Farama-Foundation/MPE2

A suite of test scenarios for multi-agent reinforcement learning.

[ICLR-2025] POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically designed to be flexible, tunable and scalable. It can be tailored to a variety of PO-MAPF / MAPF settings.

An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environments

A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities

Multi-objective multi-agent API and environments

Multi-Agent Reinforcement Learning with JAX

Multi-objective Gymnasium environments for reinforcement learning

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

A General-Purpose Environment Framework for Scalable Multimodal Agent Evaluation and RL