Maximizing adaptive power in neuroevolution.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read Online Read More Add to Saved list
  • Author(s): Pagliuca P;Pagliuca P; Milano N; Milano N; Nolfi S; Nolfi S
  • Source:
    PloS one [PLoS One] 2018 Jul 18; Vol. 13 (7), pp. e0198788. Date of Electronic Publication: 2018 Jul 18 (Print Publication: 2018).
  • Publication Type:
    Journal Article
  • Language:
    English
  • Additional Information
    • Source:
      Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE
    • Publication Information:
      Original Publication: San Francisco, CA : Public Library of Science
    • Subject Terms:
      Biological Evolution* ; Central Nervous System*; Motor Neurons/*physiology ; Nerve Net/*physiology; Algorithms ; Animals ; Humans
    • Abstract:
      In this paper we compare systematically the most promising neuroevolutionary methods and two new original methods on the double-pole balancing problem with respect to: the ability to discover solutions that are robust to variations of the environment, the speed with which such solutions are found, and the ability to scale-up to more complex versions of the problem. The results indicate that the two original methods introduced in this paper and the Exponential Natural Evolutionary Strategy method largely outperform the other methods with respect to all considered criteria. The results collected in different experimental conditions also reveal the importance of regulating the selective pressure and the importance of exposing evolving agents to variable environmental conditions. The data collected and the results of the comparisons are used to identify the most effective methods and the most promising research directions.
      Competing Interests: The authors have declared that no competing interests exist.
    • References:
      Artif Life. 2005 Winter-Spring;11(1-2):139-60. (PMID: 15811224)
      Evol Comput. 1997 Winter;5(4):373-99. (PMID: 10021764)
      Evol Comput. 2002 Summer;10(2):99-127. (PMID: 12180173)
      Artif Life. 2009 Spring;15(2):185-212. (PMID: 19199382)
      Artif Life. 2002;8(3):223-46. (PMID: 12537684)
      Proc Natl Acad Sci U S A. 2011 Jan 25;108(4):1234-9. (PMID: 21220304)
    • Publication Date:
      Date Created: 20180719 Date Completed: 20181228 Latest Revision: 20181228
    • Publication Date:
      20240105
    • Accession Number:
      PMC6051599
    • Accession Number:
      10.1371/journal.pone.0198788
    • Accession Number:
      30020942