IDEAS home Printed from https://ideas.repec.org/a/spr/mathme/v71y2010i2p307-323.html
   My bibliography  Save this article

Compactness of the space of non-randomized policies in countable-state sequential decision processes

Author

Listed:
  • Richard Chen
  • Eugene Feinberg

Abstract

For sequential decision processes with countable state spaces, we prove compactness of the set of strategic measures corresponding to nonrandomized policies. For the Borel state case, this set may not be compact (Piunovskiy, Optimal control of random sequences in problems with constraints. Kluwer, Boston, p. 170, 1997) in spite of compactness of the set of strategic measures corresponding to all policies (Schäl, On dynamic programming: compactness of the space of policies. Stoch Processes Appl 3(4):345–364, 1975b; Balder, On compactness of the space of policies in stochastic dynamic programming. Stoch Processes Appl 32(1):141–150, 1989). We use the compactness result from this paper to show the existence of optimal policies for countable-state constrained optimization of expected discounted and nonpositive rewards, when the optimality is considered within the class of nonrandomized policies. This paper also studies the convergence of a value-iteration algorithm for such constrained problems. Copyright Springer-Verlag 2010

Suggested Citation

  • Richard Chen & Eugene Feinberg, 2010. "Compactness of the space of non-randomized policies in countable-state sequential decision processes," Mathematical Methods of Operations Research, Springer;Gesellschaft für Operations Research (GOR);Nederlands Genootschap voor Besliskunde (NGB), vol. 71(2), pages 307-323, April.
    • Handle: RePEc:spr:mathme:v:71:y:2010:i:2:p:307-323
    DOI: 10.1007/s00186-009-0298-1
    as

    Download full text from publisher

    File URL: http://hdl.handle.net/10.1007/s00186-009-0298-1
    Download Restriction: Access to full text is restricted to subscribers.
    File URL: https://libkey.io/10.1007/s00186-009-0298-1?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Balder, Erik J., 1989. "On compactness of the space of policies in stochastic dynamic programming," Stochastic Processes and their Applications, Elsevier, vol. 32(1), pages 141-150, June.
    2. Eugene A. Feinberg & Adam Shwartz, 1996. "Constrained Discounted Dynamic Programming," Mathematics of Operations Research, INFORMS, vol. 21(4), pages 922-945, November.
    3. Richard Chen & Eugene Feinberg, 2007. "Non-randomized policies for constrained Markov decision processes," Mathematical Methods of Operations Research, Springer;Gesellschaft für Operations Research (GOR);Nederlands Genootschap voor Besliskunde (NGB), vol. 66(1), pages 165-179, August.
    4. Eugene A. Feinberg, 2000. "Constrained Discounted Markov Decision Processes and Hamiltonian Cycles," Mathematics of Operations Research, INFORMS, vol. 25(1), pages 130-140, February.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Eugene A. Feinberg & Pavlo O. Kasyanov & Nina V. Zadoianchuk, 2012. "Average Cost Markov Decision Processes with Weakly Continuous Transition Probabilities," Mathematics of Operations Research, INFORMS, vol. 37(4), pages 591-607, November.
    2. Eugene A. Feinberg & Uriel G. Rothblum, 2012. "Splitting Randomized Stationary Policies in Total-Reward Markov Decision Processes," Mathematics of Operations Research, INFORMS, vol. 37(1), pages 129-153, February.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Eugene A. Feinberg & Uriel G. Rothblum, 2012. "Splitting Randomized Stationary Policies in Total-Reward Markov Decision Processes," Mathematics of Operations Research, INFORMS, vol. 37(1), pages 129-153, February.
    2. Vladimir Ejov & Jerzy A. Filar & Michael Haythorpe & Giang T. Nguyen, 2009. "Refined MDP-Based Branch-and-Fix Algorithm for the Hamiltonian Cycle Problem," Mathematics of Operations Research, INFORMS, vol. 34(3), pages 758-768, August.
    3. Ohlmann, Jeffrey W. & Bean, James C., 2009. "Resource-constrained management of heterogeneous assets with stochastic deterioration," European Journal of Operational Research, Elsevier, vol. 199(1), pages 198-208, November.
    4. G. Dorini & F. Pierro & D. Savic & A. Piunovskiy, 2007. "Neighbourhood Search for constructing Pareto sets," Mathematical Methods of Operations Research, Springer;Gesellschaft für Operations Research (GOR);Nederlands Genootschap voor Besliskunde (NGB), vol. 65(2), pages 315-337, April.
    5. Krishnamurthy Iyer & Nandyala Hemachandra, 2010. "Sensitivity analysis and optimal ultimately stationary deterministic policies in some constrained discounted cost models," Mathematical Methods of Operations Research, Springer;Gesellschaft für Operations Research (GOR);Nederlands Genootschap voor Besliskunde (NGB), vol. 71(3), pages 401-425, June.
    6. Lanlan Zhang & Xianping Guo, 2008. "Constrained continuous-time Markov decision processes with average criteria," Mathematical Methods of Operations Research, Springer;Gesellschaft für Operations Research (GOR);Nederlands Genootschap voor Besliskunde (NGB), vol. 67(2), pages 323-340, April.
    7. Armando F. Mendoza-Pérez & Héctor Jasso-Fuentes & Omar A. De-la-Cruz Courtois, 2016. "Constrained Markov decision processes in Borel spaces: from discounted to average optimality," Mathematical Methods of Operations Research, Springer;Gesellschaft für Operations Research (GOR);Nederlands Genootschap voor Besliskunde (NGB), vol. 84(3), pages 489-525, December.
    8. Erik J. Balder, 2001. "On ws-Convergence of Product Measures," Mathematics of Operations Research, INFORMS, vol. 26(3), pages 494-518, August.
    9. Nandyala Hemachandra & Kamma Sri Naga Rajesh & Mohd. Abdul Qavi, 2016. "A model for equilibrium in some service-provider user-set interactions," Annals of Operations Research, Springer, vol. 243(1), pages 95-115, August.
    10. Ali Eshragh & Jerzy Filar & Michael Haythorpe, 2011. "A hybrid simulation-optimization algorithm for the Hamiltonian cycle problem," Annals of Operations Research, Springer, vol. 189(1), pages 103-125, September.
    11. Vivek Borkar & Jerzy Filar, 2013. "Markov chains, Hamiltonian cycles and volumes of convex bodies," Journal of Global Optimization, Springer, vol. 55(3), pages 633-639, March.
    12. Ali Eshragh & Jerzy Filar, 2011. "Hamiltonian Cycles, Random Walks, and Discounted Occupational Measures," Mathematics of Operations Research, INFORMS, vol. 36(2), pages 258-270, May.
    13. Armando Mendoza-Pérez & Onésimo Hernández-Lerma, 2010. "Markov control processes with pathwise constraints," Mathematical Methods of Operations Research, Springer;Gesellschaft für Operations Research (GOR);Nederlands Genootschap voor Besliskunde (NGB), vol. 71(3), pages 477-502, June.
    14. Ali Eshragh & Jerzy A. Filar & Thomas Kalinowski & Sogol Mohammadian, 2020. "Hamiltonian Cycles and Subsets of Discounted Occupational Measures," Mathematics of Operations Research, INFORMS, vol. 45(2), pages 713-731, May.
    15. Guo, Xianping & Zhang, Wenzhao, 2014. "Convergence of controlled models and finite-state approximation for discounted continuous-time Markov decision processes with constraints," European Journal of Operational Research, Elsevier, vol. 238(2), pages 486-496.
    16. Vladimir Ejov & Jerzy A. Filar & Minh-Tuan Nguyen, 2004. "Hamiltonian Cycles and Singularly Perturbed Markov Chains," Mathematics of Operations Research, INFORMS, vol. 29(1), pages 114-131, February.
    17. Balder, Erik J., 2004. "An equilibrium existence result for games with incomplete information and indeterminate outcomes," Journal of Mathematical Economics, Elsevier, vol. 40(3-4), pages 297-320, June.
    18. Kumar, Uday M & Bhat, Sanjay P. & Kavitha, Veeraruna & Hemachandra, Nandyala, 2023. "Approximate solutions to constrained risk-sensitive Markov decision processes," European Journal of Operational Research, Elsevier, vol. 310(1), pages 249-267.
    19. Nelly Litvak & Vladimir Ejov, 2009. "Markov Chains and Optimality of the Hamiltonian Cycle," Mathematics of Operations Research, INFORMS, vol. 34(1), pages 71-82, February.
    20. Guo, Xianping & Ye, Liuer & Yin, George, 2012. "A mean–variance optimization problem for discounted Markov decision processes," European Journal of Operational Research, Elsevier, vol. 220(2), pages 423-429.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:spr:mathme:v:71:y:2010:i:2:p:307-323. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.