Stochastic Game Theory: Adjustment to Equilibrium Under Noisy Directional Learning

This paper presents a dynamic model in which agents adjust their decisions in the direction of higher payoffs, subject to random error. This process produces a probability distribution of players' decisions whose evolution over time is determined by the Fokker-Planck equation. The dynamic process is stable for all potential games, a class of payoff structures that includes several widely studied games. In equilibrium, the distributions that determine expected payoffs correspond to the distributions that arise from the logit function applied to those expected payoffs. This "logit equilibrium" forms a stochastic generalization of the Nash equilibrium and provides a possible explanation of anomalous laboratory data.

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

[2]  D. Friedman,et al.  Evolving Landscapes for Population Games , 1997 .

[3]  J. Smoller.  Shock Waves and Reaction-Diffusion Equations , 1983 .

[4]  A. Roth,et al.  Predicting How People Play Games: Reinforcement Learning in Experimental Games with Unique, Mixed Strategy Equilibria , 1998 .

[5]  Jacob K. Goeree,et al.  Rent Seeking with Bounded Rationality: An Analysis of the All‐Pay Auction , 1998, Journal of Political Economy.

[6]  Kenneth J. Arrow,et al.  Stability of the Gradient Process in n-Person Games , 1960 .

[7]  Fernando Vega Redondo,et al.  The evolution of walrasian behavior , 1996 .

[8]  D. Fudenberg,et al.  Evolutionary Dynamics with Aggregate Shocks , 1992 .

[9]  H. Simon,et al.  Models of Man. , 1957 .

[10]  H. Peyton Young,et al.  Stochastic Evolutionary Game Dynamics , 1990 .

[11]  André de Palma,et al.  Discrete Choice Theory of Product Differentiation , 1995 .

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

[13]  J. Friedman,et al.  Boundedly Rational Nash Equilibrium: A Probabilistic Choice Approach☆☆☆ , 1997 .

[14]  R. Rosenthal.  A class of games possessing pure-strategy Nash equilibria , 1973 .

[15]  V. Smith,et al.  Monetary rewards and decision cost in experimental economics , 2000 .

[16]  Jacob K. Goeree,et al.  Minimum effort coordination games; an equilibrium analysis of bounded rationality , 1996 .

[17]  L. Samuelson,et al.  Evolutionary Drift and Equilibrium Selection , 2010 .

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

[19]  M. Shubik,et al.  A Behavioral Theory of the Firm. , 1964 .

[20]  P. Kline.  Models of man , 1986, Nature.

[21]  R. Rob,et al.  Learning, Mutation, and Long Run Equilibria in Games , 1993 .

[22]  R. Duncan Luce,et al.  Individual Choice Behavior , 1959 .

[23]  Alvin E. Roth,et al.  Modelling Predicting How People Play Games: Reinforcement learning in experimental games with unique , 1998 .

[24]  V. Smith.  Monetary Rewards and Decision Cost in Experimental Economics: An Extension , 1993 .

[25]  E. Johnsen.  Richard M. Cyert & James G. March, A Behavioral Theory of The Firm, Prentice-Hall, Inc., Englewood Cliffs, New Jersey, 1963, 332 s. , 1964 .

[26]  David M. Kreps,et al.  Evolutionary game theory in economics , 1997 .

[27]  H. Young,et al.  The Evolution of Conventions , 1993 .

[28]  J. Ochs.  Games with Unique, Mixed Strategy Equilibria: An Experimental Study , 1995 .

[29]  E. Renshaw,et al.  STOCHASTIC DIFFERENTIAL EQUATIONS , 1974 .

[30]  C. Leake.  Discrete Choice Theory of Product Differentiation , 1995 .

[31]  Charles A. Holt,et al.  Anomalous Behavior in a Traveler's Dilemma? , 1999 .

[32]  M. Slade.  What Does An Oligopoly Maximize , 1994 .

[33]  Ken Binmore,et al.  Muddling Through: Noisy Equilibrium Selection☆ , 1997 .

[34]  Robert W. Rosenthal,et al.  A bounded-rationality approach to the study of noncooperative games , 1989 .

[35]  R. McKelvey,et al.  Quantal Response Equilibria for Normal Form Games , 1995 .

[36]  P. Rhode,et al.  Non-Nash equilibria of Darwinian dynamics with applications to duopoly , 2001 .

[37]  David M. Kreps,et al.  Advances In Economics and Econometrics: Theory And Applications: Seventh World Congress , 1997 .

[38]  L. Samuelson,et al.  Musical Chairs: Modeling Noisy Evolution , 1995 .

[39]  R. Selten,et al.  Experimental Sealed Bid First Price Auctions with Directly Observed Bid Functions , 1994 .

[40]  Jacob K. Goeree,et al.  A theoretical analysis of altruism and decision error in public goods games , 1998 .

[41]  John B. Bryant,et al.  A Simple Rational Expectations Keynes-type Model , 1983 .