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
- [Proposal] Remove `mujoco-py` based environments at May 2025
- Rework rendering API to allow for simultaneous "human" and "rgb_array" mode rendering
- [New feature] Add reset options support for functional jax envs
- [Proposal] Initial State Tracking - Bipedal Walker Hardcore
- [Bug Report] Inconsistent definition of reward
- [Proposal] Add wrapper checker
- [Proposal] Expanding Graph Spaces to allow Node and Edge Spaces to include other Space Types including Dict
- [Bug Report] default_camera_config in MujocoEnv seems not working
- [Bug Report] render window freezes when `render_mode="human"` (LunarLander) (MacOS)
- [Question] [`FuncEnv`] `params` are not used by `__init__` & `render_init` & `render_close`
- Docs
- Python not yet supported