ma-gym

ma-gym provides a collection of multi-agent environments built upon the OpenAI Gym interface, facilitating research and development in multi-agent reinforcement learning. It includes various game-like and task-based environments, as well as wrappers to convert single-agent Gym environments into multi-agent forms for debugging.

ma-gym sits in the Multi-Agent category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Collection of diverse multi-agent environments (e.g., Checkers, Combat, PredatorPrey, TrafficJunction). A representative use case is Research and experimentation in multi-agent reinforcement learning algorithms. The listed license is Apache-2.0. GitHub stars are currently 636. Relevant tags include Reinforcement Learning, Multi-Agent Systems.