Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing

arXiv:2308.08705v2 Announce Type: replace
Abstract: We study provable multi-agent reinforcement learning (MARL) in the general framework of partially observable stochastic games (POSGs). To circumvent the known hardness results and the use of computationally intractable oracles, we advocate leveraging the potential \emph{information-sharing} among agents, a common practice in empirical MARL, and a standard model for multi-agent control systems with communications. We first establish several computation complexity results to justify the necessity of information-sharing, as well as the observability assumption that has …

abstract agent agents arxiv cs.gt cs.lg cs.ma efficiency framework games general information multi-agent observable practice reinforcement reinforcement learning results stochastic study type