Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Autonomous learning of features for control: Experiments with embodied and situated agents.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read Online Read More Add to Saved list
  • Author(s): Milano N;Milano N; Nolfi S; Nolfi S
  • Source:
    PloS one [PLoS One] 2021 Apr 15; Vol. 16 (4), pp. e0250040. Date of Electronic Publication: 2021 Apr 15 (Print Publication: 2021).
  • 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:
      Learning* ; Neural Networks, Computer*; Algorithms ; Humans
    • Abstract:
      The efficacy of evolutionary or reinforcement learning algorithms for continuous control optimization can be enhanced by including an additional neural network dedicated to features extraction trained through self-supervision. In this paper we introduce a method that permits to continue the training of the features extracting network during the training of the control network. We demonstrate that the parallel training of the two networks is crucial in the case of agents that operate on the basis of egocentric observations and that the extraction of features provides an advantage also in problems that do not benefit from dimensionality reduction. Finally, we compare different feature extracting methods and we show that sequence-to-sequence learning outperforms the alternative methods considered in previous studies.
      Competing Interests: The authors have declared that no competing interests exist.
    • References:
      Behav Brain Sci. 2017 Jan;40:e253. (PMID: 27881212)
      Neural Comput. 1997 Nov 15;9(8):1735-80. (PMID: 9377276)
      Evol Comput. 2001 Summer;9(2):159-95. (PMID: 11382355)
      Front Robot AI. 2020 Jul 28;7:98. (PMID: 33501265)
      Neural Netw. 2018 Dec;108:379-392. (PMID: 30268059)
    • Publication Date:
      Date Created: 20210415 Date Completed: 20210924 Latest Revision: 20240331
    • Publication Date:
      20250114
    • Accession Number:
      PMC8049238
    • Accession Number:
      10.1371/journal.pone.0250040
    • Accession Number:
      33857220