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
- Record the Cliff Walking gif from a learned policy
- Add optional fixed node and edge counts to Graph spaces
- Update gif for cliff walking to show a good policy
- [Proposal] Document sensitivity of InvertedDoublePendulum to tiny numerical differences in long-horizon trajectory comparisons
- Fix iterator inputs to concatenate for composite spaces
- [Bug Report] DiscretizeObservation collapses narrow Box ranges into the first bin
- Fix DiscretizeObservation for narrow observation ranges
- Use New Pixel Art for Frozen Lake
- Set an infinite bound's dtype limit after the cast, not into the caller's array
- Sync Reacher body xpos after step (#1690)
- Docs
- Python not yet supported