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
- Fix vector info dtype when sub-environments mix int and float
- Grow the offscreen framebuffer to fit the requested viewport in `OffScreenViewer`
- Support integer bounds up to the dtype limits in Box.sample
- Return False from Sequence.contains for non-batch inputs
- Advance composite Graph feature generators between samples
- [Bug Report] Sequence(stack=True).contains raises for non-batch inputs instead of returning False
- Preserve mutable controls in StickyAction repeats
- [Bug Report] `OneOf.to_jsonable` / `from_jsonable` fail for `Dict` and `Tuple` subspaces
- MultiDiscrete masked sampling loses large uint64 start offsets
- Preserve exact uint64 starts in MultiDiscrete masked sampling
- Docs
- Python not yet supported