Access the full text.
Sign up today, get DeepDyve free for 14 days.
Loading next page...
/lp/springer-journals/existence-of-optimal-stationary-policies-in-average-reward-markov-gWdcqwRyyZ
References (16)
-
Sheldon Ross (1982)
Stochastic Processes -
W. Rudin (1964)
Principles of mathematical analysis -
H. L. Royden (1968)
Real Analysis -
J. Munkres (1974)
Topology; a first course -
R. Cavazos-Cadena (1988)
Necessary and sufficient conditions for a bounded solution to the optimality equation in average reward Markov decision chainsSystems & Control Letters, 10
-
(1983)
Introduction to Stochastic Dynamic Programming -
L. C. Thomas (1980)
Recent Developments in Markov Decision Processes -
R. Cavazos-Cadena (1989)
Necessary conditions for the optimality equation in average-reward Markov decision processesApplied Mathematics and Optimization, 19
-
D. Heyman, M. Sobel (1982)
Stochastic models in operations research -
D. Heyman, M. Sobel (1984)
Stochastic Models in Operations Research, Vol. II -
L. Sennott (1986)
A new condition for the existence of optimal stationary policies in average cost Markov decision processesOperations Research Letters, 5
-
R. Ash, E. Lukács, Z. Birnbaum (1975)
Real analysis and probabilityAmerican Mathematical Monthly, 82
-
K. Hinderer (1970)
Foundations of Non-stationary Dynamic Programming with Discrete Time Parameter -
James Flynn (1976)
Conditions for the Equivalence of Optimality Criteria in Dynamic ProgrammingAnnals of Statistics, 4
-
(1992)
Applied Probability Models with Optimization Applications -
J. Baras, A. Dorsey, A. Makowski (1984)
Stability, parameter estimation and adaptive control for discrete-time competing queuesThe 23rd IEEE Conference on Decision and Control
- Publisher
- Springer Journals
- Copyright
- Copyright © 1992 by Springer-Verlag New York Inc.
- Subject
- Mathematics; Calculus of Variations and Optimal Control; Optimization; Systems Theory, Control; Theoretical, Mathematical and Computational Physics; Mathematical Methods in Physics; Numerical and Computational Physics, Simulation
- ISSN
- 0095-4616
- eISSN
- 1432-0606
- DOI
- 10.1007/BF01189029
- Publisher site
- See Article on Publisher Site
Abstract
We consider discrete-timeaverage reward Markov decision processes with denumerable state space andbounded reward function. Under structural restrictions on the model the existence of an optimal stationary policy is proved; both the lim inf and lim sup average criteria are considered. In contrast to the usual approach our results donot rely on the average regard optimality equation. Rather, the arguments are based on well-known facts fromRenewal Theory.
Journal
Applied Mathematics and Optimization – Springer Journals
Published: Feb 2, 2005