Original title:
The Variance of Discounted Rewards in Markov Decision Processes: Laurent Expansion and Sensitive Optimality
Authors:
Sladký, Karel Document type: Papers Conference/Event: MME 2014. International Conference Mathematical Methods in Economics /32./, Olomouc (CZ), 2014-09-10 / 2014-09-12
Year:
2014
Language:
eng Abstract:
In this paper we consider discounted Markov decision processes with finite state space and compact actions spaces. We present formulas for the variance of total expected discounted rewards along with its partial Laurent expansion. This enables to compare the obtained results with similar results for undiscounted models.
Keywords:
discrete-time Markov decision chains; Laurent expansion; mean-variance optimality; variance of total discounted rewards Project no.: GA13-14445S (CEP), 171396 Funding provider: GA ČR, CONACYT Host item entry: 32nd International Conference Mathematical Methods in Economics MME 2014, ISBN 978-80-244-4209-9