Games & virtual worlds · PROJECT NOTES
MOMAland
A multi-objective multi-agent environment suite whose PettingZoo-style interfaces return reward vectors, including board games, cooperative physics tasks and resource-allocation simulations.
What can you do with it?
Compare multi-agent policies under competing objectives and utility choices, including multi-objective Connect4, Breakthrough and Pistonball, using versioned environments and supplied learning baselines.
What should you know before using it?
Reward vectors need an explicit utility, scalarization or multi-objective evaluation protocol; scores are not interchangeable with scalar-reward PettingZoo results. PyPI 0.2.0 metadata permits Python 3.9+, while the reviewed main source requires 3.11+. Optional learning extras add JAX and other dependencies. LICENSE and the package license field say GPLv3, but an MIT classifier conflicts with them.
What is verified here?
Creator: Farama Foundation and MOMAland contributors
Runtime: Python environment APIs and optional renderers; some environments adapt existing PettingZoo tasks and others come from multi-objective literature. Pin the library commit/package, versioned environment ID and objective configuration. Desktop OS support was not established by this review.
License note: Repository LICENSE is GNU GPLv3 and pyproject license text agrees; the same pyproject also includes a contradictory MIT classifier. Preserve that inconsistency rather than describing the suite as MIT. Dependencies retain their own licenses. Upstream license ↗
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 + benchmark
- Provenance
- Development provenance not established
- Reviewed
- Platforms
- Consult upstream documentation