On the Rate of Convergence of Fictitious Play
Fictitious play is a simple learning algorithm for strategic games that proceeds in rounds. In each round, the players play a best response to a mixed strategy that is given by the empirical frequencies of actions played in previous rounds. There is a close relationship between fictitious play and the Nash equilibria of a game: if the empirical frequencies of fictitious play converge to a strategy profile, this strategy profile is a Nash equilibrium. While fictitious play does not converge in general, it is known to do so for certain restricted classes of games, such as constant-sum games, non-degenerate 2×n games, and potential games. We study the rate of convergence of fictitious play and show that, in all the classes of games mentioned above, fictitious play may require an exponential number of rounds (in the size of the representation of the game) before some equilibrium action is eventually played. In particular, we show the above statement for symmetric constant-sum win-lose-tie games.
KeywordsNash Equilibrium Learning Sequence Strategic Game Exponential Number Potential Game
Unable to display preview. Download preview PDF.
- 1.Bellman, R.: On a new iterative algorithm for finding the solutions of games and linear programming problems. In: Research Memorandum P-473, The RAND Corporation (1953)Google Scholar
- 5.Berger, U.: The convergence of fictitious play in games with strategic complementarities: A comment. MPRA Paper No. 20241, Munich Personal RePEc Archive (2009)Google Scholar
- 7.Brown, G.W.: Iterative solutions of games by fictitious play. In: Koopmans, T.C. (ed.) Activity Analysis of Production and Allocation, pp. 374–376. John Wiley and Sons, Inc., Chichester (1951)Google Scholar
- 8.Conitzer, V.: Approximation guarantees for fictitious play. In: Proc. of 47th Annual Allerton Conference on Communication, Control and Computing (2009)Google Scholar
- 10.Dantzig, G.B.: A proof of the equivalence of the programming problem and the game problem. In: Koopmans, T.C. (ed.) Activity Analysis of Production and Allocation, pp. 330–335. John Wiley & Sons Inc., Chichester (1951)Google Scholar
- 12.Ganzfried, S., Sandholm, T.: Computing an approximate jam/fold equilibrium for 3-player no-limit texas hold’em tournaments. In: Proc. of 7th AAMAS Conference, pp. 919–925 (2008)Google Scholar
- 15.Hannan, J.: Approximation to Bayes risk in repeated plays. In: Dresher, M., Tucker, A.W., Wolfe, P. (eds.) Contributions to the Theory of Games, vol. 3, pp. 97–139. Princeton University Press, Princeton (1957)Google Scholar
- 17.Miyasawa, K.: On the convergence of the learning process in a 2×2 nonzero sum two-person game. In: Research Memorandum 33, Econometric Research Program. Princeton University, Princeton (1961)Google Scholar
- 22.Powers, R., Shoham, Y.: New criteria and a new algorithm for learning in multi-agent systems. In: Advances in Neural Information Processing Systems, vol. 17, pp. 1089–1096. MIT Press, Cambridge (2004)Google Scholar
- 23.Rabinovich, Z., Gerding, E., Polukarov, M., Jennings, N.R.: Generalised fictitious play for a continuum of anonymous players. In: Proc. of 21st IJCAI, pp. 245–250 (2009)Google Scholar
- 25.Shapley, L.: Some topics in two-person games. In: Dresher, M., Shapley, L.S., Tucker, A.W. (eds.) Advances in Game Theory. Annals of Mathematics Studies, vol. 52, pp. 1–29. Princeton University Press, Princeton (1964)Google Scholar
- 28.Zhu, W., Wurman, P.R.: Structural leverage and fictitious play in sequential auctions. In: Proc. of 18th AAAI Conference, pp. 385–390 (2002)Google Scholar