Počet záznamů: 1

Identification of Optimal Policies in Markov Decision Processes

  1. 1.
    0346161 - UTIA-B 2011 RIV CZ eng J - Článek v odborném periodiku
    Sladký, Karel
    Identification of Optimal Policies in Markov Decision Processes.
    Kybernetika. 46 2010, č. 3 (2010), s. 558-570 ISSN 0023-5954.
    [International Conference on Mathematical Methods in Economy and Industry. České Budějovice, 15.06.2009-18.06.2009]
    Grant CEP: GA ČR(CZ) GA402/08/0107; GA ČR GA402/07/1113
    Výzkumný záměr: CEZ:AV0Z10750506
    Klíčová slova: finite state Markov decision processes * discounted and average costs * elimination of suboptimal policies
    Kód oboru RIV: BB - Aplikovaná statistika, operační výzkum
    Impakt faktor: 0.461, rok: 2010
    http://library.utia.cas.cz/separaty/2010/E/sladky-identification of optimal policies in markov decision processes.pdf http://library.utia.cas.cz/separaty/2010/E/sladky-identification of optimal policies in markov decision processes.pdf

    In this note we focus attention on identifying optimal policies and on elimination suboptimal policies minimizing optimality criteria in discrete-time Markov decision processes with finite state space and compact action set. We present unified approach to value iteration algorithms that enables to generate lower and upper bounds on optimal values, as well as on the current policy. Using the modified value iterations it is possible to eliminate suboptimal actions and to identify an optimal policy or nearly optimal policies in a finite number of steps without knowing precise values of the performance function.
    Trvalý link: http://hdl.handle.net/11104/0187257
    Název souboruStaženoVelikostKomentářVerzePřístup
    0346161.pdf1153 KBVydavatelský postprintpovolen