Scaling Up Learning Models in Public Good Games

We study three learning rules (reinforcement learning (RL), experience weighted attraction learning (EWA), and individual evolutionary learning (IEL)) and how they perform in three different Groves–Ledyard mechanisms. We are interested in how well these learning rules duplicate human behavior in repeated games with a continuum of strategies. We find that RL does not do well, IEL does significantly better, as does EWA, but only if given a small discretized strategy space. We identify four main features a learning rule should have in order to stack up against humans in a minimal competency test: (1) the use of hypotheticals to create history, (2) the ability to focus only on what is important, (3) the ability to forget history when it is no longer important, and (4) the ability to try new things.

[1]  L. L. Thurstone,et al.  The Learning Function , 1930 .

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

[3]  Patrick H. McAllister,et al.  Adaptive approaches to stochastic programming , 1991, Ann. Oper. Res..

[4]  F. Tang,et al.  Learning and incentive‐Compatible Mechanisms for Public Goods Provision: An Experimental Study , 1998, Journal of Political Economy.

[5]  Colin F. Camerer,et al.  Functional EWA: A One-parameter Theory of Learning in Games , 2002 .

[6]  T. Groves,et al.  Optimal Allocation of Public Goods: A Solution to the 'Free Rider Problem' , 1977 .

[7]  Colin Camerer.  Behavioral Game Theory: Experiments in Strategic Interaction , 2003 .

[8]  J. Ledyard.  Public Goods: A Survey of Experimental Research , 1994 .

[9]  Jasmina Arifovic,et al.  An initial implementation of the Turing tournament to learning in repeated two-person games , 2006, Games Econ. Behav..

[10]  Charles R. Plott,et al.  The Groves-Ledyard mechanism: An experimental study of institutional design , 1996 .

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

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

[13]  John O. Ledyard,et al.  Computer Testbeds and Mechanism Design: Application to the Class of Groves-Ledyard Mechanisms for Pr , 2001 .

[14]  S. Page,et al.  The Existence and Stability of Equilibria in the Groves Ledyard Mechanism , 2003 .

[15]  Frederick Mosteller,et al.  Stochastic Models for Learning , 1956 .