Number of the records: 1
Identification of Optimal Policies in Markov Decision Processes
- 1.
SYSNO ASEP 0346161 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Identification of Optimal Policies in Markov Decision Processes Author(s) Sladký, Karel (UTIA-B) RID Source Title Kybernetika. - : Ústav teorie informace a automatizace AV ČR, v. v. i. - ISSN 0023-5954
46 2010, č. 3 (2010), s. 558-570Number of pages 13 s. Action International Conference on Mathematical Methods in Economy and Industry Event date 15.06.2009-18.06.2009 VEvent location České Budějovice Country CZ - Czech Republic Event type CST Language eng - English Country CZ - Czech Republic Keywords finite state Markov decision processes ; discounted and average costs ; elimination of suboptimal policies Subject RIV BB - Applied Statistics, Operational Research R&D Projects GA402/08/0107 GA ČR - Czech Science Foundation (CSF) GA402/07/1113 GA ČR - Czech Science Foundation (CSF) CEZ AV0Z10750506 - UTIA-B (2005-2011) UT WOS 000280425000019 Annotation 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. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2011
Number of the records: 1