Rule Learning in Symmetric Normal-Form Games: Theory and Evidence

We improve Stahl's (1996b) model of boundedly rational behavioral rules and rule learning for symmetric normal-form games with unique symmetric Nash equilibria. A player begins with initial propensities on a class of evidence-based behavioral rules, and given experience over time adjusts his/her propensities in proportion to the past performance of the rules. An experiment consisting of two 15 period runs with 5x5 games was designed to test this model. The experimental data provide significant support for rule learning and heterogeneity among individuals. We also strongly reject "Nash learning" and "Cournot dynamics" in favor of rule learning.

[1]  Dearborn.  Animal Intelligence: An Experimental Study of the Associative Processes in Animals , 1900 .

[2]  D. McFadden.  Conditional logit analysis of qualitative choice behavior , 1972 .

[3]  P. Zarembka.  Frontiers in econometrics , 1973 .

[4]  B. Bernheim.  Rationalizable Strategic Behavior , 1984 .

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

[6]  Ken Binmore,et al.  Modeling rational players I , 1987 .

[7]  Josef Hofbauer,et al.  The theory of evolution and dynamical systems , 1988 .

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

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

[10]  D. Schmeidler,et al.  A More Robust Definition of Subjective Probability , 1992 .

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

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

[13]  R. Battalio,et al.  Selection Dynamics, Asymptotic Stability, and Adaptive Behavior , 1994, Journal of Political Economy.

[14]  D. Stahl,et al.  Experimental evidence on players' models of other players , 1994 .

[15]  Dilip Mookherjee,et al.  Learning behavior in an experimental matching pennies game , 1994 .

[16]  Ying-Wong Cheung,et al.  Individual Learning in Games: Some Laboratory Results , 1995 .

[17]  D. Stahl,et al.  On Players' Models of Other Players: Theory and Experimental Evidence , 1995 .

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

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

[20]  V. Crawford.  Adaptive dynamics in coordination games , 1995 .

[21]  Michael M. Cohen,et al.  A comparison of learning models , 1995 .

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

[23]  A. Rapoport,et al.  Organizational Behavior and Human Decision Processes Randomization and Adaptive Learning in a Simplified Poker Game , 2022 .

[24]  Daniel Friedman,et al.  Individual Learning in Normal Form Games: Some Laboratory Results☆☆☆ , 1997 .

[25]  Dilip Mookherjee,et al.  Learning and Decision Costs in Experimental Constant Sum Games , 1997 .

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

[27]  R. McKelvey,et al.  Quantal Response Equilibria for Extensive Form Games , 1998 .

[28]  I. Erev,et al.  Games and Human Behavior , 1999 .

[29]  Maxwell B. Stinchcombe,et al.  Neural network approximation of continuous functionals and continuous functions on compactifications , 1999, Neural Networks.

[30]  Colin Camerer,et al.  Experience‐weighted Attraction Learning in Normal Form Games , 1999 .

[31]  Dale O. Stahl,et al.  Evidence based rules and learning in symmetric normal-form games , 1999, Int. J. Game Theory.