Coevolutionary Fitness Switching: Learning Complex Collective Behaviors Using Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@InCollection{zhang:1999:aigp3,
  author =       "Byoung-Tak Zhang and Dong-Yeon Cho",
  title =        "Coevolutionary Fitness Switching: Learning Complex
                 Collective Behaviors Using Genetic Programming",
  booktitle =    "Advances in Genetic Programming 3",
  publisher =    "MIT Press",
  year =         "1999",
  editor =       "Lee Spector and William B. Langdon and 
                 Una-May O'Reilly and Peter J. Angeline",
  chapter =      "18",
  pages =        "425--445",
  address =      "Cambridge, MA, USA",
  month =        jun,
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "0-262-19423-6",
  URL =          "http://bi.snu.ac.kr/Publications/Books/aigp3.ps",
  URL =          "http://www.cs.bham.ac.uk/~wbl/aigp3/ch18.pdf",
  URL =          "http://citeseer.ist.psu.edu/454784.html",
  abstract =     "Genetic programming provides a useful paradigm for
                 developing multiagent systems in the domains where
                 human programming alone is not sufficient to take into
                 account all the details of possible situations.
                 However, existing GP methods attempt to evolve
                 collective behavior immediately from primitive actions.
                 More realistic tasks require several emergent behaviors
                 and a proper coordination of these is essential for
                 success. We have recently proposed a framework, called
                 fitness switching, to facilitate learning to coordinate
                 composite emergent behaviors using genetic programming.
                 Coevolutionary fitness switching described in this
                 chapter extends our previous work by introducing the
                 concept of coevolution for more effective
                 implementation of fitness switching. Performance of the
                 presented method is evaluated on the table transport
                 problem and a simple version of simulated robot soccer
                 problem. Simulation results show that coevolutionary
                 fitness switching provides an effective mechanism for
                 learning complex collective behaviors which may not be
                 evolved by simple genetic programming.",
  notes =        "AiGP3",
}

Genetic Programming entries for Byoung-Tak Zhang Dong-Yeon Cho

Citations