gymnasium
https://github.com/farama-foundation/gymnasium
Python
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported2 Subscribers
Add a CodeTriage badge to gymnasium
Help out
- Issues
- Sync Pusher body xpos after step
- Compare Humanoid COM velocity with a tolerance in test_verify_info_xy_velocity_com
- Record Autoreset's mode as a string in its spec kwargs
- Preserve uint8 dtype for grayscale noise in rendering wrappers
- Preserve frame durations when saving triggered video snippets
- Reset the environment before benchmarking render
- Support an inferred -1 dimension in ReshapeObservation
- Fix OneOf jsonable conversion for Dict, Tuple and stacked Sequence subspaces
- Use the spec's max_episode_steps for max_episode_steps=None in make_vec vector entry point mode
- Disable CartPoleVectorEnv's time limit for a non-positive max_episode_steps
- Docs
- Python not yet supported