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

https://github.com/lcswillems/rl-starter-files/issues/46 #47

Merged
merged 1 commit into from
Oct 18, 2020
Merged

https://github.com/lcswillems/rl-starter-files/issues/46 #47

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
https://github.com/lcswillems/rl-starter-files/issues/46
  • Loading branch information
Vitalii A committed Oct 18, 2020
commit b12ea43a66baf6c3e29102a4c42755917785ced9
4 changes: 2 additions & 2 deletions utils/agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ def __init__(self, obs_space, action_space, model_dir,
self.num_envs = num_envs

if self.acmodel.recurrent:
self.memories = torch.zeros(self.num_envs, self.acmodel.memory_size)
self.memories = torch.zeros(self.num_envs, self.acmodel.memory_size, device=self.device)

self.acmodel.load_state_dict(utils.get_model_state(model_dir))
self.acmodel.to(self.device)
Expand Down Expand Up @@ -49,7 +49,7 @@ def get_action(self, obs):

def analyze_feedbacks(self, rewards, dones):
if self.acmodel.recurrent:
masks = 1 - torch.tensor(dones, dtype=torch.float).unsqueeze(1)
masks = 1 - torch.tensor(dones, dtype=torch.float, device=self.device).unsqueeze(1)
self.memories *= masks

def analyze_feedback(self, reward, done):
Expand Down