Mean-Field Multiagent Reinforcement Learning: A Decentralized Network Approach

Haotian Gu (), Xin Guo (), Xiaoli Wei () and Renyuan Xu ()
Additional contact information
Haotian Gu: Department of Mathematics, University of California, Berkeley, Berkeley, California 94720
Xin Guo: Department of Industrial Engineering & Operations Research, University of California, Berkeley, Berkeley, California 94720
Xiaoli Wei: Tsinghua Shenzhen International Graduate School, Shenzhen 518071, China
Renyuan Xu: Industrial & Systems Engineering, University of Southern California, Los Angeles, California 90089

Mathematics of Operations Research, 2025, vol. 50, issue 1, 506-536

Abstract: One of the challenges for multiagent reinforcement learning (MARL) is designing efficient learning algorithms for a large system in which each agent has only limited or partial information of the entire system. Whereas exciting progress has been made to analyze decentralized MARL with the network of agents for social networks and team video games, little is known theoretically for decentralized MARL with the network of states for modeling self-driving vehicles, ride-sharing, and data and traffic routing. This paper proposes a framework of localized training and decentralized execution to study MARL with the network of states. Localized training means that agents only need to collect local information in their neighboring states during the training phase; decentralized execution implies that agents can execute afterward the learned decentralized policies, which depend only on agents’ current states. The theoretical analysis consists of three key components: the first is the reformulation of the MARL system as a networked Markov decision process with teams of agents, enabling updating the associated team Q-function in a localized fashion; the second is the Bellman equation for the value function and the appropriate Q-function on the probability measure space; and the third is the exponential decay property of the team Q-function, facilitating its approximation with efficient sample efficiency and controllable error. The theoretical analysis paves the way for a new algorithm LTDE-N eural -AC, in which the actor–critic approach with overparameterized neural networks is proposed. The convergence and sample complexity are established and shown to be scalable with respect to the sizes of both agents and states. To the best of our knowledge, this is the first neural network–based MARL algorithm with network structure and provable convergence guarantee.

Keywords: Primary: 49N80; 93A16; 68T05; secondary: 90B15; 60K35; multiagent reinforcement learning; mean-field; neural network approximation (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/moor.2022.0055 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:ormoor:v:50:y:2025:i:1:p:506-536

Access Statistics for this article

More articles in Mathematics of Operations Research from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().