Multi-Agent Bandit Learning through Heterogeneous Action Erasure Channels

arXiv:2312.14259v2 Announce Type: replace
Abstract: Multi-Armed Bandit (MAB) systems are witnessing an upswing in applications within multi-agent distributed environments, leading to the advancement of collaborative MAB algorithms. In such settings, communication between agents executing actions and the primary learner making decisions can hinder the learning process. A prevalent challenge in distributed learning is action erasure, often induced by communication delays and/or channel noise. This results in agents possibly not receiving the intended action from the learner, subsequently leading to misguided …

abstract advancement agent agents algorithms applications arxiv challenge channels collaborative communication cs.dc cs.lg cs.ma decisions distributed distributed learning environments hinder making multi-agent process systems through type