Mastering Asymmetrical Multiplayer Game with Multi-Agent Asymmetric-Evolution Reinforcement Learning

no code implementations • 20 Apr 2023 • Chenglu Sun, Yichi Zhang, Yu Zhang, Ziling Lu, Jingbin Liu, Sijia Xu, Weidong Zhang

We propose asymmetric-evolution training (AET), a novel multi-agent reinforcement learning framework that can train multiple kinds of agents simultaneously in AMP game.

Multi-agent Reinforcement Learning reinforcement-learning