Skip to content

Fix uint8 issue for newer versions of PyTorch #6

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

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Fix uint8 issue for newer versions of PyTorch #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9d7c500
Fix uint8 issue for newer versions of PyTorch
srikanthkb May 5, 2020
0351272
Update dueling_ddqn_agent.py
srikanthkb May 5, 2020
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
4 changes: 2 additions & 2 deletions DDQN/ddqn_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ def sample_memory(self):

states = T.tensor(state).to(self.q_eval.device)
rewards = T.tensor(reward).to(self.q_eval.device)
dones = T.tensor(done).to(self.q_eval.device)
dones = T.tensor(done, dtype=T.bool).to(self.q_eval.device)
actions = T.tensor(action).to(self.q_eval.device)
states_ = T.tensor(new_state).to(self.q_eval.device)

Expand Down Expand Up @@ -83,7 +83,7 @@ def learn(self):
q_next = self.q_next.forward(states_)
q_eval = self.q_eval.forward(states_)

max_actions = T.argmax(q_eval, dim=1)
max_actions = T.argmax(q_eval, dim=1).detach()
q_next[dones] = 0.0

q_target = rewards + self.gamma*q_next[indices, max_actions]
Expand Down
2 changes: 1 addition & 1 deletion DQN/dqn_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ def sample_memory(self):

states = T.tensor(state).to(self.q_eval.device)
rewards = T.tensor(reward).to(self.q_eval.device)
dones = T.tensor(done).to(self.q_eval.device)
dones = T.tensor(done, dtype=T.bool).to(self.q_eval.device)
actions = T.tensor(action).to(self.q_eval.device)
states_ = T.tensor(new_state).to(self.q_eval.device)

Expand Down
4 changes: 2 additions & 2 deletions DuelingDDQN/dueling_ddqn_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ def sample_memory(self):

states = T.tensor(state).to(self.q_eval.device)
rewards = T.tensor(reward).to(self.q_eval.device)
dones = T.tensor(done).to(self.q_eval.device)
dones = T.tensor(done, dtype=T.bool).to(self.q_eval.device)
actions = T.tensor(action).to(self.q_eval.device)
states_ = T.tensor(new_state).to(self.q_eval.device)

Expand Down Expand Up @@ -92,7 +92,7 @@ def learn(self):

q_eval = T.add(V_s_eval, (A_s_eval - A_s_eval.mean(dim=1,keepdim=True)))

max_actions = T.argmax(q_eval, dim=1)
max_actions = T.argmax(q_eval, dim=1).detach()
q_next[dones] = 0.0

q_target = rewards + self.gamma*q_next[indices, max_actions]
Expand Down
2 changes: 1 addition & 1 deletion DuelingDQN/dueling_dqn_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ def sample_memory(self):

states = T.tensor(state).to(self.q_eval.device)
rewards = T.tensor(reward).to(self.q_eval.device)
dones = T.tensor(done).to(self.q_eval.device)
dones = T.tensor(done, dtype=T.bool).to(self.q_eval.device)
actions = T.tensor(action).to(self.q_eval.device)
states_ = T.tensor(new_state).to(self.q_eval.device)

Expand Down