Skip to content

fix(saute): coerce tensors to correct device in SauteAdapter #387

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
96sanjay wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(saute): coerce tensors to correct device in SauteAdapter #387

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
7 changes: 7 additions & 0 deletions omnisafe/adapter/saute_adapter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,6 +128,7 @@ def reset(
info: Some information logged by the environment.
"""
obs, info = self._env.reset(seed=seed, options=options)
obs = obs.to(self._device)
self._safety_obs = torch.ones(self._env.num_envs, 1).to(self._device)
obs = self._augment_obs(obs)
return obs, info
Expand Down Expand Up @@ -161,6 +162,11 @@ def step(
info: Some information logged by the environment.
"""
next_obs, reward, cost, terminated, truncated, info = self._env.step(action)
next_obs = next_obs.to(self._device)
reward = reward.to(self._device)
cost = cost.to(self._device)
terminated = terminated.to(self._device)
truncated = truncated.to(self._device)
info['original_reward'] = reward

self._safety_step(cost)
Expand Down Expand Up @@ -214,6 +220,7 @@ def _augment_obs(self, obs: torch.Tensor) -> torch.Tensor:
Returns:
The augmented observation.
"""
obs = obs.to(self._device)
return torch.cat([obs, self._safety_obs], dim=-1)

def _log_value(
Expand Down