Exploiting inter-agent coupling information for efficient reinforcement learning of cooperative LQR

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Syed, Shahbaz P Qadri, Bai, He
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918004563902464
author Syed, Shahbaz P Qadri
Bai, He
author_facet Syed, Shahbaz P Qadri
Bai, He
contents Developing scalable and efficient reinforcement learning algorithms for cooperative multi-agent control has received significant attention over the past years. Existing literature has proposed inexact decompositions of local Q-functions based on empirical information structures between the agents. In this paper, we exploit inter-agent coupling information and propose a systematic approach to exactly decompose the local Q-function of each agent. We develop an approximate least square policy iteration algorithm based on the proposed decomposition and identify two architectures to learn the local Q-function for each agent. We establish that the worst-case sample complexity of the decomposition is equal to the centralized case and derive necessary and sufficient graphical conditions on the inter-agent couplings to achieve better sample efficiency. We demonstrate the improved sample efficiency and computational efficiency on numerical examples.
format Preprint
id arxiv_https___arxiv_org_abs_2504_20927
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploiting inter-agent coupling information for efficient reinforcement learning of cooperative LQR
Syed, Shahbaz P Qadri
Bai, He
Systems and Control
Machine Learning
Multiagent Systems
Optimization and Control
Developing scalable and efficient reinforcement learning algorithms for cooperative multi-agent control has received significant attention over the past years. Existing literature has proposed inexact decompositions of local Q-functions based on empirical information structures between the agents. In this paper, we exploit inter-agent coupling information and propose a systematic approach to exactly decompose the local Q-function of each agent. We develop an approximate least square policy iteration algorithm based on the proposed decomposition and identify two architectures to learn the local Q-function for each agent. We establish that the worst-case sample complexity of the decomposition is equal to the centralized case and derive necessary and sufficient graphical conditions on the inter-agent couplings to achieve better sample efficiency. We demonstrate the improved sample efficiency and computational efficiency on numerical examples.
title Exploiting inter-agent coupling information for efficient reinforcement learning of cooperative LQR
topic Systems and Control
Machine Learning
Multiagent Systems
Optimization and Control
url https://arxiv.org/abs/2504.20927