Intelligent Players in a Fictitious Play Framework
Bhaskar Vundurthy, Aris Kanellopoulos, Vijay Gupta, Kyriakos G. Vamvoudakis · IEEE Transactions on Automatic Control · 2023
Fictitious play is a popular learning algorithm in which players that utilize the history of actions played by the players and the knowledge of their own payoff matrix can converge to the Nash equilibrium under certain conditions on the game. We consider the presence of anintelligentplayer that has access to the entire payoff matrix for the game. We show that by not conforming to fictitious play, such a player can achieve a better payoff than the one at the Nash Equilibrium. This result can be viewed both as a fragility of the fictitious play algorithm to a strategic intelligent player and an indication that players should not throw away additional information they may have, as suggested by classical fictitious play.