Layered Learning in Genetic Programming for a Co-operative Robot Soccer Problem

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

@InProceedings{gustafson:2001:EuroGP,
  author =       "Steven M. Gustafson and William H. Hsu",
  title =        "Layered Learning in Genetic Programming for a
                 Co-operative Robot Soccer Problem",
  booktitle =    "Genetic Programming, Proceedings of EuroGP'2001",
  year =         "2001",
  editor =       "Julian F. Miller and Marco Tomassini and 
                 Pier Luca Lanzi and Conor Ryan and Andrea G. B. Tettamanzi and 
                 William B. Langdon",
  volume =       "2038",
  series =       "LNCS",
  pages =        "291--301",
  address =      "Lake Como, Italy",
  publisher_address = "Berlin",
  month =        "18-20 " # apr,
  organisation = "EvoNET",
  publisher =    "Springer-Verlag",
  keywords =     "genetic algorithms, genetic programming, Layered
                 Learning, Hierarchical abstractions, Robot soccer,
                 Robots, Multiagent systems: Poster",
  ISBN =         "3-540-41899-7",
  URL =          "http://www.cs.nott.ac.uk/~smg/research/publications/eurogp-2001.ps",
  URL =          "http://www.cs.nott.ac.uk/~smg/research/publications/eurogp-2001.pdf",
  URL =          "http://www.springerlink.com/openurl.asp?genre=article&issn=0302-9743&volume=2038&spage=291",
  DOI =          "doi:10.1007/3-540-45355-5_23",
  size =         "11 pages",
  abstract =     "We present an alternative to standard genetic
                 programming (GP) that applies layered learning
                 techniques to decompose a problem. GP is applied to
                 subproblems sequentially, where the population in the
                 last generation of a subproblem is used as the initial
                 population of the next subproblem. This method is
                 applied to evolve agents to play keep-away soccer, a
                 subproblem of robotic soccer that requires cooperation
                 among multiple agents in a dynnamic environment. The
                 layered learning paradigm allows GP to evolve better
                 solutions faster than standard GP. Results show that
                 the layered learning GP outperforms standard GP by
                 evolving a lower fitness faster and an overall better
                 fitness. Results indicate a wide area of future
                 research with layered learning in GP.

                 ",
  notes =        "EuroGP'2001, part of miller:2001:gp. See also
                 \cite{gustafson:mastersthesis}",
}

Genetic Programming entries for Steven M Gustafson William H Hsu

Citations