Open Access
Translator Disclaimer
March, 1975 Markov Decision Processes with a New Optimality Criterion: Continuous Time
Stratton C. Jaquette
Ann. Statist. 3(2): 547-553 (March, 1975). DOI: 10.1214/aos/1176343087


Standard finite state and action continuous time Markov decision processes with discounting are studied using a new optimality criterion called moment optimality. A policy is moment optimal if it lexicographically maximizes the sequence of signed moments of total discounted return with a positive (negative) sign if the moment is odd (even). It is shown constructively that a stationary policy is moment optimal among the class of piecewise constant policies by examining the negative of the Laplace transform of the total return random variable and its Taylor series expansion.


Download Citation

Stratton C. Jaquette. "Markov Decision Processes with a New Optimality Criterion: Continuous Time." Ann. Statist. 3 (2) 547 - 553, March, 1975.


Published: March, 1975
First available in Project Euclid: 12 April 2007

zbMATH: 0321.90051
MathSciNet: MR363493
Digital Object Identifier: 10.1214/aos/1176343087

Primary: 90B99
Secondary: 60J25 , 90B99 , 90C40 , 93E20

Keywords: dynamic programming , Markov decision processes , moments of return , optimality criterion

Rights: Copyright © 1975 Institute of Mathematical Statistics


Vol.3 • No. 2 • March, 1975
Back to Top