Evolutionary Learning of Multiagents Using Strategic Coalition in the IPD Game
Social and economic systems consist of complex interactions among its members. Their behaviors become adaptive according to changing environment. In many cases, an individual’s behaviors can be modeled by a stimulus-response system in a dynamic environment. In this paper, we use the Iterated Prisoner’s Dilemma (IPD) game, which is a simple model to deal with complex problems for dynamic systems. We propose strategic coalition consisting of many agents and simulate their emergence in a co-evolutionary learning environment. Also we introduce the concept of confidence for agents in a coalition and show how such confidences help to improve the generalization ability of the whole coalition. Experimental results show that co-evolutionary learning with coalitions and confidence can produce better performing strategies that generalize well in dynamic environments.
KeywordsGeneralization Ability Coalition Formation Coalition Structure Evolutionary Learn Game Form Coalition
Unable to display preview. Download preview PDF.
- 1.Ord, T., Blair, A.: Exploitation and peacekeeping: Introducing more sophisticated interactions to the iterated prisoner’s dilemma. In: Proceedings of the 2002 Congress on Evolutionary Computation, vol. 2, pp. 1606–1611 (2002)Google Scholar
- 4.Seo, Y.G., Cho, S.B., Yao, X.: Exploiting coalition in co-evolutionary learning. In: Proceedings of the Congress on Evolutionary Computation, vol. 2, pp. 1268–1275 (2000)Google Scholar
- 5.Fletcher, J.A., Zwick, M.: N-Player prisoner’s dilemma in multiple groups: A model of multilevel selection. In: Proceedings of the Artificial Life VII Workshops, Portland, Oregon (2000)Google Scholar
- 8.Yao, X., Darwen, P.J.: How important is your reputation in a multi-agent environment. In: Proceedings of IEEE International Conference on Systems, Man, and Cybernetics (SMC 1999), vol. 2, pp. II-575–II-580. IEEE Press, Piscataway (1999)Google Scholar
- 9.Darwen, P.J., Yao, X.: On evolving robust strategies for iterated prisoner’s dilemma. In: Yao, X. (ed.) AI-WS 1993 and 1994. LNCS, vol. 956, pp. 276–292. Springer, Heidelberg (1995)Google Scholar
- 10.Ashlock, D., Joenks, M.: ISAc lists, a different representation for program induction. In: Proceedings of the Third Annual Genetic Programming Conference on Genetic Programming 1998, pp. 3–10. Morgan Kaufmann, San Francisco (1998)Google Scholar
- 11.Axelrod, R.: The evolution of strategies in the iterated prisoner’s dilemma. In: Genetic Algorithms and Simulated Annealing, vol. 3, pp. 32–41. Morgan-Kaufmann, San Mateo (1987)Google Scholar
- 14.Allsopp, D.N., Kirton, P., Bradshaw, M., et al.: Coalition agents experiment: Multiagent cooperation in international coalitions. IEEE Intelligent Systems 17, 26–35 (2002)Google Scholar
- 15.Tate, A., Bradshaw, M., Pechoucek, M.: Knowledge systems for coalition operations. IEEE Intelligent Systems 17, 14–16 (2002)Google Scholar
- 17.Axelrod, R.: The Evolution of Cooperation. Basic Books, New York (1984)Google Scholar