Creating High-Level Components with a Generative Representation for Body-Brain Evolution

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

@Article{Hornby:2002:AL,
  author =       "Gregory S. Hornby and Jordan B. Pollack",
  title =        "Creating High-Level Components with a Generative
                 Representation for Body-Brain Evolution",
  journal =      "Artificial Life",
  year =         "2002",
  volume =       "8",
  number =       "3",
  pages =        "223--246",
  month =        "Summer",
  email =        "hornby@email.arc.nasa.gov",
  keywords =     "genetic algorithms, genetic programming, Body-brain
                 evolution, generative representations, representation,
                 Lindenmayer systems, L-systems",
  ISSN =         "1064-5462",
  URL =          "http://www.demo.cs.brandeis.edu/papers/hornby_alife02.pdf",
  URL =          "http://ic.arc.nasa.gov/people/hornby/genre/genre.html",
  URL =          "http://mitpress.mit.edu/journals/pdf/alife_8_3_223_0.pdf",
  DOI =          "doi:10.1162/106454602320991837",
  size =         "30 pages",
  size =         "25 pages",
  abstract =     "One of the main limitations of scalability in
                 body-brain evolution systems is the representation
                 chosen for encoding creatures. This paper defines a
                 class of representations called generative
                 representations, which are identified by their ability
                 to reuse elements of the genotype in the translation to
                 the phenotype. This paper presents an example of a
                 generative representation for the concurrent evolution
                 of the morphology and neural controller of simulated
                 robots, and also introduces GENRE, an evolutionary
                 system for evolving designs using this representation.
                 Applying GENRE to the task of evolving robots for
                 locomotion and comparing it against a non-generative
                 (direct) representation shows that the generative
                 representation system rapidly produces robots with
                 significantly greater fitness. Analyzing these results
                 shows that the generative representation system
                 achieves better performance by capturing useful bias
                 from the design space and by allowing viable large
                 scale mutations in the phenotype. Generative
                 representations thereby enable the encapsulation,
                 coordination, and reuse of assemblies of parts.",
  notes =        "The project page for this work is at:
                 http://www.demo.cs.brandeis.edu/pr/evo_design/evo_design.html

                 Managed to get two entries for this paper. Combined
                 them (ie also known as \cite{hornby_alife02}. April
                 2008.",
  notes =        "genetic variations are repeated if offspring
                 fitness<0.1 parent",
}

Genetic Programming entries for Gregory S Hornby Jordan B Pollack

Citations