Multi-Agent Soft Actor-Critic with Global Loss for Autonomous Mobility-on-Demand Fleet Control

arXiv:2404.06975v1 Announce Type: cross
Abstract: We study a sequential decision-making problem for a profit-maximizing operator of an Autonomous Mobility-on-Demand system. Optimizing a central operator's vehicle-to-request dispatching policy requires efficient and effective fleet control strategies. To this end, we employ a multi-agent Soft Actor-Critic algorithm combined with weighted bipartite matching. We propose a novel vehicle-based algorithm architecture and adapt the critic's loss function to appropriately consider global actions. Furthermore, we extend our algorithm to incorporate rebalancing capabilities. Through numerical experiments, we …

abstract actor actor-critic agent algorithm arxiv autonomous control cs.lg cs.ma cs.sy decision demand eess.sy global loss making mobility multi-agent policy profit request strategies study type