Major-Minor Mean Field Multi-Agent Reinforcement Learning

arXiv:2303.10665v2 Announce Type: replace
Abstract: Multi-agent reinforcement learning (MARL) remains difficult to scale to many agents. Recent MARL using Mean Field Control (MFC) provides a tractable and rigorous approach to otherwise difficult cooperative MARL. However, the strict MFC assumption of many independent, weakly-interacting agents is too inflexible in practice. We generalize MFC to instead simultaneously model many similar and few complex agents -- as Major-Minor Mean Field Control (M3FC). Theoretically, we give approximation results for finite agent control, and verify …

abstract agent agents arxiv control cs.lg cs.ma however independent major math.oc mean multi-agent practice reinforcement reinforcement learning scale tractable type