Skip to content

Fix observation space issue for BaseEnv #125

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

Merged
yuecideng merged 2 commits into from
Feb 9, 2026
Merged

Fix observation space issue for BaseEnv #125

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
aaf5d0e
wip
yuecideng Feb 9, 2026
f3b3170
wip
yuecideng Feb 9, 2026
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
22 changes: 22 additions & 0 deletions embodichain/lab/gym/utils/gym_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,6 +77,28 @@ def convert_observation_to_space(
array = np.array(observation)
dtype = array.dtype
space = spaces.Box(-np.inf, np.inf, shape=array.shape, dtype=dtype)
elif isinstance(observation, torch.Tensor):
if unbatched:
shape = observation.shape[1:]
else:
shape = observation.shape
dtype = observation.dtype
# Map torch dtype to numpy dtype and reuse get_dtype_bounds for consistency
torch_to_numpy_dtype = {
torch.float16: np.float16,
torch.float32: np.float32,
torch.float64: np.float64,
torch.int8: np.int8,
torch.int16: np.int16,
torch.int32: np.int32,
torch.int64: np.int64,
torch.bool: np.bool_,
}
np_dtype = torch_to_numpy_dtype.get(dtype, np.float32)
low, high = get_dtype_bounds(np_dtype)
if np.issubdtype(np_dtype, np.floating):
low, high = -np.inf, np.inf
space = spaces.Box(low, high, shape=shape, dtype=np_dtype)
elif isinstance(observation, np.ndarray):
if unbatched:
shape = observation.shape[1:]
Expand Down