Cyclic evolution: a new strategy for improving controllers obtained by layered evolution

• Autores: Javier Hugo Olivera, Laura Cristina Lanzarini
• Localización: Journal of Computer Science and Technology, ISSN-e 1666-6038, Vol. 5, Nº. 4, 2005 (Ejemplar dedicado a: Sixteenth Issue), págs. 211-217
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Complex control tasks may be solved by dividing them into a more specific and more easily handled subtasks hierarchy. Several authors have demonstrated that the incremental layered evolution paradigm allows obtaining controllers capable of solving this type of tasks. In this direction, different solutions combining Incremental Evolution with Evolving Neural Networks have been developed in order to provide an adaptive mechanism minimizing the previous knowledge necessary to obtain a good performance giving place to controllers made up of several networks. This paper is focused on the presentation of a new mechanism, called Cyclic Evolution, which allows improving controllers based on neural networks obtained through layered evolution. Its performance is based on continuing the cyclic improvement of each of the networks making up the controller within the whole domain of the problem. The proposed method of this paper has been used to solve the Keepaway game with successful results compared to other solutions recently proposed. Finally, some conclusions are included together with some future lines of work.

• Referencias bibliográficas
  • References [1] Bruce, J. and Miikkulainnen, R. Evolving Populations of Expert Neural Networks. Department of Computer Sciences, The University...
  • [2] Corbalán L., Osella Massa G., Lanzarini L., De Giusti A. ANELAR. Arreglos Neuronales Evolutivos de Longitud Adaptable Reducida. X Congreso...
  • [3] Gomez, F. and Miikkulainen, R. Incremental Evolution Of Complex General Behavior Department of Computer Sciences, The University of Texas...
  • [4] S. Whitson, N. Kohl, R. Miikkulainen, P. Stone. Evolving. Soccer Keepaway Players through Task Decompositions. Machine Learning, 59(1):...
  • [5] Stone P., Veloso M. Multiagent Systems: A survey from a Machine Learning Perspective. Autonomous Robots. Vol.8, nro. 3, pp. 345-383. 2000.
  • [6] Stone, P. Layered Learning in Multiagent Systems. PhD Thesis. CMU-CS-98-187. School of Computer Science. Carnegie Melon University. 1998
  • [7] Stone, P. and R. S. Sutton: 2002, ‘KeepAway Soccer: a Machine Learning Tesbed’. In: A. Birk, S. Coradeschi, and S. Tadokoro (eds.): RoboCup-2001:...
  • [8] Whiteson S., Stone P. Concurrent Layered Learning. Second International Conference on Autonomous Agents and Multiagent Systems -AAMAS’03...
  • [9] Yao, X. and Liu, Y. Ensemble Structure of Evolutionary Artificial Neural networks. Computational intelligence Group, School of Computer...
  • [10] Yao, X. Evolving Artificial Neural networks. School of Computer Science The University of Birmingham Edgbaston, Birmingham B15 2TT. Proceedings...