Multi-agent Reinforcement Learning for Networked System ControlDownload PDF

Published: 20 Dec 2019, Last Modified: 22 Oct 2023ICLR 2020 Conference Blind SubmissionReaders: Everyone
Keywords: deep reinforcement learning, multi-agent reinforcement learning, decision and control
TL;DR: This paper proposes a new formulation and a new communication protocol for networked multi-agent control problems
Abstract: This paper considers multi-agent reinforcement learning (MARL) in networked system control. Specifically, each agent learns a decentralized control policy based on local observations and messages from connected neighbors. We formulate such a networked MARL (NMARL) problem as a spatiotemporal Markov decision process and introduce a spatial discount factor to stabilize the training of each local agent. Further, we propose a new differentiable communication protocol, called NeurComm, to reduce information loss and non-stationarity in NMARL. Based on experiments in realistic NMARL scenarios of adaptive traffic signal control and cooperative adaptive cruise control, an appropriate spatial discount factor effectively enhances the learning curves of non-communicative MARL algorithms, while NeurComm outperforms existing communication protocols in both learning efficiency and control performance.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](
Original Pdf: pdf
9 Replies