Evolution and Cooperation of Virtual Entities with Classifier Systems
This paper presents a behavioral system based on artiticial life paradigms. The system, called αCS, is suited to be employed for the animation of virtual entities immersed in concurrent and changing environments. The αCS system is the extension of an original classifier system to collaborative abilities. The main modifications enable αCS to use cooperation and communication to build dynamically the behavior of virtual entities which goal is to achieve several tasks. Our classifier system is evaluated by the way of two applications. Firstly, we present the performances of αCS in an optimization problem consisting on following a moving target. Secondly, we investigate a complex 3D world where autonomous entities and avatars interact. Through the simulation of a virtual game, we show how the integration of our system in virtual entities enables to build evolving behaviors thanks to adaptation, communication and auto-organization.
KeywordsFitness Function Virtual World Classifier System Condition Part Reward System
Unable to display preview. Download preview PDF.
- 1.Blumberg B., Galyean T., “Multi-Level. Direction of Autonomous Creatures for Real-Time Virtual Environment”. Proceedings of Siggraph 95. Computer Graphics Proceedings. Aug 1995.Google Scholar
- 2.Butz M., Stolzmann W. “Action-Planning in Anticipatory Classifier”, IWLCS’ 99, Second International Workshop on Learning Classifier Systems, Orlando USA, 13 Juillet 1999.Google Scholar
- 3.Holland J. H., “Adaptation in Natural and Artificial Systems”, Ann Arbor, University of Michigan Press, 1975.Google Scholar
- 4.Holland J. H., “Adaptive Algorithms for Discovering and Using General Patterns in Growing Knowledge Bases”, International Journal for Policy Analysis and Informations Systems, Vol 4, No 3, pp 245–268, 1980.Google Scholar
- 5.Lattaud C., “Non-Homogeneous Classifier Systems in a Macro-Evolution Process”, IWLCS’ 99, Second International Workshop on Learning Classifier Systems, Orlando USA, 13 July 1999.Google Scholar
- 6.Mataric M.J., “Reward Functions for Accelerated Learning” in Machine Learning: Proceedings of the Eleventh International Conference, William W. Cohen and Haym Hirsh, eds., Morgan Kaufmann Publishers, San Francisco, CA, 1994.Google Scholar
- 7.Musse S.R., Kallmann M., Thalmann D., “Level of Autonomy for Virtual Human Agents”. Proceedings ECAL 99, 5th European Conference on Artificial Life. Lausanne, Switzerland. Sep 1999.Google Scholar
- 8.Panatier C., Luga H., Duthen Y., “Collective Learning for Spatial Collaboration”, SAB’ 98, From Animals to Animats 5, Zurich, Switzerland, August 1998.Google Scholar
- 9.Sanza C., Panatier C., Duthen Y., “Communication and Interaction with Learning Agents in Virtual Soccer”, VW’ 2000, 2nd International Conference on Virtual Worlds, Paris, France, Juillet 2000Google Scholar
- 10.Stolzmann W., “Anticipatory Classifier Systems”, Genetic Programming’ 98, Proceedings of the Third Annual Conference, Morgan Kaufmann p. 658–664, San Francisco, USA, 22-25 July 1998.Google Scholar
- 11.Wilson S.W., “Classifier Fitness Based on Accuracy”, Evolutionary Computation, Vol 3 (2), MIT Press, 1995.Google Scholar
- 12.http://www.sense8.comGoogle Scholar