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
- migrating the MuJoCo environments v2 and v3 to `Gymnasium-Robotics` (`mujoco-py` based)
- Re-enable `reportGeneralTypeIssues` typing rule
- [Proposal] Making gymnasium framework agnostic
- [Bug Report] pip install "gymnasium[all]" installs nvidia-cuda on system with no nvidia hardware
- Add `Discrete(dtype)` parameter
- Include initial state manager for BipedalWalker
- [RFC] `MJX` environment prototype (WIP)
- [Proposal] Can the dependency `box2d-py==2.3.8` be replaced with `Box2D==2.3.10`, which will simplify the installation?
- Add tutorial: qlearning with/without action masking for Taxi v3 env
- [Bug Report] Rendering two environments at the same time
- Docs
- Python not yet supported