Reducing Redundant Computation in Multi-Agent Coordination through Locally Centralized Execution

arXiv:2404.13096v1 Announce Type: cross
Abstract: In multi-agent reinforcement learning, decentralized execution is a common approach, yet it suffers from the redundant computation problem. This occurs when multiple agents redundantly perform the same or similar computation due to overlapping observations. To address this issue, this study introduces a novel method referred to as locally centralized team transformer (LCTT). LCTT establishes a locally centralized execution framework where selected agents serve as leaders, issuing instructions, while the rest agents, designated as workers, act …

abstract agent agents arxiv computation cs.ai cs.lg cs.ma decentralized issue multi-agent multiple novel reinforcement reinforcement learning study through type