Dynamics of Co-evolutionary Learning

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@InProceedings{juile:1996:dcl,
  author =       "Hugues Juille and Jordan B. Pollack",
  title =        "Dynamics of Co-evolutionary Learning",
  booktitle =    "Proceedings of the Fourth International Conference on
                 Simulation of Adaptive Behavior: From animals to
                 animats 4",
  year =         "1996",
  editor =       "Pattie Maes and Maja J. Mataric and 
                 Jean-Arcady Meyer and Jordan Pollack and Stewart W. Wilson",
  pages =        "526--534",
  address =      "Cape Code, USA",
  publisher_address = "Cambridge, MA, USA",
  month =        "9-13 " # sep,
  publisher =    "MIT Press",
  keywords =     "genetic algorithms, genetic programming, Spirals,
                 Coevolution",
  ISBN =         "0-262-63178-4",
  URL =          "http://www.demo.cs.brandeis.edu/papers/sab96b.pdf",
  URL =          "http://www.demo.cs.brandeis.edu/papers/sab96b.ps.gz",
  URL =          "http://www.demo.cs.brandeis.edu/papers/sab96b.ps",
  URL =          "http://www.cs.brandeis.edu/~hugues/papers/SAB_96.ps.gz",
  URL =          "http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6291901",
  size =         "9 pages",
  abstract =     "Co-evolutionary learning, which involves the embedding
                 of adaptive learning agents in a fitness environment
                 which dynamically responds to their progress, is a
                 potential solution for many technological chicken and
                 egg problems, and is at the heart of several recent and
                 surprising successes, such as Sim's artificial robot
                 and Tesauro's backgammon player. We recently solved the
                 two spirals problem, a difficult neural network
                 benchmark classification problem, using the genetic
                 programming primitives set up by [ \cite{koza:book} ].
                 Instead of using absolute fitness, we use a relative
                 fitness [ \cite{icga93:angeline} ] based on a
                 competition for coverage of the data set. As the
                 population reproduces, the fitness function driving the
                 selection changes, and subproblem niches are opened,
                 rather than crowded out. The solutions found by our
                 method have a symbiotic structure which suggests that
                 by holding niches open.",
  notes =        "SAB-96",
}

Genetic Programming entries for Hugues Juille Jordan B Pollack

Citations