Graphon mean-field control for cooperative multi-agent reinforcement learning

DOI10.1016/J.JFRANKLIN.2023.09.002zbMATH Open1530.93012arXiv2209.04808OpenAlexW4386511453MaRDI QIDQ6136535FDOQ6136535

Xiaoli Wei, Yuanquan Hu, Junji Yan, Hengxi Zhang

Publication date: 17 January 2024

Published in: Journal of the Franklin Institute (Search for Journal in Brave)

Abstract: The marriage between mean-field theory and reinforcement learning has shown a great capacity to solve large-scale control problems with homogeneous agents. To break the homogeneity restriction of mean-field theory, a recent interest is to introduce graphon theory to the mean-field paradigm. In this paper, we propose a graphon mean-field control (GMFC) framework to approximate cooperative multi-agent reinforcement learning (MARL) with nonuniform interactions and show that the approximate order is of $mathcalO(frac1sqrtN)$, with $N$ the number of agents. By discretizing the graphon index of GMFC, we further introduce a smaller class of GMFC called block GMFC, which is shown to well approximate cooperative MARL. Our empirical studies on several examples demonstrate that our GMFC approach is comparable with the state-of-art MARL algorithms while enjoying better scalability.

Full work available at URL: https://arxiv.org/abs/2209.04808

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Applications of graph theory (05C90) Multi-agent systems (93A16)

Cites Work

• Title not available (Why is that?)
• High-Dimensional Statistics
• Mean field games
• Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
• Probabilistic analysis of mean-field games
• Distributed learning and cooperative control for multi-agent systems
• Mean field games: A toy model on an Erdös-Renyi graph.
• Stochastic Graphon Games: I. The Static Case
• Mean field game of controls and an application to trade crowding
• Graphon Control of Large-Scale Networks of Linear Systems
• Finite mean field games: fictitious play and convergence to a first order continuous mean field game
• Mean-Field Controls with Q-Learning for Cooperative MARL: Convergence and Complexity Analysis
• Convergence of Weighted Empirical Measures

Cited In (1)

• Breaking consensus in kinetic opinion formation models on graphons

This page was built for publication: Graphon mean-field control for cooperative multi-agent reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6136535)