Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update: vision #1

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update: vision #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added player_game/env/__pycache__/grid.cpython-38.pyc
View file
Open in desktop
Binary file not shown.
Binary file added player_game/env/__pycache__/player.cpython-38.pyc
View file
Open in desktop
Binary file not shown.
Binary file added player_game/env/__pycache__/plot.cpython-38.pyc
View file
Open in desktop
Binary file not shown.
Binary file added player_game/env/__pycache__/utils.cpython-38.pyc
View file
Open in desktop
Binary file not shown.
14 changes: 7 additions & 7 deletions player_game/env/grid.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,14 +42,14 @@ def __init__(self, player, n_rows=10, n_cols=10, screen_width=1000, screen_heigh

self.grid = array([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 3, 3, 3, 0, 3, 3, 3, 0, 0],
[0, 0, 3, 0, 0, 3, 0, 3, 0, 0],
[0, 0, 3, 0, 0, 3, 3, 3, 0, 0],
[0, 0, 3, 0, 0, 3, 0, 3, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 3, 0, 0, 0, 3, 0, 0, 0],
[0, 0, 3, 0, 0, 0, 3, 0, 0, 0],
[0, 0, 3, 0, 0, 0, 3, 3, 0, 0]]).T
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]).T

# Posicao do objetivo
self.goal_x = randint(0, n_cols-1)
Expand Down
23 changes: 9 additions & 14 deletions player_game/env/rat_game_env.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,7 +113,7 @@ def _get_state(self):
current_x = self.agent.x
current_y = self.agent.y

while self.maze.grid.is_valid_position(self.maze.grid[current_x, current_y]):
for i in range(2):
if self.agent.direction == "Up":
current_x -= 1
state.append(self.maze.grid[current_x, current_y])
Expand All @@ -130,7 +130,7 @@ def _get_state(self):
current_y -= 1
state.append(self.maze.grid[current_x, current_y])

return (self.agent.x, self.agent.y)
return (self.agent.x, self.agent.y, state)

def _take_action(self, action):
self.agent.got_cheese = False
Expand All @@ -157,7 +157,7 @@ def __init__(self):
self.maze_size = tuple([10,10])
self.state_bounds = list(zip([0,0], [10,10]))
self.number_actions = 4
self.Q = np.zeros(self.maze_size + (self.number_actions, ), dtype=float)
self.Q = np.zeros(self.maze_size + (4, 4) + (self.number_actions, ), dtype=float)
self.epsilon = 1
self.learning_rate = 1
self.decay = DECAY
Expand All @@ -167,16 +167,7 @@ def __init__(self):


def discretize_state(self, state) -> tuple:
discretazed_state = []
for i in range(len(state)):
if state[i] <= self.state_bounds[i][0]:
new_state = 0
elif state[i] >= self.state_bounds[i][1]:
new_state = (10,10)[i] - 1
else:
new_state = int(round(state[i]))
discretazed_state.append(new_state)
return tuple(discretazed_state)
return tuple(state)

def decide_action(self, state) -> int:

Expand All @@ -188,6 +179,10 @@ def decide_action(self, state) -> int:
return action

def update_q(self, current_state, action, reward, next_state):
print("current:",current_state)
print("next:",next_state)
print("action:", action)
print("sum",tuple(current_state) + (action,))

self.Q[tuple(current_state) + (action,)] = self.Q[tuple(current_state) + (action,)] + self.learning_rate * (reward + self.discount * np.max(self.Q[tuple(next_state)]) - self.Q[tuple(current_state) + (action,)])

Expand All @@ -206,7 +201,7 @@ def update_epsilon(self, episode) -> float:
def train(self):
for episode in range(EPISODES):
current_state = self.env._reset()
#current_state = self.discretize_state(current_state)
current_state = self.discretize_state(current_state)

done = False

Expand Down