The impact of cellular representation on finite state agents for prisoner's dilemma

ABSTRACT

The iterated prisoner's dilemma is a widely used computational model of cooperation and conflict. Many studies report emergent cooperation in populations of agents trained to play prisoner's dilemma with an evolutionary algorithm. Cellular representation is the practice of evolving a set of instructions for constructing a desired structure. This paper presents a cellular encoding for finite state automata and specializes it to play the iterated prisoner's dilemma. The impact on the character and behavior of finite state agents that results from using the cellular representation is investigated. For the cellular representation presented a statistically significant drop in the level of cooperation is found. Other differences in the character of the automaton generated with a direct and cellular representation are reported. This paper forms part of an ongoing study of the impact of representation on evolved agents for playing prisoner's dilemma.

REFERENCES

• 1: D. Ashlock and N. Leahy. A representational study of game theoretic simulations. In SMCia/03: Proceedings of the 2003 IEEE Conference on Soft Computing in Industrial Applications, pages 67--72, Piscataway NJ, 2003. IEEE Press.
• 2: D. Ashlock, M. D. Smucker, E. A. Stanley, and L. Tesfatsion. Preferential partner selection in an evolutionary study of prisoner's dilemma. Biosystems, 37:99--125, 1996.
• 3: R. Axelrod. The Evolution of Cooperation. Basic Books, New York, 1984.
• 4: R. Axelrod and W. D. Hamilton. The evolution of cooperation. Science, 211:1390--1396, 1981.
• 5: Wolfgang Banzhaf , Frank D. Francone , Robert E. Keller , Peter Nordin, Genetic programming: an introduction: on the automatic evolution of computer programs and its applications, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1998
• 6: L. A. Dugatkin and M. Mesterton-Gibbons. Cooperation among unrealted individuals: Reciprocal altruism, byproduct mutalism and group selection in fishes. Biosystems, 37:19--30, 1996.
• 7: David B. Fogel, Evolving behaviors in the iterated prisoner's dilemma, Evolutionary Computation, v.1 n.1, p.77-97, Spring 1993
• 8: D. B. Fogel. On the relationship between the duration of an encounter and the evolution of cooperation in the iterated prisoner's dilemma. Working Paper, July 1994.
• 9: F. Gruau. Neural Network Synthesis using Cellular Encoding and the Genetic Algorithm. PhD thesis, France, 1994.
• 10: Frédéric Gruau, Automatic definition of modular neural networks, Adaptive Behavior, v.3 n.2, p.151-183, Fall 1994 [doi>10.1177/105971239400300202]
• 11: M. Hemesath. Cooperate or defect? russian and american students in a prisoner's dilemma. Comparative Economics Studies, 176:83--93, 1994.
• 12: J. M. Houston, J. Kinnie, B. Lupo, C. Terry, and S. S. Ho. Competitiveness and conflict behavior in simulation of a social dilemma. Psychological Reports, 86:1219--1225, 2000.
• 13: J. H. Miller. The coevolution of automata in the repeated prisoner's dilemma. Journal of Economic Behavior and Organization, 29(1):87--112, January 1996.
• 14: D. Roy. Learning and the theory of games. Journal of Theoretical Biology, 204:409--414, 2000.
• 15: K. Sigmund and M. A. Nowak. Evolutionary game theory. Current Biology, 9(14):R503--505, 1999.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.m Miscellaneous

General Terms:
Design

Keywords:
cellular representation, evolutionary computation, prisoner's dilemma