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
- Allow HumanRendering to return displayed RGB frames on request
- Support shared memory for fixed-count Graph observations
- Add support for `rgb_array_list` in vector HumanRendering
- Stage Python 3.15 support for core installs
- Python 3.15 Support
- Fix Graph.contains raising for malformed composite batches
- Keep DiscretizeAction bin centers finite for large Box bounds
- Keep underscore-prefixed info keys in DictInfoToList
- Preserve frame history when observations reuse buffers
- [Bug Report] Vector info silently truncates numeric values depending on environment order
- Docs
- Python not yet supported