Blackwell optimality in the class of all policies in Markov decision chains with a Borel state space and unbounded rewards

Mathematical Methods of Operations Research

Volumn 50, Issue 3, 1999, Pages 421-448

  Hordijk, Arie ^a   Yushkevich, Alexander A ^b  

^a LEIDEN UNIVERSITY   (Netherlands)

^b UNIVERSITY OF NORTH CAROLINA AT CHARLOTTE   (United States)

Author keywords

Blackwell optimality; Drift and recurrence conditions; Markov decision chains

Indexed keywords

EID: 0000296818     PISSN: 14322994     EISSN: None     Source Type: Journal    
DOI: 10.1007/s001860050079     Document Type: Article

References (17)

1. Dekker R, Hordijk A (1988) Average, sensitive and Blackwell optimal policies in denumerable Markov decision chains with unbounded rewards. Math Oper Res 13:395-420
2. Dekker R, Hordijk A (1992) Recurrence conditions for average and Blackwell optimality in denumerable state Markov decision chains. Math Oper Res 17:271-289
3. Dekker R, Hordijk A, Spieksma FM (1994) On the relation between recurrence and ergodicity properties in denumerable Markov decision chains. Math Oper Res 19:1-21
4. Van Dijk NM, Hordijk A (1996) Time discretization for controlled Markov processes Part II: A jump and diffusion application. Kybernetika (Prague) 32:139-158
5. Dynkin EB, Yushkevich AA (1979) Controlled Markov processes. Springer-Verlag
6. Hernandéz-Lerma O, Montes-de-Oca R, Cavazos-Cadena R (1991) Recurrence conditions for Markov decision processes with Borel state space: a survey. Ann Oper Res 28:29-46
7. Hordijk A, Sladký K (1977) Sensitive optimality criteria in countable state dynamic programming. Math Oper Res 2:1-14
8. Hordijk A, Spieksma FM (1992) On ergodicity and recurrence properties of a Markov chain with an application to an open Jackson network. Adv Appl Prob 24:343-376
9. Hordijk A, Spieksma FM, Tweedie RL (1995) Uniform stability conditions for general space Markov decision processes. Technical report, Leiden University and Colorado State University
10. Hordijk A, Yushkevich AA (1999) Blackwell optimality in the class of stationary policies in Markov decision chains with a Borel state space and unbounded rewards. Math Meth Oper Res 49:1-39
11. Kushner H (1971) Introduction to stochastic control. Holt, New York
12. Meyn SP (1997) The policy improvement algorithm for Markov decision processes with general state space. Transactions on Automatic Control AC-42:191-196
13. Meyn SP, Tweedie RL (1993) Markov chains and stochastic stability. Springer-Verlag
14. Sladký K (1974) On the set of optimal controls for Markov chains with rewards. Kybernetika (Prague) 10:350-367.
15. Strauch RE (1969) Negative dynamic programming. Ann Math Stat 37:871-890
16. Yushkevich AA (1994) Blackwell optimal policies in a Markov decision process with a Borel state space. Z Oper Res 40:253-288
17. Yushkevich AA (1997) Blackwell optimality in Borelian continuous in action Markov decision processes. SIAM J Control 35:2157-2182