Saved in:
Bibliographic Details
Main Authors: Yu, Jiajia, Cheng, Xiuyuan, Liu, Jian-Guo, Zhao, Hongkai
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.07989
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918089758605312
author Yu, Jiajia
Cheng, Xiuyuan
Liu, Jian-Guo
Zhao, Hongkai
author_facet Yu, Jiajia
Cheng, Xiuyuan
Liu, Jian-Guo
Zhao, Hongkai
contents A mean-field game (MFG) seeks the Nash Equilibrium of a game involving a continuum of players, where the Nash Equilibrium corresponds to a fixed point of the best-response mapping. However, simple fixed-point iterations do not always guarantee convergence. Fictitious play is an iterative algorithm that leverages a best-response mapping combined with a weighted average. Through a thorough study of the best-response mapping, this paper develops a simple and unified convergence analysis, providing the first explicit convergence rate for the fictitious play algorithm in MFGs of general types, especially non-potential MFGs. We demonstrate that the convergence and rate can be controlled through the weighting parameter in the algorithm, with linear convergence achievable under a general assumption. Building on this analysis, we propose two strategies to accelerate fictitious play. The first uses a backtracking line search to optimize the weighting parameter, while the second employs a hierarchical grid strategy to enhance stability and computational efficiency. We demonstrate the effectiveness of these acceleration techniques and validate our convergence rate analysis with various numerical examples.
format Preprint
id arxiv_https___arxiv_org_abs_2411_07989
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Convergence Analysis and Acceleration of Fictitious Play for General Mean-Field Games via the Best Response
Yu, Jiajia
Cheng, Xiuyuan
Liu, Jian-Guo
Zhao, Hongkai
Optimization and Control
A mean-field game (MFG) seeks the Nash Equilibrium of a game involving a continuum of players, where the Nash Equilibrium corresponds to a fixed point of the best-response mapping. However, simple fixed-point iterations do not always guarantee convergence. Fictitious play is an iterative algorithm that leverages a best-response mapping combined with a weighted average. Through a thorough study of the best-response mapping, this paper develops a simple and unified convergence analysis, providing the first explicit convergence rate for the fictitious play algorithm in MFGs of general types, especially non-potential MFGs. We demonstrate that the convergence and rate can be controlled through the weighting parameter in the algorithm, with linear convergence achievable under a general assumption. Building on this analysis, we propose two strategies to accelerate fictitious play. The first uses a backtracking line search to optimize the weighting parameter, while the second employs a hierarchical grid strategy to enhance stability and computational efficiency. We demonstrate the effectiveness of these acceleration techniques and validate our convergence rate analysis with various numerical examples.
title Convergence Analysis and Acceleration of Fictitious Play for General Mean-Field Games via the Best Response
topic Optimization and Control
url https://arxiv.org/abs/2411.07989