Two more classes of games with the continuous-time fictitious play property

Fictitious Play is the oldest and most studied learning process for games. Since the already classical result for zero-sum games, convergence of beliefs to the set of Nash equilibria has been established for several classes of games, including weighted potential games, supermodular games with diminishing returns, and 3×3 supermodular games. Extending these results, we establish convergence of Continuous-time Fictitious Play for ordinal potential games and quasi-supermodular games with diminishing returns. As a by-product we obtain convergence for 3×m and 4×4 quasi-supermodular games.

[1]  Ulrich Berger.  Learning in games with strategic complementarities revisited , 2008, J. Econ. Theory.

[2]  Paul R. Milgrom,et al.  Monotone Comparative Statics , 1994 .

[3]  S. Hahn.  The convergence of fictitious play in 3×3 games with strategic complementarities , 1999 .

[4]  I. Gilboa,et al.  Social Stability and Equilibrium , 1991 .

[5]  D. Monderer,et al.  Fictitious play and- no-cycling conditions , 1997 .

[6]  Paul R. Milgrom,et al.  Adaptive and sophisticated learning in normal form games , 1991 .

[7]  Joachim RosenmÜller.  Über periodizitätseigenschaften spieltheoretischer lernprozesse , 1971 .

[8]  Sergiu Hart,et al.  Cooperation: Game-Theoretic Approaches , 2012, NATO ASI Series.

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

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

[11]  Josef Hofbauer,et al.  Stochastic Approximations and Differential Inclusions, Part II: Applications , 2006, Math. Oper. Res..

[12]  D. M. Topkis.  Equilibrium Points in Nonzero-Sum n-Person Submodular Games , 1979 .

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

[14]  X. Vives.  Nash equilibrium with strategic complementarities , 1990 .

[15]  Satoru Takahashi,et al.  The pure Nash equilibrium property and the quasi-acyclic condition , 2002 .

[16]  D. Monderer,et al.  A 2£ 2 Game without the Fictitious Play Property ⁄ , 1996 .

[17]  Ulrich Berger,et al.  Brown's original fictitious play , 2007, J. Econ. Theory.

[18]  Paul R. Milgrom,et al.  Rationalizability, Learning, and Equilibrium in Games with Strategic Complementarities , 1990 .

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

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

[21]  Josef Hofbauer,et al.  Stochastic Approximations and Differential Inclusions , 2005, SIAM J. Control. Optim..

[22]  Aner Sela,et al.  Fictitious Play in 2 × 3 Games , 2000, Games Econ. Behav..

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

[24]  J. Geanakoplos,et al.  Multimarket Oligopoly: Strategic Substitutes and Complements , 1985, Journal of Political Economy.

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

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

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

[28]  Akihiko Matsui,et al.  Best response dynamics and socially stable strategies , 1992 .

[29]  C. Harris.  On the Rate of Convergence of Continuous-Time Fictitious Play , 1998 .

[30]  A. W. Tucker,et al.  Advances in game theory , 1964 .

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

[32]  L. Shapley,et al.  Potential Games , 1994 .

[33]  J. Hofbauer,et al.  Fictitious Play, Shapley Polygons and the Replicator Equation , 1995 .

[34]  G. Brown.  SOME NOTES ON COMPUTATION OF GAMES SOLUTIONS , 1949 .

[35]  Vijay Krishna,et al.  Learning in Games: Fictitious Play Dynamics , 1997 .

[36]  Alfredo Garcia,et al.  Fictitious play for finding system optimal routings in dynamic traffic networks 1 This work was supp , 2000 .