Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems

Abstract

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 a O(ρ^(κ+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.