Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances
It provides a review of incremental progress in decentralized MARL for networked systems, relevant to researchers in control and machine learning.
This paper reviews recent advances in decentralized multi-agent reinforcement learning where agents operate without a central controller and communicate over networks, highlighting applications in robotics, unmanned vehicles, and smart grids.
Multi-agent reinforcement learning (MARL) has long been a significant and everlasting research topic in both machine learning and control. With the recent development of (single-agent) deep RL, there is a resurgence of interests in developing new MARL algorithms, especially those that are backed by theoretical analysis. In this paper, we review some recent advances a sub-area of this topic: decentralized MARL with networked agents. Specifically, multiple agents perform sequential decision-making in a common environment, without the coordination of any central controller. Instead, the agents are allowed to exchange information with their neighbors over a communication network. Such a setting finds broad applications in the control and operation of robots, unmanned vehicles, mobile sensor networks, and smart grid. This review is built upon several our research endeavors in this direction, together with some progresses made by other researchers along the line. We hope this review to inspire the devotion of more research efforts to this exciting yet challenging area.