Games & virtual worlds · PROJECT NOTES
Gymnasium
A common interface and reference environments for single-agent reinforcement learning, continuing the maintenance lineage of OpenAI Gym.
What can you do with it?
Train and compare policies through consistent reset/step, observation, reward and termination interfaces, or build custom environments.
What should you know before using it?
The base package does not install every environment family. Current main requires Python 3.11+; extras, simulators and game assets have separate requirements. Pin environment version suffixes for comparisons. Framework code is MIT; external environments and ROMs may have different terms.
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