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 is currently grouped under Multi-Agent, which makes it easier to evaluate through workflow fit instead of isolated features alone. Based on the available data, it leans most heavily toward Collection of diverse multi-agent environments (e.g., Checkers, Combat, PredatorPrey, TrafficJunction) and Research and experimentation in multi-agent reinforcement learning algorithms. It also shows measurable community traction with 634 GitHub stars.