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

Ensure correct seeding behaviour. Using the self.np_random rather tha… #468

Closed
wants to merge 1 commit into from
Closed

Ensure correct seeding behaviour. Using the self.np_random rather tha… #468

wants to merge 1 commit into from

Conversation

BruceGeLi
Copy link

This is a PR to solve issue #461
Ensure correct seeding behaviour. Using the self.np_random rather than the np.random. This makes sure:

  1. Deterministic env resetting.
  2. Different seeds for envs running in parallel, e.g. Async Vector Env of gymnasium.
  3. Make the seed in the reset function useful, following the gymnasium interface.

@BruceGeLi
Ensure correct seeding behaviour. Using the self.np_random rather tha…
5c80e3d 
…n the np.random. This makes sure:

1. Deterministic env resetting.
2. Different seeds for envs running in parallel, e.g. Vector Env of gymnasium.
@reginald-mclean
Copy link
Collaborator

This isn't exactly the correct way to seed environments in MW. super().reset(seed=seed) doesn't produce the behaviour that you would expect in all cases. There is a fix for #468 coming, we are just waiting for Gymnasium 1.0.0 to be fully released before making that change.

@BruceGeLi
Copy link
Author

Thanks for your reply.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@BruceGeLi @reginald-mclean