Distributed Multi-Agent Reinforcement Learning Based on Graph-Induced Local Value Functions

arXiv:2202.13046v4 Announce Type: replace
Abstract: Achieving distributed reinforcement learning (RL) for large-scale cooperative multi-agent systems (MASs) is challenging because: (i) each agent has access to only limited information; (ii) issues on convergence or computational complexity emerge due to the curse of dimensionality. In this paper, we propose a general computationally efficient distributed framework for cooperative multi-agent reinforcement learning (MARL) by utilizing the structures of graphs involved in this problem. We introduce three coupling graphs describing three types of inter-agent couplings …

abstract agent arxiv complexity computational convergence cs.ai cs.lg cs.ma dimensionality distributed functions general graph information multi-agent paper reinforcement reinforcement learning scale systems the curse of dimensionality type value