A Probabilistic Model of Learning in Games

This paper presents a new, probabilistic model of learning in games which investigates the often stated intuition that common knowledge of strategic intent may arise from repeated interaction. The model is set in the usual repeated game framework, but the two key assumptions are framed in terms of the likelihood of beliefs and actions conditional on the history of play. The first assumption formalizes the basic intuition of the learning approach; the second, the indeterminacy that inspired resort to learning models in the first place. Together the assumptions imply that, almost surely, play will remain almost always within one of the stage game's "minimal inclusive sets." In important classes of games, including those with strategic complementarities, potential functions, and bandwagon effects, all such sets are singleton Nash.

[1]  Faruk Gul,et al.  Rationality and Coherent Theories of Strategic Behavior , 1996 .

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

[3]  C. Sanchirico.  A Probabilistic Model of Learning in Games Author ( s ) : , 1996 .

[4]  Doron Sonsino.  Learning to learn, pattern recognition, and Nash equilibrium , 1995 .

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

[6]  S. Hart,et al.  A simple adaptive procedure leading to correlated equilibrium , 2000 .

[7]  J. Weibull,et al.  Strategy subsets closed under rational behavior , 1991 .

[8]  Sanjeev Goyal,et al.  Self-Organization in Communication Networks , 1997 .

[9]  K. Knopp.  Theory and Application of Infinite Series , 1990 .

[10]  J. Weibull.  Evolution, rationality and equilibrium in games , 1998 .

[11]  Sjaak Hurkens.  Learning by Forgetful Players: From Primitive Formations to Persistent Retracts , 1994 .

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

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

[14]  Minimal Inclusive Sets in Special Classes of Games , 1994 .

[15]  R. Rob,et al.  Bandwagon Effects and Long Run Technology Choice , 2010 .

[16]  T. Tan,et al.  The Bayesian foundations of solution concepts of games , 1988 .

[17]  Chris William Sanchirico,et al.  Minimal Inclusive Sets in Special Classes of Games , 1994 .

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

[19]  J. Weibull.  What have we learned from Evolutionary Game Theory so far , 1998 .

[20]  David Pearce.  Rationalizable Strategic Behavior and the Problem of Perfection , 1984 .

[21]  R. Ash,et al.  Real analysis and probability , 1975 .

[22]  E. Kalai,et al.  Rational Learning Leads to Nash Equilibrium , 1993 .