Saved in:
Bibliographic Details
Main Authors: Wu, Zhouming, Mu, Yifen, Yang, Xiaoguang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.19216
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909443512336384
author Wu, Zhouming
Mu, Yifen
Yang, Xiaoguang
author_facet Wu, Zhouming
Mu, Yifen
Yang, Xiaoguang
contents As the earliest and one of the most fundamental learning dynamics for computing NE, fictitious play (FP) has being receiving incessant research attention and finding games where FP would converge (games with FPP) is one central question in related fields. In this paper, we identify a new class of games with FPP, i.e., $3\times3$ games without IIP, based on the geometrical approach by leveraging the location of NE and the partition of best response region. During the process, we devise a new projection mapping to reduce a high-dimensional dynamical system to a planar system. And to overcome the non-smoothness of the systems, we redefine the concepts of saddle and sink NE, which are proven to exist and help prove the convergence of CFP by separating the projected space into two parts. Furthermore, we show that our projection mapping can be extended to higher-dimensional and degenerate games.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19216
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the convergence of fictitious play algorithm in repeated games via the geometrical approach
Wu, Zhouming
Mu, Yifen
Yang, Xiaoguang
Optimization and Control
As the earliest and one of the most fundamental learning dynamics for computing NE, fictitious play (FP) has being receiving incessant research attention and finding games where FP would converge (games with FPP) is one central question in related fields. In this paper, we identify a new class of games with FPP, i.e., $3\times3$ games without IIP, based on the geometrical approach by leveraging the location of NE and the partition of best response region. During the process, we devise a new projection mapping to reduce a high-dimensional dynamical system to a planar system. And to overcome the non-smoothness of the systems, we redefine the concepts of saddle and sink NE, which are proven to exist and help prove the convergence of CFP by separating the projected space into two parts. Furthermore, we show that our projection mapping can be extended to higher-dimensional and degenerate games.
title On the convergence of fictitious play algorithm in repeated games via the geometrical approach
topic Optimization and Control
url https://arxiv.org/abs/2412.19216