Games & virtual worlds · PROJECT NOTES
PettingZoo
A multi-agent environment library with turn-by-turn Agent Environment Cycle and parallel-action APIs, covering cooperative and competitive games.
What can you do with it?
Train agents that cooperate or compete using sequential or simultaneous action semantics appropriate to the game.
What should you know before using it?
Each environment family needs its own extras. Current main requires Python 3.11–3.14; Windows is not officially supported in the README. MAgent and MPE now live in separate MAgent2/MPE2 projects. Core code is MIT; emulator/game dependencies may carry additional 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
- Linux, macOS