• DocumentCode
    2276985
  • Title

    Non-randomized control of constrained Markov decision processes

  • Author

    Chen, Richard C. ; Feinberg, Eugene A.

  • Author_Institution
    Radar Div., Naval Res. Lab., Washington, DC
  • fYear
    2006
  • fDate
    14-16 June 2006
  • Abstract
    This paper presents results concerning the optimal control of constrained Markov decision processes with expected-cost criteria using non-randomized policies. A dynamic programming approach is used to construct optimal policies. The convergence of the finite horizon value function to the infinite horizon value function is also shown. A simple example application is presented
  • Keywords
    Markov processes; dynamic programming; optimal control; constrained Markov decision processes; dynamic programming; infinite horizon value function; nonrandomized control; optimal control; Control systems; Convergence; Cost function; Dynamic programming; Equations; Infinite horizon; Minimax techniques; Optimal control; Process control; Radar;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    American Control Conference, 2006
  • Conference_Location
    Minneapolis, MN
  • Print_ISBN
    1-4244-0209-3
  • Electronic_ISBN
    1-4244-0209-3
  • Type

    conf

  • DOI
    10.1109/ACC.2006.1656446
  • Filename
    1656446
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2276985