Efficient Reinforcement Learning for Global Decision Making in the Presence of Local Agents at Scale

arXiv:2403.00222v1 Announce Type: new
Abstract: We study reinforcement learning for global decision-making in the presence of many local agents, where the global decision-maker makes decisions affecting all local agents, and the objective is to learn a policy that maximizes the rewards of both the global and the local agents. Such problems find many applications, e.g. demand response, EV charging, queueing, etc. In this setting, scalability has been a long-standing challenge due to the size of the state/action space which can …

abstract agents arxiv cs.lg cs.ma decision decision making decisions global learn maker making policy reinforcement reinforcement learning scale study type