Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Fuzhong, Zhang, Chenyu, Chen, Xu, Di, Xuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917686025388032
author Zhou, Fuzhong
Zhang, Chenyu
Chen, Xu
Di, Xuan
author_facet Zhou, Fuzhong
Zhang, Chenyu
Chen, Xu
Di, Xuan
contents We propose a discrete time graphon game formulation on continuous state and action spaces using a representative player to study stochastic games with heterogeneous interaction among agents. This formulation admits both philosophical and mathematical advantages, compared to a widely adopted formulation using a continuum of players. We prove the existence and uniqueness of the graphon equilibrium with mild assumptions, and show that this equilibrium can be used to construct an approximate solution for finite player game on networks, which is challenging to analyze and solve due to curse of dimensionality. An online oracle-free learning algorithm is developed to solve the equilibrium numerically, and sample complexity analysis is provided for its convergence.
format Preprint
id arxiv_https___arxiv_org_abs_2405_08005
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm
Zhou, Fuzhong
Zhang, Chenyu
Chen, Xu
Di, Xuan
Optimization and Control
Artificial Intelligence
Computer Science and Game Theory
Machine Learning
We propose a discrete time graphon game formulation on continuous state and action spaces using a representative player to study stochastic games with heterogeneous interaction among agents. This formulation admits both philosophical and mathematical advantages, compared to a widely adopted formulation using a continuum of players. We prove the existence and uniqueness of the graphon equilibrium with mild assumptions, and show that this equilibrium can be used to construct an approximate solution for finite player game on networks, which is challenging to analyze and solve due to curse of dimensionality. An online oracle-free learning algorithm is developed to solve the equilibrium numerically, and sample complexity analysis is provided for its convergence.
title Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm
topic Optimization and Control
Artificial Intelligence
Computer Science and Game Theory
Machine Learning
url https://arxiv.org/abs/2405.08005