On the Exponential Rate of Convergence of Fictitious Play in Potential Games

07/25/2017
by   Brian Swenson, et al.
0

The paper studies fictitious play (FP) learning dynamics in continuous time. It is shown that in almost every potential game, and for almost every initial condition, the rate of convergence of FP is exponential. In particular, the paper focuses on studying the behavior of FP in potential games in which all equilibria of the game are regular, as introduced by Harsanyi. Such games are referred to as regular potential games. Recently it has been shown that almost all potential games (in the sense of the Lebesgue measure) are regular. In this paper it is shown that in any regular potential game (and hence, in almost every potential game), FP converges to the set of Nash equilibria at an exponential rate from almost every initial condition.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/19/2017

Fictitious Play in Potential Games

This work studies the convergence properties of continuous-time fictitio...
research
07/19/2017

On Best-Response Dynamics in Potential Games

The paper studies the convergence properties of (continuous) best-respon...
research
02/12/2022

Games of Artificial Intelligence: A Continuous-Time Approach

This paper studies the strategic interaction of algorithms in economic g...
research
12/20/2022

Anticipatory Fictitious Play

Fictitious play is an algorithm for computing Nash equilibria of matrix ...
research
03/17/2021

Decentralized Fictitious Play in Near-Potential Games with Time-Varying Communication Networks

We study the convergence properties of decentralized fictitious play (DF...
research
10/22/2020

Approximating the Minimal Lookahead Needed to Win Infinite Games

We present an exponential-time algorithm approximating the minimal looka...
research
08/17/2019

Generalized potential games

In this paper, we introduce a notion of generalized potential games that...

Please sign up or login with your details

Forgot password? Click here to reset