MIR2: Towards Provably Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization

no code implementations • 15 Oct 2023 • Simin Li, Ruixiao Xu, Jun Guo, Pu Feng, Jiakai Wang, Aishan Liu, Yaodong Yang, Xianglong Liu, Weifeng Lv

Existing max-min optimization techniques in robust MARL seek to enhance resilience by training agents against worst-case adversaries, but this becomes intractable as the number of agents grows, leading to exponentially increasing worst-case scenarios.

Multi-agent Reinforcement Learning Starcraft +1