Rational Learning Leads to Nash Equilibrium

Two players are about to play a discounted infinitely repeated bimatrix game. Each player knows his own payoff matrix and chooses a strategy which is a best response to some private beliefs over strategies chosen by his opponent. If both players' beliefs contain a grain of truth (each assigns some positive probability to the strategy chosen by the opponent), then they will eventually (a) accurately predict the future play of the game and (b) play a Nash equilibrium of the repeated game. An immediate corollary is that in playing a Harsanyi-Nash equilibrium of a discounted repeated game of incomplete information about opponents' payoffs, the players will eventually play an equilibrium of the real game as if they had complete information.

[1]  Philip Wolfe,et al.  Contributions to the theory of games , 1960 .

[2]  J. Nash Equilibrium Points in N-Person Games. , 1950, Proceedings of the National Academy of Sciences of the United States of America.

[3]  J. Robinson An Iterative Method of Solving a Game , 1951 .

[4]  L. Shapley Stochastic Games* , 1953, Proceedings of the National Academy of Sciences.

[5]  宮沢 光一 On the convergence of the learning process in a 2 x 2 non-zero-sum two-person game , 1961 .

[6]  K. Arrow The Economic Implications of Learning by Doing , 1962 .

[7]  D. Blackwell,et al.  Merging of Opinions with Increasing Information , 1962 .

[8]  Robert J . Aumann 28. Mixed and Behavior Strategies in Infinite Extensive Games , 1964 .

[9]  J. Harsanyi Games with Incomplete Information Played by “Bayesian” Players Part II. Bayesian Equilibrium Points , 1968 .

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

[11]  M. Rothschild A two-armed bandit theory of market pricing , 1974 .

[12]  R. Selten Reexamination of the perfectness concept for equilibrium points in extensive games , 1975 .

[13]  David Easley,et al.  Introduction to the stability of rational expectations equilibrium , 1982 .

[14]  Jerry R. Green,et al.  Individual forecasting and aggregate outcomes: On mistaken beliefs and resultant equilibria , 1984 .

[15]  Rationalizable Strategic Behavior and the Problem of Perfection , 1984 .

[16]  Learning Rational Expectations: The Finite State Case , 1985 .

[17]  Sergiu Hart Nonzero-Sum Two-Person Repeated Games with Incomplete Information , 1985, Math. Oper. Res..

[18]  B. Douglas Bernheim,et al.  Axiomatic Characterizations of Rational Choice in Strategic Environme nts , 1986 .

[19]  David M. Kreps,et al.  Rational Learning and Rational Expectations , 1987 .

[20]  N. Kiefer,et al.  Controlling a Stochastic Process with Unknown Parameters , 1988 .

[21]  Vincent P. Crawford Learning and mixed-strategy equilibria in evolutionary games , 1989 .

[22]  David Canning Convergence to Equilibrium in a Sequence for Games with Learning , 1989 .

[23]  Andrew Schotter,et al.  Behavior And Efficiency In The Sealed-Bid Mechanism , 1990 .

[24]  M. Woodford Learning to Believe in Sunspots , 1990 .

[25]  Economic dynamics with learning : some instability examples , 1990 .

[26]  P. Milgrom,et al.  Adaptive and sophisticated learning in normal form games , 1991 .

[27]  S. Zamir,et al.  Bargaining and Market Behavior in Jerusalem, Ljubljana, Pittsburgh, and Tokyo: An Experimental Study , 1991 .

[28]  J. Jordan Bayesian learning in normal form games , 1991 .

[29]  Yaw Nyarko Learning In Mis-Specified Models And The Possibility Of Cycles , 1991 .

[30]  Prestable strategies in discounted duopoly games , 1991 .

[31]  Mark Blaug,et al.  Appraising Economic Theories , 1991 .

[32]  David Canning Average behavior in learning models , 1992 .

[33]  J. Jordan The exponential convergence of Bayesian learning in normal form games , 1992 .

[34]  Pierpaolo Battigalli,et al.  Learning and Convergence to Equilibrium in Repeated Strategic Interactions: An Introductory Survey , 1992 .

[35]  A. Roth,et al.  Considerations of Fairness and Strategy: Experimental Data from Sequential Games , 1992 .

[36]  E. Kalai,et al.  Subjective Equilibrium in Repeated Games , 1993 .

[37]  David Easley,et al.  Rational Expectations and Rational Learning , 1993 .

[38]  D. Fudenberg,et al.  Steady state learning and Nash equilibrium , 1993 .

[39]  D. Fudenberg,et al.  Self-confirming equilibrium , 1993 .

[40]  Ehud Kalai,et al.  Weak and Strong Merging of Opinions , 1994 .

[41]  Dov Monderer,et al.  Stochastic Common Learning , 1995 .