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
- [Question] What actions are expected for a previously terminated sub-env in a vector (next `env.step()` should return reset obs so the actions shouldn't matter)?
- [Bug Report] "TypeError: 'float' object does not support indexing" in step method after 12M steps of training.
- [Proposal] Allow to specify dtype for Discrete
- [Question] Improving Tutorial Documention
- Q-learning implementation for Taxi-v3 environment
- Improve the documentation website rendering such that code blocks are wider on wider screens
- [Question] How to save a state and restore the env
- [Proposal] Full Stack Trace when exceptions thrown from vectorized environments
- [Proposal] Inclusion of ActionRepeat wrapper
- [Proposal & Design Goals] Add `MJX` based version of the existing `MuJoCo` environments
- Docs
- Python not yet supported