = -0.12080593407154083\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 46%|████▌     | 4601/10000 [41:11<3:53:44,  2.60s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4600: loss = -0.05429302901029587, reward = -0.08684021234512329\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 47%|████▋     | 4701/10000 [42:00<3:44:05,  2.54s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4700: loss = 0.005476806312799454, reward = 0.005218320991843939\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 48%|████▊     | 4801/10000 [42:51<3:50:34,  2.66s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4800: loss = 0.002454745350405574, reward = -0.02282392606139183\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 49%|████▉     | 4901/10000 [43:41<3:38:04,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 4900: loss = 0.00216989335604012, reward = 0.008491285145282745\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 50%|█████     | 5001/10000 [44:32<3:33:03,  2.56s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5000: loss = 0.007778072264045477, reward = -0.05301349237561226\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 51%|█████     | 5101/10000 [45:22<3:27:46,  2.54s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5100: loss = -0.10312110930681229, reward = 0.1318182647228241\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 52%|█████▏    | 5201/10000 [46:12<3:24:23,  2.56s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5200: loss = -0.00267457845620811, reward = -0.1441565603017807\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 53%|█████▎    | 5301/10000 [47:02<3:23:29,  2.60s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5300: loss = -0.009113558568060398, reward = -0.008346456103026867\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 54%|█████▍    | 5401/10000 [47:52<3:16:34,  2.56s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5400: loss = -0.004117089323699474, reward = -0.005369010381400585\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 55%|█████▌    | 5501/10000 [48:43<3:11:44,  2.56s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5500: loss = -0.0033366698771715164, reward = 0.006968374364078045\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 56%|█████▌    | 5601/10000 [49:33<3:07:15,  2.55s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5600: loss = 0.0053539699874818325, reward = -0.3954353928565979\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 57%|█████▋    | 5701/10000 [50:23<3:01:32,  2.53s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5700: loss = -0.005777641199529171, reward = -0.4003916382789612\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 58%|█████▊    | 5801/10000 [51:13<2:58:54,  2.56s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5800: loss = -0.0013245362788438797, reward = -0.08402419835329056\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 59%|█████▉    | 5901/10000 [52:03<2:53:27,  2.54s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 5900: loss = 0.004345765803009272, reward = -0.11660643666982651\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 60%|██████    | 6001/10000 [52:53<2:50:32,  2.56s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6000: loss = -0.00141683139372617, reward = -0.37293437123298645\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 61%|██████    | 6101/10000 [53:43<2:46:44,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6100: loss = 0.0020304021891206503, reward = -0.46715623140335083\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 62%|██████▏   | 6201/10000 [54:33<2:41:45,  2.55s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6200: loss = 0.002308701630681753, reward = -0.4524999260902405\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 63%|██████▎   | 6301/10000 [55:23<2:36:05,  2.53s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6300: loss = 0.000125030055642128, reward = -0.5659657120704651\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 64%|██████▍   | 6401/10000 [56:13<2:32:57,  2.55s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6400: loss = -0.0006637836340814829, reward = -0.5557823777198792\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 65%|██████▌   | 6501/10000 [57:03<2:28:50,  2.55s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6500: loss = -0.003973644692450762, reward = 0.05257822945713997\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 66%|██████▌   | 6601/10000 [57:53<2:24:07,  2.54s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6600: loss = -0.007424875628203154, reward = 0.02047843299806118\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 67%|██████▋   | 6701/10000 [58:43<2:20:26,  2.55s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6700: loss = -0.03125167265534401, reward = -0.08490550518035889\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 68%|██████▊   | 6801/10000 [59:34<2:20:06,  2.63s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6800: loss = -0.006715892814099789, reward = -0.20727285742759705\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 69%|██████▉   | 6901/10000 [1:00:26<2:12:41,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 6900: loss = -0.002833651378750801, reward = -0.14743776619434357\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 70%|███████   | 7001/10000 [1:01:17<2:11:12,  2.62s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7000: loss = -0.0018620153423398733, reward = -0.03974051773548126\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 71%|███████   | 7101/10000 [1:02:21<2:05:20,  2.59s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7100: loss = -0.006395635660737753, reward = -0.13103936612606049\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 72%|███████▏  | 7201/10000 [1:03:15<2:01:14,  2.60s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7200: loss = -0.0013959211064502597, reward = -0.09121858328580856\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 73%|███████▎  | 7301/10000 [1:04:08<1:56:31,  2.59s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7300: loss = -0.030369849875569344, reward = -0.13139879703521729\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 74%|███████▍  | 7401/10000 [1:05:01<1:52:57,  2.61s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7400: loss = -0.0003544760402292013, reward = -0.17020411789417267\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 75%|███████▌  | 7501/10000 [1:05:54<1:47:44,  2.59s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7500: loss = -0.0017358472105115652, reward = -0.09534154832363129\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 76%|███████▌  | 7601/10000 [1:06:47<1:44:21,  2.61s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7600: loss = -0.00711114052683115, reward = -0.09150321781635284\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 77%|███████▋  | 7701/10000 [1:07:40<1:38:42,  2.58s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7700: loss = -0.01760304719209671, reward = 0.01841781474649906\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 78%|███████▊  | 7801/10000 [1:08:33<1:34:56,  2.59s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7800: loss = -0.0004201991541776806, reward = 0.11232483386993408\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 79%|███████▉  | 7901/10000 [1:09:25<1:30:09,  2.58s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 7900: loss = 0.0022978587076067924, reward = 0.0885215550661087\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 80%|████████  | 8001/10000 [1:10:18<1:27:39,  2.63s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8000: loss = 0.0017010057345032692, reward = 0.06793919205665588\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 81%|████████  | 8101/10000 [1:11:10<1:21:48,  2.58s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8100: loss = 0.0019339965656399727, reward = 0.08732522279024124\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 82%|████████▏ | 8201/10000 [1:12:02<1:17:01,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8200: loss = -0.001657668617554009, reward = 0.023821990936994553\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 83%|████████▎ | 8301/10000 [1:15:04<1:13:48,  2.61s/it] "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8300: loss = -0.002437570597976446, reward = 0.10907639563083649\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 84%|████████▍ | 8401/10000 [1:15:55<1:08:07,  2.56s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8400: loss = -0.002247120952233672, reward = 0.038752634078264236\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 85%|████████▌ | 8501/10000 [1:16:46<1:04:17,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8500: loss = -0.0022757744882255793, reward = 0.06408777832984924\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 86%|████████▌ | 8601/10000 [1:17:36<1:00:02,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8600: loss = -0.004113011993467808, reward = -0.0400715097784996\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 87%|████████▋ | 8701/10000 [1:18:27<56:11,  2.60s/it]  "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8700: loss = -0.002262270776554942, reward = -0.05166323855519295\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 88%|████████▊ | 8801/10000 [1:19:18<51:27,  2.58s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8800: loss = -0.0010613177437335253, reward = -0.09124276041984558\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 89%|████████▉ | 8901/10000 [1:20:09<46:44,  2.55s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 8900: loss = -0.002044474007561803, reward = -0.5163190364837646\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 90%|█████████ | 9001/10000 [1:21:00<42:35,  2.56s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9000: loss = -0.0025240506511181593, reward = -0.572773814201355\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 91%|█████████ | 9101/10000 [1:21:51<38:26,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9100: loss = -0.0029183807782828808, reward = -0.5777910947799683\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 92%|█████████▏| 9201/10000 [1:22:43<34:21,  2.58s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9200: loss = -0.0010590116726234555, reward = -0.5694754123687744\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 93%|█████████▎| 9301/10000 [1:23:34<29:59,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9300: loss = -0.00102526496630162, reward = 0.052893705666065216\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 94%|█████████▍| 9401/10000 [1:24:25<25:38,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9400: loss = -0.0010977387428283691, reward = -0.520660936832428\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 95%|█████████▌| 9501/10000 [1:25:17<21:17,  2.56s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9500: loss = -0.016466550529003143, reward = -0.010863653384149075\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 96%|█████████▌| 9601/10000 [1:26:08<16:59,  2.56s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9600: loss = -0.004927287343889475, reward = 0.09239820390939713\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 97%|█████████▋| 9701/10000 [1:26:59<12:47,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9700: loss = -0.05658155307173729, reward = 0.10042295604944229\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 98%|█████████▊| 9801/10000 [1:27:50<08:30,  2.56s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9800: loss = -0.007920180447399616, reward = 0.06870749592781067\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 99%|█████████▉| 9901/10000 [1:28:41<04:14,  2.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "step = 9900: loss = -0.0016685246955603361, reward = 0.05374101921916008\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 10000/10000 [1:29:25<00:00,  1.86it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "loss, observations, rewards = train(\n",
+    "    agent, train_env, test_env, collect_driver, replay_buffer, steps = num_steps, eval_interval=100)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/ellkrauze/projects/gc-ml/gc-ml-env/lib/python3.8/site-packages/tensorflow/python/saved_model/nested_structure_coder.py:475: UserWarning: Encoding a StructuredValue with type tfp.distributions.Deterministic_ACTTypeSpec; loading this StructuredValue will require that this type be imported and registered.\n",
+      "  warnings.warn(\"Encoding a StructuredValue with type %s; loading this \"\n"
+     ]
+    }
+   ],
+   "source": [
+    "tf_policy_saver.save(policy_dir)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plot_training(loss, rewards, num_steps, 100)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def test(env, policy, patience: int=50, verbose: bool=False, num_flags: int=2):\n",
+    "    i = 0\n",
+    "    _observations = np.array([])\n",
+    "    _actions = np.array([])\n",
+    "    \n",
+    "    time_step = env.reset()\n",
+    "    default_state = get_env_state(env)\n",
+    "    \n",
+    "    while not time_step.is_last():\n",
+    "        if i >= patience:\n",
+    "            break\n",
+    "        \n",
+    "        _observations = np.append(_observations, time_step.observation.numpy().squeeze()[:num_flags])\n",
+    "        \n",
+    "        action_step = policy.action(time_step)\n",
+    "        time_step = env.step(action_step.action)\n",
+    "        \n",
+    "        _actions = np.append(_actions, action_step.action.numpy()[0])\n",
+    "\n",
+    "        i += 1\n",
+    "        \n",
+    "    if verbose:\n",
+    "        print(\"start:\", *default_state, \n",
+    "          \"recommendation:\", *get_env_state(env))\n",
+    "    \n",
+    "    return _observations, _actions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 88,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Getting 5000 samples...\n"
+     ]
+    }
+   ],
+   "source": [
+    "# observations = np.array([])\n",
+    "# actions = np.array([])\n",
+    "observations = []\n",
+    "actions = []\n",
+    "# flags_num = 2\n",
+    "flags_num = 10\n",
+    "num_episodes = 500\n",
+    "# num_episodes = 1\n",
+    "envs = [*batched_env.envs] # , JVMEnv(bm_name=\"h2\", **env_args)\n",
+    "\n",
+    "print(f\"Getting {num_episodes * len(envs)} samples...\")\n",
+    "\n",
+    "for env in envs:\n",
+    "    # print(env._bm)\n",
+    "    env = tf_py_environment.TFPyEnvironment(env)\n",
+    "    \n",
+    "    for _ in range(num_episodes):\n",
+    "        # Get the agent's next recommendation (patience=1)\n",
+    "        # based on the input state.\n",
+    "        obs, act = test(env, agent.policy, patience=1, verbose=False, num_flags=flags_num)\n",
+    "        observations.append(obs)\n",
+    "        actions.append(act)\n",
+    "        # observations = np.vstack([observations, obs])\n",
+    "        # actions = np.vstack([actions, act])\n",
+    "    \n",
+    "# print(\"Test environments\")\n",
+    "# obs, act = test(test_env, agent.policy, patience=1)\n",
+    "# observations.append(obs)\n",
+    "# actions.append(act)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 89,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>observations</th>\n",
+       "      <th>actions</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>[13.0, 16.0, 0.009589999914169312, 0.994306325...</td>\n",
+       "      <td>[2.0]</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>[10.0, 20.0, 0.008620000444352627, 0.992601871...</td>\n",
+       "      <td>[2.0]</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>[13.0, 16.0, 0.009589999914169312, 0.994306325...</td>\n",
+       "      <td>[2.0]</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>[7.0, 16.0, 0.008170000277459621, 0.9922335147...</td>\n",
+       "      <td>[0.0]</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>[13.0, 12.0, 0.00880999956279993, 0.9933167695...</td>\n",
+       "      <td>[0.0]</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>[7.0, 4.0, 0.010130000300705433, 0.99206787347...</td>\n",
+       "      <td>[2.0]</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>[10.0, 8.0, 0.00839999970048666, 0.99285924434...</td>\n",
+       "      <td>[0.0]</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>[1.0, 12.0, 0.0072200000286102295, 0.992177724...</td>\n",
+       "      <td>[0.0]</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>[13.0, 8.0, 0.009399999864399433, 0.9920404553...</td>\n",
+       "      <td>[0.0]</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>[13.0, 20.0, 0.010130000300705433, 0.992835521...</td>\n",
+       "      <td>[2.0]</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                        observations actions\n",
+       "0  [13.0, 16.0, 0.009589999914169312, 0.994306325...   [2.0]\n",
+       "1  [10.0, 20.0, 0.008620000444352627, 0.992601871...   [2.0]\n",
+       "2  [13.0, 16.0, 0.009589999914169312, 0.994306325...   [2.0]\n",
+       "3  [7.0, 16.0, 0.008170000277459621, 0.9922335147...   [0.0]\n",
+       "4  [13.0, 12.0, 0.00880999956279993, 0.9933167695...   [0.0]\n",
+       "5  [7.0, 4.0, 0.010130000300705433, 0.99206787347...   [2.0]\n",
+       "6  [10.0, 8.0, 0.00839999970048666, 0.99285924434...   [0.0]\n",
+       "7  [1.0, 12.0, 0.0072200000286102295, 0.992177724...   [0.0]\n",
+       "8  [13.0, 8.0, 0.009399999864399433, 0.9920404553...   [0.0]\n",
+       "9  [13.0, 20.0, 0.010130000300705433, 0.992835521...   [2.0]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "df = pd.DataFrame(data={\n",
+    "    \"observations\": observations,\n",
+    "    \"actions\": actions,\n",
+    "})\n",
+    "# df[[\"MaxTenuringThreshold\", \"ParallelGCThreads\"]] = df[\"observations\"].apply(pd.Series)\n",
+    "# df = df.drop(columns=[\"observations\"])\n",
+    "display(df[:10])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Here we transform the input data X by PCA into Xt. We consider only the first two columns, which contain the most information, and plot it in two dimensional. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 90,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 500x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import seaborn as sns\n",
+    "from sklearn.decomposition import PCA\n",
+    "from sklearn.manifold import TSNE\n",
+    "from sklearn.cluster import KMeans\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "\n",
+    "fig = plt.figure(figsize=(5, 5))\n",
+    "X, y = df[\"observations\"].apply(pd.Series), df[\"actions\"]\n",
+    "\n",
+    "Xt = StandardScaler().fit_transform(X) # normalizing the features\n",
+    "\n",
+    "Xt = TSNE().fit_transform(X)\n",
+    "\n",
+    "plot = plt.scatter(Xt[:,0], Xt[:,1], c=y)\n",
+    "\n",
+    "# plot = plt.scatter(X[0], X[1], c=y)\n",
+    "target_names = [\n",
+    "    \"decrease_MaxTenuringThreshold\", \n",
+    "    \"increase_MaxTenuringThreshold\", \n",
+    "    \"decrease_ParallelGCThreads\", \n",
+    "    \"increase_ParallelGCThreads\"\n",
+    "]\n",
+    "# plt.legend(handles=plot.legend_elements()[0], labels=target_names)\n",
+    "plt.legend(\n",
+    "    handles=plot.legend_elements()[0], labels=target_names,  bbox_to_anchor=(1.1, 1.0))\n",
+    "# plt.xlabel(\"MaxTenuringThreshold\")\n",
+    "# plt.ylabel(\"ParallelGCThreads\")\n",
+    "plt.xlabel(\"Principal Component 1\")\n",
+    "plt.ylabel(\"Principal Component 2\")\n",
+    "plt.grid()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 93,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 500x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from sklearn.decomposition import PCA\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "\n",
+    "fig = plt.figure(figsize=(5, 5))\n",
+    "X, y = df[\"observations\"].apply(pd.Series), df[\"actions\"]\n",
+    "\n",
+    "X = StandardScaler().fit_transform(X) # normalizing the features\n",
+    "\n",
+    "# pca = PCA()\n",
+    "# Xt = pca.fit_transform(X)\n",
+    "\n",
+    "# plot = plt.scatter(Xt[:,0], Xt[:,1], c=y)\n",
+    "# plot = plt.scatter(X[0], X[1], c=y)\n",
+    "plot = plt.scatter(X[:, 0], X[:, 1], c=y)\n",
+    "target_names = [\n",
+    "    \"decrease_MaxTenuringThreshold\", \n",
+    "    \"increase_MaxTenuringThreshold\", \n",
+    "    \"decrease_ParallelGCThreads\", \n",
+    "    \"increase_ParallelGCThreads\"\n",
+    "]\n",
+    "\n",
+    "plt.legend(\n",
+    "    handles=plot.legend_elements()[0], labels=target_names,  bbox_to_anchor=(1.1, 1.0))\n",
+    "plt.xlabel(\"MaxTenuringThreshold\")\n",
+    "plt.ylabel(\"ParallelGCThreads\")\n",
+    "# plt.xlabel(\"Principal Component 1\")\n",
+    "# plt.ylabel(\"Principal Component 2\")\n",
+    "plt.grid()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 154,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "KeyError",
+     "evalue": "(slice(None, None, None), 0)",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[154], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mX\u001b[49m\u001b[43m[\u001b[49m\u001b[43m:\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\n",
+      "File \u001b[0;32m~/projects/gc-ml/gc-ml-env/lib/python3.8/site-packages/pandas/core/frame.py:3761\u001b[0m, in \u001b[0;36mDataFrame.__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   3759\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcolumns\u001b[38;5;241m.\u001b[39mnlevels \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m   3760\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_getitem_multilevel(key)\n\u001b[0;32m-> 3761\u001b[0m indexer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcolumns\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   3762\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_integer(indexer):\n\u001b[1;32m   3763\u001b[0m     indexer \u001b[38;5;241m=\u001b[39m [indexer]\n",
+      "File \u001b[0;32m~/projects/gc-ml/gc-ml-env/lib/python3.8/site-packages/pandas/core/indexes/range.py:349\u001b[0m, in \u001b[0;36mRangeIndex.get_loc\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m    347\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(key) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01merr\u001b[39;00m\n\u001b[1;32m    348\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(key, Hashable):\n\u001b[0;32m--> 349\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(key)\n\u001b[1;32m    350\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_check_indexing_error(key)\n\u001b[1;32m    351\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(key)\n",
+      "\u001b[0;31mKeyError\u001b[0m: (slice(None, None, None), 0)"
+     ]
+    }
+   ],
+   "source": [
+    "X[:, 0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.011308405\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(compute_avg_return_episodic(test_env, agent.policy, num_episodes=50))\n",
+    "# print(compute_avg_return_episodic(test_env_2, agent.policy, num_episodes=50))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### PCA Visualization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Save the progress.\n",
+    "train_checkpointer.save(global_step)\n",
+    "tf_policy_saver.save(policy_dir)"
    ]
   },
   {
diff --git a/requirements.txt b/requirements-macos.txt
similarity index 100%
rename from requirements.txt
rename to requirements-macos.txt
diff --git a/util/dataset_util.py b/util/dataset_util.py
index db66b55..ead29cb 100644
--- a/util/dataset_util.py
+++ b/util/dataset_util.py
@@ -1,4 +1,5 @@
 import os
+import glob
 import pandas as pd
 import numpy as np
 import seaborn as sns
@@ -25,17 +26,21 @@ def get_data_from_csv(csv_dir: str, goals):
     flag_2_values = []
     goal_values = []
 
-    for summary in os.listdir(csv_dir):
+    for summary in glob.glob(csv_dir):
         basename = os.path.splitext(summary)[0]
         p, m = basename.split('_')[-2], basename.split('_')[-1]
-        summary_abs_path = os.path.join(csv_dir, summary)
+        summary_abs_path = os.path.abspath(summary)
 
         summary_df = (pd
                       .read_csv(
                           summary_abs_path, sep=sep, skiprows=1, header=None)
                       .replace(',', '', regex=True)
                       .replace('n.a.', 'NaN', regex=True))
-        params = summary_df[summary_df[0].isin(goals)][1].astype(float).values
+        # params = summary_df[summary_df[0].isin(goals)][1].astype(float).values
+        params = []
+        for goal in goals:
+            param = summary_df[summary_df[0] == goal][1].astype(float).values[0]
+            params.append(param)
         assert len(goals) == len(params), "Check if goal name is in summary"
         
         flag_1_values.append(int(p))
diff --git a/util/plots_util.py b/util/plots_util.py
index 45478e9..5d10f6c 100644
--- a/util/plots_util.py
+++ b/util/plots_util.py
@@ -47,7 +47,7 @@ def plot_goal_heatmap(env, flags=None, goal: str="Average GC Pause"):
         flags[1]: Y, 
         goal: Z})
     data_pivoted = data.pivot(index=flags[0], columns=flags[1], values=goal)
-    ax = sns.heatmap(data_pivoted, annot=True, ax=ax, fmt=".2f")
+    ax = sns.heatmap(data_pivoted, annot=True, ax=ax, fmt=".3f")
     ax.invert_yaxis()
     plt.show()
 
@@ -65,6 +65,6 @@ def plot_heatmap(x, y, z, flags=None, goal: str="Average GC Pause"):
         goal: z})
     
     data_pivoted = data.pivot(index=flags[0], columns=flags[1], values=goal)
-    ax = sns.heatmap(data_pivoted, annot=True, ax=ax, fmt=".2f")
+    ax = sns.heatmap(data_pivoted, annot=True, ax=ax, fmt=".3f")
     ax.invert_yaxis()
     plt.show()
\ No newline at end of file