Unified convergence proofs of continuous-time fictitious play

We consider a continuous-time version of fictitious play (FP), in which interacting players evolve their strategies in reaction to their opponents' actions without knowledge of their opponents' utilities. It is known that FP need not converge, but that convergence is possible in certain special cases including zero-sum games, identical interest games, and two-player/two-move games. We provide a unified proof of convergence in all of these cases by showing that a Lyapunov function previously introduced for zero-sum games also can establish stability in the other special cases. We go on to consider a two-player game in which only one player has two-moves and use properties of planar dynamical systems to establish convergence.

[1]  O. H. Brownlee,et al.  ACTIVITY ANALYSIS OF PRODUCTION AND ALLOCATION , 1952 .

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

[3]  C. Connell McCluskey,et al.  Stability Implications of Bendixson's Criterion , 1998, SIAM Rev..

[4]  Raymond A. DeCarlo,et al.  Switched Controller Synthesis for the Quadratic Stabilisation of a Pair of Unstable Linear Systems , 1998, Eur. J. Control.

[5]  Ziv Gorodeisky.  Stability of Mixed Equilibria , 2005 .

[6]  Shuzhi Sam Ge,et al.  Dynamic output feedback stabilization of a class of switched linear systems , 2003 .

[7]  M. Hirsch,et al.  Mixed Equilibria and Dynamical Systems Arising from Fictitious Play in Perturbed Games , 1999 .

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

[9]  Ulrich Berger.  Fictitious play in 2xn games , 2003 .

[10]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Two Volume Set , 1995 .

[11]  Vijay Krishna,et al.  On the Convergence of Fictitious Play , 1998, Math. Oper. Res..

[12]  J. Jordan.  Three Problems in Learning Mixed-Strategy Nash Equilibria , 1993 .

[13]  Drew Fudenberg,et al.  Learning Purified Mixed Equilibria , 2000, J. Econ. Theory.

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

[15]  Y. Pyatnitskiy,et al.  Criteria of asymptotic stability of differential and difference inclusions encountered in control theory , 1989 .

[16]  Harold J. Kushner,et al.  Stochastic Approximation Algorithms and Applications , 1997, Applications of Mathematics.

[17]  William H. Sandholm,et al.  ON THE GLOBAL CONVERGENCE OF STOCHASTIC FICTITIOUS PLAY , 2002 .

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

[19]  A. Morse,et al.  Basic problems in stability and design of switched systems , 1999 .

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

[21]  丸山 徹.  Convex Analysisの二,三の進展について , 1977 .

[22]  L. Shapley,et al.  Fictitious Play Property for Games with Identical Interests , 1996 .

[23]  M. Benaïm.  A Dynamical System Approach to Stochastic Approximations , 1996 .

[24]  Fernando Paganini,et al.  IEEE Transactions on Automatic Control , 2006 .

[25]  D. Stanford,et al.  Some Convergence Properties of Matrix Sets , 1994 .

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

[27]  K. Miyasawa.  ON THE CONVERGENCE OF THE LEARNING PROCESS IN A 2 X 2 NON-ZERO-SUM TWO-PERSON GAME , 1961 .

[28]  Dean P. Foster,et al.  On the Nonconvergence of Fictitious Play in Coordination Games , 1998 .

[29]  Alexander Vasin.  On stability of mixed equilibria , 1999 .