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
- Save MuJoCo viewer frame captures to the temporary directory
- Rebind cached MuJoCo viewers before rendering
- Preserve the stored Dict key order when batching vector spaces
- Return frames from this step when MaxAndSkipObservation ends mid-skip
- Preserve strings in ArrayConversion
- Docs: document numerical sensitivity of long-horizon MuJoCo trajectory comparisons
- Keep AsyncVectorEnv workers running after a failed call or set_attr
- fix: preserve generator batches in composite space serialization
- Normalize validated probability masks in Discrete and Text sampling
- Check Box bounds against the dtype range only when they can exceed it
- Docs
- Python not yet supported