Evolving Controllers for Autonomous Agents Using Genetically Programmed Networks

Created by W.Langdon from gp-bibliography.bib Revision:1.4420

  author =       "Arlindo Silva and Ana Neves and Ernesto Costa",
  title =        "Evolving Controllers for Autonomous Agents Using
                 Genetically Programmed Networks",
  booktitle =    "Genetic Programming, Proceedings of EuroGP'99",
  year =         "1999",
  editor =       "Riccardo Poli and Peter Nordin and 
                 William B. Langdon and Terence C. Fogarty",
  volume =       "1598",
  series =       "LNCS",
  pages =        "255--269",
  address =      "Goteborg, Sweden",
  publisher_address = "Berlin",
  month =        "26-27 " # may,
  organisation = "EvoNet",
  publisher =    "Springer-Verlag",
  keywords =     "genetic algorithms, genetic programming: Poster",
  ISBN =         "3-540-65899-8",
  URL =          "http://eden.dei.uc.pt/~ernesto/EvoCo/papers/papers/1999/eurgp992.pdf",
  URL =          "http://citeseer.ist.psu.edu/442333.html",
  URL =          "http://www.springerlink.com/openurl.asp?genre=article&issn=0302-9743&volume=1598&spage=255",
  DOI =          "doi:10.1007/3-540-48885-5_22",
  abstract =     "This article presents a new approach to the evolution
                 of controllers for autonomous agents. We propose the
                 evolution of a connectionist structure where each node
                 has an associated program, evolved using genetic
                 programming. We call this structure a Genetically
                 Programmed Network and use it to successfully evolve
                 control systems with very different architectures, by
                 making small restrictions to the evolutionary process.
                 Experimental results of applying this method to evolve
                 neural networks, distributed programs and rule-based
                 systems all capable of solving a common benchmark
                 problem, the Ant Problem, are presented. Comparisons
                 with other known genetic programming based approaches,
                 show that our method requires less effort to find a
  notes =        "EuroGP'99, part of \cite{poli:1999:GP}

                 Santa Fe ant",

Genetic Programming entries for Arlindo Ferreira da Silva Ana Paula Neves F Silva Ernesto Costa