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

Why converting observation space to np.float32? #438

Open
jamartinh opened this issue Dec 8, 2023 · 2 comments
Open

Why converting observation space to np.float32? #438

jamartinh opened this issue Dec 8, 2023 · 2 comments

Comments

@jamartinh
Copy link

Why converting observation space to np.float?

cleanrl/cleanrl/sac_continuous_action.py

Line 205 in 329b128

envs.single_observation_space.dtype = np.float32

This breaks compatibility with Gymnasium.
@pseudo-rnd-thoughts
Copy link
Collaborator

It shouldn't affect performance and reduces the memory overhead of the replay buffer

@jamartinh
Copy link
Author

Ok, just to verify why I was getting warns with Gymnasium 1.0.0rc and assertion error in Minari.

@jamartinh jamartinh changed the title Why converting observation space to np.float? Why converting observation space to np.float32? Dec 8, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@jamartinh @pseudo-rnd-thoughts