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] Add fully tunable transition dynamics (including deterministic mode) to LunarLander
- Add wrapper checker utility for validating wrapper implementations
- Allow generic type hinting for Tuple space
- Allow custom rewards in FrozenLakeEnv
- [Question] On the Redundancy of Discrete Spaces: Could MultiDiscrete Supersede Discrete and MultiBinary?
- [Proposal] Make the Tuple space a generic class
- Add `params` argument to `FuncEnv.__init__` and update JAX wrappers
- [Question] Inverse Pendulum v5 init state all 0 but Pendulum falls down
- [Proposal] Add native support for chunked (N-step) rewards and statistics wrappers in Gymnasium
- [MuJoCo] Question about OpenGL rendering size
- Docs
- Python not yet supported