Learning in games with strategic complementarities revisited

Fictitious play is a classical learning process for games, and games with strategic complementarities are an important class including many economic applications. Knowledge about convergence properties of fictitious play in this class of games is scarce, however. Beyond games with a unique equilibrium, global convergence has only been claimed for games with diminishing returns [V. Krishna, Learning in games with strategic complementarities, HBS Working Paper 92-073, Harvard University, 1992]. This result remained unpublished, and it relies on a specific tie-breaking rule. Here we prove an extension of it by showing that the ordinal version of strategic complementarities suffices. The proof does not rely on tie-breaking rules and provides some intuition for the result.

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

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

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

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

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

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

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

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

[9]  R. Cressman.  Evolutionary Dynamics and Extensive Form Games , 2003 .

[10]  Ulrich Berger,et al.  Two more classes of games with the continuous-time fictitious play property , 2007, Games Econ. Behav..

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

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

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

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

[15]  H. Peyton Young,et al.  Strategic Learning and Its Limits , 2004 .

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

[17]  D. Monderer,et al.  Belief Affirming in Learning Processes , 1997 .

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

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

[20]  David S. Leslie,et al.  Generalised weakened fictitious play , 2006, Games Econ. Behav..

[21]  X. Vives.  Complementarities and Games: New Developments , 2004 .

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

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

[24]  Ulrich Berger.  Some Notes on Learning in Games with Strategic Complementarities , 2004 .

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

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

[27]  Dov Monderer,et al.  A Learning Approach to Auctions , 1998 .

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

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

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