Effects of Learning to Interact on the Evolution of Social Behavior of Agents in Continuous Predators-Prey Pursuit Problem
We present the results of our work on the effect of learning to interact on the evolution of social behavior of agents situated in inherently cooperative environment. Using continuous predators-prey pursuit problem we verified our hypothesis that relatively complex social behavior may emerge from simple, implicit, locally defined, and therefore – robust and highly-scalable interactions between the predator agents. We argue that the ability of agents to learn to perform simple, atomic acts of implicit interaction facilitates the performance of evolution of more complex, social behavior. The empirical results show about two-fold decrease of computational effort of proposed strongly typed genetic programming (STGP), used as an algorithmic paradigm to evolve the social behavior of the agents, when STGP is combined with learning of agents to implicitly interact with each other.
KeywordsSocial Behavior Genetic Programming Document Object Model Cooperative Environment Complex Social Behavior
Unable to display preview. Download preview PDF.
- 1.Benda, M., Jagannathan, B., Dodhiawala, R.: On Optimal Cooperation of Knowledge Sources. Technical Report BCS-G2010-28, Boeing AI Center, Boeing Computer Services, Bellevue, WA (1986)Google Scholar
- 3.Ferber, J.: Multi-Agent Systems: An Introduction to Distributed Artificial Intelligence. Addison Wesley Longman, Harlow (1999)Google Scholar
- 4.Floreano, D., Nolfi, S., Mondada, F.: Co-evolution and ontogenetic change in competing robots. In: Mukesh, J.P., Honavar, V., Balakrishan, K. (eds.) Advances in Evolutionary Synthesis of Neural Networks, pp. 273–306. MIT Press, Cambridge (2001)Google Scholar
- 5.Haynes, T., Sen, S.: Evolving Behavioral Strategies in Predators and Prey. In: Weiss, G., Sen, S. (eds.) Adaptation and Learning in Multi-Agent Systems, pp. 113–126 (1996)Google Scholar
- 6.Haynes, T., Wainwright, R., Sen, S., Schoenefeld, D.: Strongly Typed Genetic Programming in Evolving Cooperation Strategies. In: Eshelman, L. (ed.) Genetic Algorithms: Proceedings of the Sixth International Conference (ICGA 1995), pp. 271–278. M. Kaufmann, San Francisco (1995)Google Scholar
- 7.Holand, J.H.: Emergence: From Chaos to Order. Perseus Books, Cambridge (1999)Google Scholar
- 10.Morgan, C.: Emergent Evolution, New York (1923)Google Scholar
- 11.Morowitz, H.J.: The emergence of Everything: How the World Became Complex. Oxford University Press, New York (2002)Google Scholar
- 12.Parunak, H., Van, D., Brueckner, S., Fleischer, M., Odell, J.: Co-X: Defining what Agents Do Together. In: Shehory, O., Ioerger, T.R., Vassileva, J., Yen, J. (eds.) Proceedings of the AAMAS 2002 Workshop on Teamwork and Coalition Formation, Bologna, Italy (2002)Google Scholar
- 13.Tanev, I., Shimohara, K.: On Role of Implicit Interaction and Explicit Communications in Emergence of Social Behavior in Continuous Predators-prey Pursuit Problem. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2003), Chicago, IL, USA (2003) (to appear)Google Scholar