Abstract
Two species of agents coevolve in a 2D, physically simulated world. A simple fitness function rewards agents for shooting at agents of the other species. An evolutionary framework consisting of the gridbrain agent controller model and the SEEA steady-state evolutionary algorithm is used. We were able to observe a phenomenon of species specialization without the need for geographical separation. Species with equal initial conditions were shown to diverge to different specialization niches by way of the systems dynamics. This kind of research may lead to more interesting gaming environments, where the world keeps changing and evolving even in the absence of human interaction.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Stanley, K.O., Bryant, B.D., Miikkulainen, R.: Evolving Neural Network Agents in the Nero Video Game. In: Proceedings of the IEEE 2005 Symposium on Computational Intelligence and Games (2005)
Menezes, T., Costa, E.: Artificial Brains as Networks of Computational Building Blocks. In: Proc. of the 5th European Conference on Complex Systems, Jerusalem, Israel (2008), http://www.jeruccs2008.org/node/606
Menezes, T.: Evolutionary Computational Intelligence for Multi-Agent Simulations. Departamento de Engenharia Informatica, Faculdade de Ciencias e Tecnologia, Universidade de Coimbra (2008)
Poli, R.: Parallel Distributed Genetic Programming. technical report CSRP-96-15. The University of Birmingham, UK (1996)
Poli, R.: Optimization, Advanced Topics in Computer Science. In: Corne, D., et al. (eds.) Parallel Distributed Genetic Programming, ch. 27, pp. 403–431. McGraw-Hill, Maidenhead (1999)
Miller, J.F.: An Empirical Study of the Efficiency of Learning Boolean Functions using a Cartesian Genetic Programming Approach. In: GECCO 1999: Proceedings of the Genetic and Evolutionary Computation Conference, Orlando, Florida, pp. 1135–1142. Morgan Kaufmann, San Francisco (1999)
Miller, J.F., Thomson, P.: Cartesian Genetic Programming. In: Poli, R., Banzhaf, W., Langdon, W.B., Miller, J., Nordin, P., Fogarty, T.C. (eds.) EuroGP 2000. LNCS, vol. 1802, pp. 121–132. Springer, Heidelberg (2000)
Langdon, W.B.: The Evolution of Size in Variable Length Representations. In: 1998 IEEE International Conference on Evolutionary Computation, Anchorage, Alaska, USA, pp. 633–638. IEEE Press, Los Alamitos (1998)
Smith, M.J.: Group Selection and Kin Selection. Nature 201, 1145–1147 (1964)
Menezes, T.: Lablove - Laboratory of Life on a Virtual Environment (2007), http://sourceforge.net/projects/lablove
Dawkins, R., Krebs, J.: Arms Races Between and Within Species. Proceedings of the Royal Society of London 205(1161), 489–511 (1979)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Menezes, T., Costa, E. (2009). Coevolution of Competing Agent Species in a Game-Like Environment. In: Giacobini, M., et al. Applications of Evolutionary Computing. EvoWorkshops 2009. Lecture Notes in Computer Science, vol 5484. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01129-0_30
Download citation
DOI: https://doi.org/10.1007/978-3-642-01129-0_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01128-3
Online ISBN: 978-3-642-01129-0
eBook Packages: Computer ScienceComputer Science (R0)