On the approximation performance of fictitious play in finite games

We study the performance of Fictitious Play, when used as a heuristic for finding an approximate Nash equilibrium of a two-player game. We exhibit a class of two-player games having payoffs in the range [0, 1] that show that Fictitious Play fails to find a solution having an additive approximation guarantee significantly better than 1/2. Our construction shows that for n × n games, in the worst case both players may perpetually have mixed strategies whose payoffs fall short of the best response by an additive quantity 1/2-O(1/n1-δ) for arbitrarily small δ. We also show an essentially matching upper bound of 1/2 - O(1/n).

[1]  William Dudziak.  Using Fictitious Play to Find Pseudo-optimal Solutions for Full-scale Poker , 2006, IC-AI.

[2]  Xiaotie Deng,et al.  Settling the complexity of computing two-player Nash equilibria , 2007, JACM.

[3]  L. Shapley,et al.  REGULAR ARTICLEPotential Games , 1996 .

[4]  Felix A. Fischer,et al.  On the Rate of Convergence of Fictitious Play , 2010, Theory of Computing Systems.

[5]  ChenXi,et al.  Settling the complexity of computing two-player Nash equilibria , 2009 .

[6]  D. Fudenberg,et al.  Consistency and Cautious Fictitious Play , 1995 .

[7]  H PapadimitriouChristos,et al.  The complexity of computing a Nash equilibrium , 2009 .

[8]  V. Conitzer,et al.  Approximation guarantees for fictitious play , 2009, 2009 47th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[9]  Tuomas Sandholm,et al.  Computing an approximate jam/fold equilibrium for 3-player no-limit Texas Hold'em tournaments , 2008, AAMAS.

[10]  Troels Bjerre Lund,et al.  Approximate Well-Supported Nash Equilibria Below Two-Thirds , 2012, SAGT.

[11]  D. Fudenberg,et al.  The Theory of Learning in Games , 1998 .

[12]  S. Hart,et al.  Uncoupled Dynamics Do Not Lead to Nash Equilibrium , 2003 .

[13]  Evangelos Markakis,et al.  New algorithms for approximate Nash equilibria in bimatrix games , 2007, Theor. Comput. Sci..

[14]  Robert L. Smith,et al.  A Fictitious Play Approach to Large-Scale Optimization , 2005, Oper. Res..

[15]  David M. Kreps,et al.  Learning Mixed Equilibria , 1993 .

[16]  L. Shapley.  SOME TOPICS IN TWO-PERSON GAMES , 1963 .

[17]  Aranyak Mehta,et al.  Progress in approximate nash equilibria , 2007, EC '07.

[18]  Christos H. Papadimitriou,et al.  On Learning Algorithms for Nash Equilibria , 2010, SAGT.

[19]  Geoffrey J. Gordon,et al.  A Fast Bundle-based Anytime Algorithm for Poker and other Convex Games , 2007, AISTATS.

[20]  Kousha Etessami,et al.  Recursive Markov chains, stochastic grammars, and monotone systems of nonlinear equations , 2005, JACM.

[21]  Evangelos Markakis,et al.  New algorithms for approximate Nash equilibria in bimatrix games , 2010, Theor. Comput. Sci..

[22]  J. Robinson.  AN ITERATIVE METHOD OF SOLVING A GAME , 1951, Classics in Game Theory.

[23]  Ulrich Berger,et al.  Fictitious play in 2×n games , 2005, J. Econ. Theory.

[24]  Paul W. Goldberg,et al.  The complexity of computing a Nash equilibrium , 2006, STOC '06.

[25]  Amin Saberi,et al.  Approximating nash equilibria using small-support strategies , 2007, EC '07.

[26]  Paul G. Spirakis,et al.  An Optimization Approach for Approximate Nash Equilibria , 2007, WINE.

[27]  Paul G. Spirakis,et al.  Well Supported Approximate Equilibria in Bimatrix Games , 2010, Algorithmica.

[28]  S. Vajda.  Some topics in two-person games , 1971 .

[29]  Aranyak Mehta,et al.  A note on approximate Nash equilibria , 2006, Theor. Comput. Sci..