• DocumentCode
    1408274
  • Title

    Finite-Time Performance of Some Two-Armed Bandit Controllers

  • Author

    Witten, Ian H.

  • Author_Institution
    Department of Electrical Engineering Science, University of Essex, Colchester, Essex, England.
  • Issue
    2
  • fYear
    1973
  • fDate
    3/1/1973 12:00:00 AM
  • Firstpage
    194
  • Lastpage
    197
  • Abstract
    A class of asymptotically ¿-optimal two-armed bandit controllers is given, and two criteria for comparing the long-term finite-time performance of controllers in this class are proposed. The performances of three particular controllers are compared using the criteria, and the analysis is confirmed by computer iteration if the appropriate probability recurrence relations.
  • Keywords
    Arm; History; Optimal control; Proportional control; Shape control; Upper bound;
  • fLanguage
    English
  • Journal_Title
    Systems, Man and Cybernetics, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0018-9472
  • Type

    jour

  • DOI
    10.1109/TSMC.1973.5408504
  • Filename
    5408504
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1408274