Games & virtual worlds · PROJECT NOTES
Gymnax
A functional JAX environment library with implemented classic-control, diagnostic and small-game tasks, exposing explicit state, randomness and parameters.
What can you do with it?
Run batched JAX rollouts and vary environment parameters for controlled or meta-learning experiments.
What should you know before using it?
Many tasks reimplement Gym, bsuite or MinAtar and are not new benchmark families. PyPI 1.0.0 requires Python 3.10–3.13; the default env-dev branch contains older setup text. Pin code and task parameters and do not assume behavior matches upstream implementations. Code is Apache 2.0.
What is verified here?
This entry was reviewed against original project material. We have not independently run the software or reproduced its results. AI-development claims are author-reported; check upstream for current versions, setup requirements, and licenses.
- Resource type
- Environment framework
- Provenance
- Development provenance not established
- Reviewed
- Platforms
- Consult upstream documentation