A Caltech Library Service

Scalable Reinforcement Learning for Multiagent Networked Systems

Qu, Guannan and Wierman, Adam and Li, Na (2022) Scalable Reinforcement Learning for Multiagent Networked Systems. Operations Research . ISSN 0030-364X. doi:10.1287/opre.2021.2226. (In Press)

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


We study reinforcement learning (RL) in a setting with a network of agents whose states and actions interact in a local manner where the objective is to find localized policies such that the (discounted) global reward is maximized. A fundamental challenge in this setting is that the state-action space size scales exponentially in the number of agents, rendering the problem intractable for large networks. In this paper, we propose a scalable actor critic (SAC) framework that exploits the network structure and finds a localized policy that is an O(ρκ+1)-approximation of a stationary point of the objective for some ρ∈(0,1), with complexity that scales with the local state-action space size of the largest κ-hop neighborhood of the network. We illustrate our model and approach using examples from wireless communication, epidemics, and traffic.

Item Type:Article
Related URLs:
URLURL TypeDescription ItemDiscussion Paper
Qu, Guannan0000-0002-5466-3550
Wierman, Adam0000-0002-5923-0199
Li, Na0000-0001-9545-3050
Alternate Title:Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems
Record Number:CaltechAUTHORS:20220914-591652300
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:116912
Deposited By: Tony Diaz
Deposited On:22 Sep 2022 19:44
Last Modified:22 Sep 2022 19:44

Repository Staff Only: item control page