Multi-Population Competitive Co-Evolution of Car Racing Controllers

Created by W.Langdon from gp-bibliography.bib Revision:1.4192

  author =       "Julian Togelius and Peter Burrow and Simon M. Lucas",
  title =        "Multi-Population Competitive Co-Evolution of Car
                 Racing Controllers",
  booktitle =    "2007 IEEE Congress on Evolutionary Computation",
  year =         "2007",
  editor =       "Dipti Srinivasan and Lipo Wang",
  pages =        "4043--4050",
  address =      "Singapore",
  month =        "25-28 " # sep,
  organization = "IEEE Computational Intelligence Society",
  publisher =    "IEEE Press",
  ISBN =         "1-4244-1340-0",
  file =         "1549.pdf",
  keywords =     "genetic algorithms, genetic programming",
  DOI =          "doi:10.1109/CEC.2007.4424998",
  abstract =     "Multi-population competitive co-evolution is explored
                 as a way of developing controllers for a simple (but
                 definitely not trivial) car racing game. The three main
                 uses we see for this method are to evolve more complex
                 general intelligence than would be possible with other
                 methods, to compare different evolvable architectures
                 for controllers, and to develop behaviourally diverse
                 populations of agents for computer games.
                 Nine-population co-evolution is compared with
                 single-population co-evolution and standard evolution
                 strategies, steady-state and generational versions of
                 the algorithm are compared, and a number of different
                 controller architectures are compared with each
  notes =        "CEC 2007 - A joint meeting of the IEEE, the EPS, and
                 the IET.

                 IEEE Catalog Number: 07TH8963C",

Genetic Programming entries for Julian Togelius Peter Burrow Simon M Lucas