Population-aware Online Mirror Descent for Mean-Field Games by Deep Reinforcement Learning

arXiv:2403.03552v1 Announce Type: cross
Abstract: Mean Field Games (MFGs) have the ability to handle large-scale multi-agent systems, but learning Nash equilibria in MFGs remains a challenging task. In this paper, we propose a deep reinforcement learning (DRL) algorithm that achieves population-dependent Nash equilibrium without the need for averaging or sampling from history, inspired by Munchausen RL and Online Mirror Descent. Through the design of an additional inner-loop replay buffer, the agents can effectively learn to achieve Nash equilibrium from any …

abstract agent algorithm arxiv cs.gt cs.lg cs.ma cs.sy eess.sy equilibria equilibrium games mean multi-agent nash equilibrium paper population reinforcement reinforcement learning scale systems type