Niching in Evolutionary Multi-agent Systems

Daniel Krzywicki

doi:10.7494/csci.2013.14.1.77

Authors

Daniel Krzywicki

DOI:

https://doi.org/10.7494/csci.2013.14.1.77

Keywords:

niching, evolutionary algorithms, multi-agent systems

Abstract

Niching is a group of techniques used in evolutionary algorithms, useful inseveral types of problems, including multimodal or nonstationary optimiza-tion. This paper investigates the applicability of these methods to evolutionarymulti-agent systems (EMAS), a hybrid model combining the advantages of evo-lutionary algorithms and multi-agent systems. This could increase the eﬃciencyof this type of algorithms and allow to apply them to a wider class of prob-lems. As a starting point, a simple but ﬂexible EMAS framework is proposed.Then, it is shown how to extend this framework in order to introduce niching,by adapting two classical niching methods. Finally, preliminary experimentalresults show the eﬃciency and the simultaneous discovery of multiple optimaby this modiﬁed EMAS.

Downloads

Download data is not yet available.

References

Byrski A., Kisiel-Dorohinicki M., Nawarecki E.: Agent-based evolution of neural network architecture. In Applied Informatics, ACTA Press, 2002.

Byrski A., Schaefer R.: Stochastic model of evolutionary and immunological multi-agent systems: Mutually exclusive actions. Fundamenta Informaticae, 95(2):263–285, IOS Press, 2009.

Cetnarowicz K., Kisiel-Dorohinicki M., Nawarecki E.: The application of evolution process in multi-agent world to the prediction system. In Proc. of the Second International Conference on Multi-Agent Systems, ICMAS, vol. 96, pp. 26–32, 1996.

De Jong K.: An analysis of the behavior of a class of genetic adaptive systems. PhD thesis, University of Michigan, Ann Arbor, MI, USA, 1975.

Defaweux A., Lenaerts T., Maes S., Tuyls K., van Remortel P., Verbeeck K., Nowe A., Manderick B.: Niching and evolutionary transitions in mas. In Proc. of GECCO 2001, presented at the Workshop on Evolutionary Computation and Multi-agent Systems, 7–11 July, 2001.

Drezewski R.: A model of co-evolution in multi-agent system. Multi-Agent Systems and Applications III, pp. 1067–1067, Springer, 2003.

Drezewski R., Sepielak J., Siwik L.: Classical and agent-based evolutionary algorithms for investment strategies generation. Natural Computing in Computational Finance, pp. 181–205, Springer, 2009.

Drezewski R., Siwik L.: Co-evolutionary multi-agent system for portfolio optimization. Natural Computing in Computational Finance, pp. 271–299, Springer, 2008.

Frey B., Dueck D.: Clustering by passing messages between data points. Science, 315(5814):972–976, 2007.

Givoni I., Chung C., Frey B.: Hierarchical aﬃnity propagation. Arxiv preprint arXiv:1202.3722, 2012.

Horn J.: The nature of niching: Genetic algorithms and the evolution of optimal, cooperative populations. PhD thesis, Citeseer, 1997.

Jennings N.: On agent-based software engineering. Artiﬁcial Intelligence, 117(2):277–296, Elsevier, 2000.

Kisiel-Dorohinicki M.: Flock-based architecture for distributed evolutionary algorithms. In Artiﬁcial Intelligence and Soft Computing, pp. 841–846. ICAISC, Springer, 2004.

Mahfoud S.: Niching methods for genetic algorithms. Urbana, 51(95001), 1995. Citeseer.

Mengshoel O., Galan S.: Generalized crowding for genetic algorithms. In Genetic and Evolutionary Computation Conference 2010, pp. 775–782. GECCO, 2010.

Mengshoel O., Goldberg D.: Probabilistic crowding: Deterministic crowding with probabilistic replacement. In Proc. of the Genetic and Evolutionary Computation Conference, pp. 409–416. GECCO, 1999.

Mengshoel O., Goldberg D.: The crowding approach to niching in genetic algorithms. Evolutionary Computation, 16(3):315–354, 2008.

Morrison R., De Jong K.: Measurement of population diversity. In Artiﬁcial Evolution, pp. 1047–1074. Springer, 2002.

Petrowski A.: A clearing procedure as a niching method for genetic algorithms. In Evolutionary Computation, 1996., Proc. of IEEE International Conference on, pp. 798–803. IEEE, 1996.

Petrowski A.: An eﬃcient hierarchical clustering technique for speciation. Evolution. Technical report, Institute National des Telecommunications, Evry, France, Technique Report, 1997.

Schaefer R., Byrski A., Smo lka M.: Stochastic model of evolutionary and immunological multi-agent systems: Parallel execution of local actions. Fundamenta Informaticae, 95(2):325–348, IOS Press, 2009.

Ursem R. K.: Multinational evolutionary algorithms. In Proc. of the Congress of Evolutionary Computation (CEC-99), vol. 3, pp. 1633–1640, 1999.