Evolving Complex Group Behaviors Using Genetic Programming with Fitness Switching

Created by W.Langdon from gp-bibliography.bib Revision:1.4202

  author =       "Byoung-Tak Zhang and Dong-Yeon Cho",
  title =        "Evolving Complex Group Behaviors Using Genetic
                 Programming with Fitness Switching",
  journal =      "Artificial Life and Robotics",
  year =         "2000",
  volume =       "4",
  number =       "2",
  pages =        "103--108",
  keywords =     "genetic algorithms, genetic programming",
  URL =          "http://bi.snu.ac.kr/Publications/Journals/International/AROB4-2.ps",
  URL =          "http://citeseer.ist.psu.edu/454877.html",
  abstract =     "Genetic programming provides a useful tool for
                 emergent computation and artificial life. However,
                 conventional genetic programming is not efficient
                 enough to solve realistic multiagent tasks consisting
                 of several emergent behaviours that need to be
                 coordinated in proper sequence. In this paper, we
                 describe a novel method, called fitness switching, for
                 evolving composite cooperative behaviours of multiple
                 robotic agents using genetic programming. The method
                 maintains a pool of basis fitness functions which are
                 switched from simpler ones to more complex ones. The
                 performance is demonstrated and compared in the context
                 of a table transport problem. Experimental results show
                 that the fitness switching method is an effective
                 mechanism for evolving collective behaviours which may
                 not be solved by simple genetic programming.",

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