Coevolving Deep Hierarchies of Programs to Solve Complex Tasks

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

@InProceedings{Smith:2017:GECCO,
  author =       "Robert J. Smith and Malcolm I. Heywood",
  title =        "Coevolving Deep Hierarchies of Programs to Solve
                 Complex Tasks",
  booktitle =    "Proceedings of the Genetic and Evolutionary
                 Computation Conference",
  series =       "GECCO '17",
  year =         "2017",
  isbn13 =       "978-1-4503-4920-8",
  address =      "Berlin, Germany",
  pages =        "1009--1016",
  size =         "8 pages",
  URL =          "http://doi.acm.org/10.1145/3071178.3071316",
  DOI =          "doi:10.1145/3071178.3071316",
  acmid =        "3071316",
  publisher =    "ACM",
  publisher_address = "New York, NY, USA",
  keywords =     "genetic algorithms, genetic programming, coevolution,
                 games, reinforcement learning",
  month =        "15-19 " # jul,
  abstract =     "Scaling genetic programming to organize large complex
                 combinations of programs remains an under investigated
                 topic in general. This work revisits the issue by first
                 demonstrating the respective contributions of
                 coevolution and diversity maintenance. Competitive
                 coevolution is employed to organize a task in such a
                 way that the most informative training cases are
                 retained. Cooperative coevolution helps discover
                 modularity in the solutions discovered and, in this
                 work, is fundamental to constructing complex structures
                 of programs that still execute efficiently (the policy
                 tree). The role of coevolution and diversity
                 maintenance is first independently established under
                 the task of discovering reinforcement learning policies
                 for solving Rubik's Cubes scrambled with 5-twists. With
                 this established, a combined approach is then adopted
                 for building large organizations of code for
                 representing policies that solve 5 to 8-twist
                 combinations of the Cube. The resulting deep policy
                 tree organizes hundreds of programs to provide optimal
                 solutions to tens of millions of test cube
                 configurations.",
  notes =        "Also known as \cite{Smith:2017:CDH:3071178.3071316}
                 GECCO-2017 A Recombination of the 26th International
                 Conference on Genetic Algorithms (ICGA-2017) and the
                 22nd Annual Genetic Programming Conference (GP-2017)",
}

Genetic Programming entries for Robert J Smith Malcolm Heywood

Citations