Implementation of the DDPG algorithm to solve Continuous Control Reacher Environment
-
Updated
Jan 26, 2019 - Jupyter Notebook
Implementation of the DDPG algorithm to solve Continuous Control Reacher Environment
Actor Critic approach for solving Reacher - Unity environment with continuous control
Deep Reinforcement Learning Project 2
Contains PyTorch Implementation of the following off policy actor critic algorithms
The DDPG algorithm incorporates Actor-Critic Deep Learning Agent for solving continuous action reinforcement learning problems.
Weakly supervised RL with safety cages for autonomous highway driving
DQN with Prioritized Experience Replay, DDPG for Continous Environments, DDPG for Multi-Agent Reinforcement Learning
Exploring different buffer sampling techniques to improve Hindisght Experience Replay on continuous control robotic application tasks. Continous action spaces & sparse rewards.
Contains deep reinforcement learning algorithms I have implemented.
PyTorch implementation of Twin Delayed Deep Deterministic Policy Gradient (TD3) - including additional Extension to improve the algorithm's performance.
My implementation of Udacity ML Nanodegree Quadcopter project
A simple parallel RL framework implemented with PyTorch and OpenAI Gym for an Inverted Pendulum with image data
GSC: Generalizable Service Coordination
Deep Learning Spring 2023 @ NYCU
Personal Collection of Reinforcement Learning Algorithms. So far: Parallelized DDPG,...
Learning to play tennis from scratch with AlphaGo Zero style self-play using DDPG
Mujoco Hopper agent with DDPG
Add a description, image, and links to the ddpg topic page so that developers can more easily learn about it.
To associate your repository with the ddpg topic, visit your repo's landing page and select "manage topics."