UNIFORMIZATION FOR SEMI-MARKOV DECISION PROCESSES UNDER STATIONARY POLICIES.

Frederick J. Beutler, Keith Ross

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Summary form only given. Uniformization permits the replacement of a semi-Markov decision process (SMDP) by a Markov chain exhibiting the same average rewards for simple (nonrandomized) policies. However, uniformization can be accepted as valid only for simple policies. Uniformization is generalized to yield consistent results for stationary policies also. These results are applied to constrained optimization of SMDP, in which stationary (randomized) policies appear naturally.

    Original languageEnglish (US)
    Title of host publicationUnknown Host Publication Title
    PublisherIEEE
    Pages86
    Number of pages1
    StatePublished - 1986

    Fingerprint

    Constrained optimization
    Markov processes

    ASJC Scopus subject areas

    • Engineering(all)

    Cite this

    Beutler, F. J., & Ross, K. (1986). UNIFORMIZATION FOR SEMI-MARKOV DECISION PROCESSES UNDER STATIONARY POLICIES. In Unknown Host Publication Title (pp. 86). IEEE.

    UNIFORMIZATION FOR SEMI-MARKOV DECISION PROCESSES UNDER STATIONARY POLICIES. / Beutler, Frederick J.; Ross, Keith.

    Unknown Host Publication Title. IEEE, 1986. p. 86.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Beutler, FJ & Ross, K 1986, UNIFORMIZATION FOR SEMI-MARKOV DECISION PROCESSES UNDER STATIONARY POLICIES. in Unknown Host Publication Title. IEEE, pp. 86.
    Beutler FJ, Ross K. UNIFORMIZATION FOR SEMI-MARKOV DECISION PROCESSES UNDER STATIONARY POLICIES. In Unknown Host Publication Title. IEEE. 1986. p. 86
    Beutler, Frederick J. ; Ross, Keith. / UNIFORMIZATION FOR SEMI-MARKOV DECISION PROCESSES UNDER STATIONARY POLICIES. Unknown Host Publication Title. IEEE, 1986. pp. 86
    @inproceedings{467a5cc8f0a6474d849688e8cf7f525b,
    title = "UNIFORMIZATION FOR SEMI-MARKOV DECISION PROCESSES UNDER STATIONARY POLICIES.",
    abstract = "Summary form only given. Uniformization permits the replacement of a semi-Markov decision process (SMDP) by a Markov chain exhibiting the same average rewards for simple (nonrandomized) policies. However, uniformization can be accepted as valid only for simple policies. Uniformization is generalized to yield consistent results for stationary policies also. These results are applied to constrained optimization of SMDP, in which stationary (randomized) policies appear naturally.",
    author = "Beutler, {Frederick J.} and Keith Ross",
    year = "1986",
    language = "English (US)",
    pages = "86",
    booktitle = "Unknown Host Publication Title",
    publisher = "IEEE",

    }

    TY - GEN

    T1 - UNIFORMIZATION FOR SEMI-MARKOV DECISION PROCESSES UNDER STATIONARY POLICIES.

    AU - Beutler, Frederick J.

    AU - Ross, Keith

    PY - 1986

    Y1 - 1986

    N2 - Summary form only given. Uniformization permits the replacement of a semi-Markov decision process (SMDP) by a Markov chain exhibiting the same average rewards for simple (nonrandomized) policies. However, uniformization can be accepted as valid only for simple policies. Uniformization is generalized to yield consistent results for stationary policies also. These results are applied to constrained optimization of SMDP, in which stationary (randomized) policies appear naturally.

    AB - Summary form only given. Uniformization permits the replacement of a semi-Markov decision process (SMDP) by a Markov chain exhibiting the same average rewards for simple (nonrandomized) policies. However, uniformization can be accepted as valid only for simple policies. Uniformization is generalized to yield consistent results for stationary policies also. These results are applied to constrained optimization of SMDP, in which stationary (randomized) policies appear naturally.

    UR - http://www.scopus.com/inward/record.url?scp=0022952777&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0022952777&partnerID=8YFLogxK

    M3 - Conference contribution

    SP - 86

    BT - Unknown Host Publication Title

    PB - IEEE

    ER -