Shopkeeper strategies in the iterated prisoner's dilemma

Many studies have evolved agents to play the iterated prisoner's dilemma. This study models a different situation, called the Shopkeeper model of interaction, in which a state conditioned agent interacts with a series of other agents without resetting its internal state. This is intended to simulate the situation in which a shopkeeper interacts with a series of customers. In a majority of other studies agents either reset their internal state information before each new encounter or have relatively little internal state information. This means they cannot model situations such as being the customer that meets the shopkeeper after an obnoxious customer. We train shopkeeper prisoner's dilemma agents against a variety of distributions of possible customers. The shopkeepers specialize their behavior to their customers but sometimes fail to discover maximally exploitative behaviors. The evolved shopkeeper agents are subject to fingerprint analysis and are shown to differ substantially from agents evolved with a round-robin fitness functions. Evaluation of the behavior of the shopkeeper agents with customers they did not encounter during evolution provides additional evidence that shopkeepers specialized to the customers, but did so incompletely for the more complex sets of customers.

[1]  Louis Legendre,et al.  The Importance of Being Digital , 1963 .

[2]  C. Terry,et al.  Competitiveness and Conflict Behavior in Simulation of a Social Dilemma , 2000, Psychological reports.

[3]  Daniel A. Ashlock,et al.  An Exploration of Differential Utility in Iterated Prisoner's Dilemma , 2006, 2006 IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology.

[4]  Xin Yao,et al.  Behavioral diversity, choices and noise in the iterated prisoner's dilemma , 2005, IEEE Transactions on Evolutionary Computation.

[5]  Julian Francis Miller,et al.  Redundancy and computational efficiency in Cartesian genetic programming , 2006, IEEE Transactions on Evolutionary Computation.

[6]  Daniel A. Ashlock,et al.  The impact of cellular representation on finite state agents for prisoner's dilemma , 2005, GECCO '05.

[7]  Heinz Mühlenbein,et al.  Darwin's Continent Cycle Theory and Its Simulation by the Prisoner's Dilemma , 1991, Complex Syst..

[8]  Daniel A. Ashlock,et al.  Changes in Prisoner’s Dilemma Strategies Over Evolutionary Time With Different Population Sizes , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[9]  Daniel A. Ashlock,et al.  Fingerprint analysis of the noisy prisoner’s dilemma , 2009, 2007 IEEE Congress on Evolutionary Computation.

[10]  P. Groenen,et al.  Modern Multidimensional Scaling: Theory and Applications , 1999 .

[11]  Wendy Ashlock,et al.  Why Some Representations Are More Cooperative Than Others For Prisoner's Dilemma , 2007, 2007 IEEE Symposium on Foundations of Computational Intelligence.

[12]  Daniel A. Ashlock,et al.  Filtration and Depth Annotation Improve Non-linear Projection for RNA Motif Discovery , 2006, 2006 IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology.

[13]  Eun-Youn Kim,et al.  Understanding representational sensitivity in the iterated prisoner's dilemma with fingerprints , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[14]  P. Groenen,et al.  Modern multidimensional scaling , 1996 .

[15]  K. Lindgren,et al.  Evolutionary dynamics of spatial games , 1994 .

[16]  M. Nowak,et al.  Evolutionary game theory , 1995, Current Biology.

[17]  D. Roy.  Learning and the theory of games. , 2000, Journal of theoretical biology.

[18]  Mark de Berg,et al.  Computational geometry: algorithms and applications , 1997 .

[19]  John H. Miller,et al.  The coevolution of automata in the repeated Prisoner's Dilemma , 1996 .

[20]  Hisao Ishibuchi,et al.  Effects of Spatial Structures on Evolution of Iterated Prisoner’s Dilemma Game Strategies in Single-Dimensional and Two-Dimensional Grids , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[21]  D. Ashlock,et al.  Analysis of game playing agents with fingerprints , 2005 .

[22]  Daniel A. Ashlock,et al.  A model of emotion in the prisoner’s dilemma , 2008, 2008 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology.

[23]  David B. Fogel,et al.  Evolving Behaviors in the Iterated Prisoner's Dilemma , 1993, Evolutionary Computation.

[24]  Daniel A. Ashlock,et al.  The geometry of Tartarus fitness cases , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[25]  Daniel A. Ashlock,et al.  Techniques for analysis of evolved prisoner's dilemma strategies with fingerprints , 2005, 2005 IEEE Congress on Evolutionary Computation.

[26]  Daniel A. Ashlock,et al.  Acquisition of General Adaptive Features by Evolution , 1998, Evolutionary Programming.

[27]  Daniel A. Ashlock,et al.  Fingerprinting: Visualization and Automatic Analysis of Prisoner's Dilemma Strategies , 2008, IEEE Transactions on Evolutionary Computation.

[28]  W. Hamilton,et al.  The Evolution of Cooperation , 1984 .

[29]  Lawrence J. Fogel,et al.  Artificial Intelligence through Simulated Evolution , 1966 .

[30]  Daniel A. Ashlock,et al.  Fingerprints: enabling visualization and automatic analysis of strategies for two player games , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[31]  Daniel A. Ashlock,et al.  Training Function Stacks to play the Iterated Prisoner's Dilemma , 2006, 2006 IEEE Symposium on Computational Intelligence and Games.

[32]  M. Hemesath.  Cooperate or Defect? Russian and American Students in a Prisoner's Dilemma , 1994 .

[33]  Daniel A. Ashlock,et al.  Fingerprint Analysis of the Noisy Prisoner's Dilemma Using a Finite-State Representation , 2007, IEEE Transactions on Computational Intelligence and AI in Games.