Learning with Forward Looking Players by

Experiments show difierent plays among identical players and change of reaction rules (how plays are adjusted after an observation) over time. These phenomena are not easily incorporated in adaptive learning models. We model a sophisticated learning model, where players hold \theories" which map information to beliefs using the knowledge of the game and rationality. For example, a player can think that the opponents will choose the same actions as last period, which is a Cournot type theory, but he/she could be one step forward looking and thinks that the opponents have such theory. Both theories use the same information rationally, and yet can give difierent best responses. As a consequence, when identical players hold diverse theories, they can play difierently. Players may also rationally revise theories based on their performance, which results in changes in reaction rules over time. We show various convergence results based on a model where players are allowed to hold diverse theories as explained above. When each player holds the same theory over time, we get (a) global convergence to the Nash equilibrium in dominance solvable games, (b) a large set of initial states leading to a pure Nash equilibrium in coordination games, and (c) non-Nash limit patterns in matching pennies. If players change theories in reaction to performance in su‐ciently diverse ways the dynamics exhibit enough entropy for global convergence to pure Nash equilibria in coordination games. JEL classiflcation number :C 73

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

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

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

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

[5]  A. Roth,et al.  Learning in Extensive-Form Games: Experimental Data and Simple Dynamic Models in the Intermediate Term* , 1995 .

[6]  R. Selten.  Features of experimentally observed bounded rationality , 1998 .

[7]  D. Stahl.  Boundedly rational rule learning in a guessing game , 1996 .

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

[9]  Dale O. Stahl,et al.  Evolution of Smartn Players , 1993 .

[10]  D. Stahl.  Evolution of Smart n Players , 1991 .

[11]  Jörg Oechssler,et al.  An Evolutionary Interpretation of Mixed-Strategy Equilibria , 1997 .

[12]  Masaki Aoyagi,et al.  Evolution of Beliefs and the Nash Equilibrium of Normal Form Games , 1996 .

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

[14]  Ramon Marimon,et al.  On adaptive learning in strategic games , 1993 .

[15]  J. Jordan,et al.  Bayesian learning in normal form games , 1991 .

[16]  Reinhard Selten,et al.  Anticipatory Learning in Two-Person Games , 1991 .

[17]  C. Sanchirico.  A Probabilistic Model of Learning in Games , 1996 .

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