Number of the records: 1
Constrained Risk-Sensitive Markov Decision Chains
- 1.
SYSNO ASEP 0326474 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Constrained Risk-Sensitive Markov Decision Chains Title Markovské rozhodovací procesy s omezeními za rizika Author(s) Sladký, Karel (UTIA-B) RID Source Title Operations Research Proceedings 2008. - Berlin : Springer, 2009 / Fleischmann B. ; Borgwardt K. H. ; Klein R. ; Tuma A. - ISBN 978-3-642-00141-3 Pages s. 363-368 Number of pages 6 s. Action Operations Research 2008 Event date 03.09.2008-05.09.2008 VEvent location Augsburg Country DE - Germany Event type EUR Language eng - English Country DE - Germany Keywords Markov decision chains ; exponential utility functions ; constraints 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) Annotation For a classical Markov decision chain we suppose that the streams of transition rewards are evaluated by an exponential utility function. Attention is focused on the asymptotic properties of the expected utility and the corresponding certainty equivalents if the optimal values considered with respect to transition rewards must fulfill certain additional constraint on the expected utility or the certainty equivalent generated by different transition rewards. Our analysis is based policy iterations applied on a collection of nonnegative matrices arising in the recursive formulas for the growth of expected utilities. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2010
Number of the records: 1