Random Initialization Solves Shapley's Fictitious Play Counterexample

09/05/2022
by   Sam Ganzfried, et al.
0

In 1964 Shapley devised a family of games for which fictitious play fails to converge to Nash equilibrium. The games are two-player non-zero-sum with 3 pure strategies per player. Shapley assumed that each player played a specific pure strategy in the first round. We show that if we use random (mixed) strategy profile initializations we are able to converge to Nash equilibrium approximately 1/3 of the time for a representative game in this class.

READ FULL TEXT
research
10/31/2020

When "Better" is better than "Best"

We consider two-player normal form games where each player has the same ...
research
10/26/2019

Finding Mixed Strategy Nash Equilibrium for Continuous Games through Deep Learning

Nash equilibrium has long been a desired solution concept in multi-playe...
research
09/19/2023

Game Connectivity and Adaptive Dynamics

We analyse the typical structure of games in terms of the connectivity p...
research
03/21/2022

Fictitious Play with Maximin Initialization

Fictitious play has recently emerged as the most accurate scalable algor...
research
08/04/2022

Continuous guts poker and numerical optimization of generalized recursive games

We study a type of generalized recursive game introduced by Castronova, ...
research
07/01/2003

AWESOME: A General Multiagent Learning Algorithm that Converges in Self-Play and Learns a Best Response Against Stationary Opponents

A satisfactory multiagent learning algorithm should, at a minimum, lear...
research
03/05/2018

Playing Stackelberg Opinion Optimization with Randomized Algorithms for Combinatorial Strategies

From a perspective of designing or engineering for opinion formation gam...

Please sign up or login with your details

Forgot password? Click here to reset