Optimization for Reinforcement Learning: From Single Agent to Cooperative Agents
It addresses the problem of scaling reinforcement learning to cooperative multi-agent systems for applications like control and networks, but is incremental as it is a review article summarizing existing work.
This article reviews recent advances in multi-agent reinforcement learning algorithms for large-scale control systems and communication networks, focusing on decentralized settings and coordination protocols, and aims to foster synergy among distributed optimization, signal processing, and reinforcement learning communities.
This article reviews recent advances in multi-agent reinforcement learning algorithms for large-scale control systems and communication networks, which learn to communicate and cooperate. We provide an overview of this emerging field, with an emphasis on the decentralized setting under different coordination protocols. We highlight the evolution of reinforcement learning algorithms from single-agent to multi-agent systems, from a distributed optimization perspective, and conclude with future directions and challenges, in the hope to catalyze the growing synergy among distributed optimization, signal processing, and reinforcement learning communities.