Number of the records: 1
Second Order Optimality in Transient and Discounted Markov Decision Chains
- 1.
SYSNO ASEP 0448938 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Second Order Optimality in Transient and Discounted Markov Decision Chains Author(s) Sladký, Karel (UTIA-B) RID Number of authors 1 Source Title Procedings of the 33rd International Conference Mathematical Methods in Economics MME 2015. - Plzeň : University of West Bohemia, Plzeň, 2015 - ISBN 978-80-261-0539-8 Pages s. 731-736 Number of pages 6 s. Publication form Print - P Action Mathematical Methods in Economics 2015 /33./ Event date 09.09.2015-11.09.2015 VEvent location Cheb Country CZ - Czech Republic Event type EUR Language eng - English Country CZ - Czech Republic Keywords dynamic programming ; discounted and transient Markov reward chains ; reward-variance optimality Subject RIV BC - Control Systems Theory R&D Projects GA13-14445S GA ČR - Czech Science Foundation (CSF) GA15-10331S GA ČR - Czech Science Foundation (CSF) Institutional support UTIA-B - RVO:67985556 UT WOS 000387898900125 Annotation The article is devoted to second order optimality in Markov decision processes. Attention is primarily focused on the reward variance for discounted models and undiscounted transient models (i.e. where the spectral radius of the transition probability matrix is less than unity). Considering the second order optimality criteria means that in the class of policies maximizing (or minimizing) total expected discounted reward (or undiscounted reward for the transient model) we choose the policy minimizing the total variance. Explicit formulae for calculating the variances for transient and discounted models are reported along with sketches of algoritmic procedures for finding second order optimal policies. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2016
Number of the records: 1