koulanurag/ma-gym

A collection of multi agent environments based on OpenAI gym.

63
/ 100
Established

Implements domain-specific multi-agent scenarios (Checkers, PredatorPrey, TrafficJunction, Combat) with vectorized observation/reward handling across variable agent counts. Wraps standard Gym environments into multi-agent variants and integrates with minimal-marl for pre-trained agent initialization, targeting MARL research and algorithm benchmarking.

629 stars and 152 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 15 / 25
Maturity 25 / 25
Community 23 / 25

How are scores calculated?

Stars

629

Forks

114

Language

Python

License

Apache-2.0

Last pushed

Jul 07, 2024

Monthly downloads

152

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/koulanurag/ma-gym"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.