on-policy

This repository implements MAPPO, a multi-agent variant of PPO, widely used in cooperative multi-agent games and research. It provides robust implementations for various multi-agent environments like StarCraft II, Hanabi, and Google Research Football, along with detailed training scripts and hyperparameter guidance.

on-policy is currently grouped under LLM Infra, which makes it easier to evaluate through workflow fit instead of isolated features alone. Based on the available data, it leans most heavily toward Implementation of MAPPO (Multi-Agent PPO) and Research and experimentation in cooperative multi-agent reinforcement learning. The listed license is MIT, which is useful when adoption constraints matter. It also shows measurable community traction with 2.1k GitHub stars.