Sensitive Criteria in Markov Decision Processes with a Borel State Space

  • Alexander Yushkevich
Conference paper
Part of the Operations Research Proceedings book series (ORP, volume 1994)

Summary

The paper considers Markov decision processes with a Borel state space, finite action sets, bounded rewards, and a bounded transition density satisfying a simultaneous Doeblin-type recurrence condition. The existence of stationary strong 0-discount optimal and Blackwell optimal policies is proved. A characterization of those policies in terms of the average optimality equation (the infinite dimensional lexicographical optimality equation, respectively) is given.

This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Blackwell D. Discrete dynamic programming. Ann. Math. Stat. 33 (1962), 719–726.CrossRefGoogle Scholar
  2. [2]
    Veinott A.F. Jr. Discrete dynamic programming with sensitive optimality criteria. Ann. Math. Stat. 40 (1969), 1635–1660.CrossRefGoogle Scholar
  3. [3]
    Sladky K. On the set of optimal controls for Markov chains with rewards. Kybemetika 10 (1974), 350–367.Google Scholar
  4. [4]
    Dekker R. and Hordijk A. Average, sensitive and Blackwell optimal policies in denumerable Markov decision chains with unbounded rewards. Math. Oper. Res. 13 (1988), 395–420.CrossRefGoogle Scholar
  5. [5]
    Cavazos-Cadena R. and Lasserre J.B. Strong 1-optimal stationary policies in denumerable Markov decision processes. System Control Letters 11 (1988), 65–71.CrossRefGoogle Scholar
  6. [6]
    Yushkevich A.A. Blackwell optimal policies in a Markov decision process with a Borel state space. Technical report 94-2, UNC-Chaxlotte, Dept. of Mathematics (submitted to Z. Oper. Res.).Google Scholar
  7. [7]
    Yushkevich A.A. Strong 0-discount optimal policies in a Maxkov decision process with a Borel state space. Technical report 94-3, UNC-Charlotte, Dept. of Mathematics.Google Scholar
  8. [8]
    Dynkin E.B. and Yushkevich A.A. Controlled Markov Processes. Springer-Verlag, Berlin-Heidelberg-New York 1979 (Grundlehren der mathematischen Wissenschaften 235).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Alexander Yushkevich
    • 1
  1. 1.CharlotteUSA

Personalised recommendations