MARKOV DECISION PROCESSES WITH CONSTRAINTS.

Keith Ross

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

    Abstract

    This article addresses the Markov decision problem with long-run average reward V//u when there is a global constraint to be satisfied: I//u less than equivalent to alpha , where I//u is also a long-run average. Using Lagrange multiplier techniques, existence of an optimal stationary policy is proven. Unlike the unconstrained theory, optimal stationary policies are in general randomized. Structural properties of an optimal policy are determined and the corresponding dynamic programming equations are derived.

    Original languageEnglish (US)
    Title of host publicationUnknown Host Publication Title
    PublisherPrinceton Univ, Dep of Electrical Engineering & Computer Science
    Pages175-179
    Number of pages5
    StatePublished - 1984

    Fingerprint

    Lagrange multipliers
    Dynamic programming
    Structural properties

    ASJC Scopus subject areas

    • Engineering(all)

    Cite this

    Ross, K. (1984). MARKOV DECISION PROCESSES WITH CONSTRAINTS. In Unknown Host Publication Title (pp. 175-179). Princeton Univ, Dep of Electrical Engineering & Computer Science.

    MARKOV DECISION PROCESSES WITH CONSTRAINTS. / Ross, Keith.

    Unknown Host Publication Title. Princeton Univ, Dep of Electrical Engineering & Computer Science, 1984. p. 175-179.

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

    Ross, K 1984, MARKOV DECISION PROCESSES WITH CONSTRAINTS. in Unknown Host Publication Title. Princeton Univ, Dep of Electrical Engineering & Computer Science, pp. 175-179.
    Ross K. MARKOV DECISION PROCESSES WITH CONSTRAINTS. In Unknown Host Publication Title. Princeton Univ, Dep of Electrical Engineering & Computer Science. 1984. p. 175-179
    Ross, Keith. / MARKOV DECISION PROCESSES WITH CONSTRAINTS. Unknown Host Publication Title. Princeton Univ, Dep of Electrical Engineering & Computer Science, 1984. pp. 175-179
    @inproceedings{7dae865d2b0f46ad929fcced9ea22f34,
    title = "MARKOV DECISION PROCESSES WITH CONSTRAINTS.",
    abstract = "This article addresses the Markov decision problem with long-run average reward V//u when there is a global constraint to be satisfied: I//u less than equivalent to alpha , where I//u is also a long-run average. Using Lagrange multiplier techniques, existence of an optimal stationary policy is proven. Unlike the unconstrained theory, optimal stationary policies are in general randomized. Structural properties of an optimal policy are determined and the corresponding dynamic programming equations are derived.",
    author = "Keith Ross",
    year = "1984",
    language = "English (US)",
    pages = "175--179",
    booktitle = "Unknown Host Publication Title",
    publisher = "Princeton Univ, Dep of Electrical Engineering & Computer Science",

    }

    TY - GEN

    T1 - MARKOV DECISION PROCESSES WITH CONSTRAINTS.

    AU - Ross, Keith

    PY - 1984

    Y1 - 1984

    N2 - This article addresses the Markov decision problem with long-run average reward V//u when there is a global constraint to be satisfied: I//u less than equivalent to alpha , where I//u is also a long-run average. Using Lagrange multiplier techniques, existence of an optimal stationary policy is proven. Unlike the unconstrained theory, optimal stationary policies are in general randomized. Structural properties of an optimal policy are determined and the corresponding dynamic programming equations are derived.

    AB - This article addresses the Markov decision problem with long-run average reward V//u when there is a global constraint to be satisfied: I//u less than equivalent to alpha , where I//u is also a long-run average. Using Lagrange multiplier techniques, existence of an optimal stationary policy is proven. Unlike the unconstrained theory, optimal stationary policies are in general randomized. Structural properties of an optimal policy are determined and the corresponding dynamic programming equations are derived.

    UR - http://www.scopus.com/inward/record.url?scp=0021573783&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0021573783&partnerID=8YFLogxK

    M3 - Conference contribution

    SP - 175

    EP - 179

    BT - Unknown Host Publication Title

    PB - Princeton Univ, Dep of Electrical Engineering & Computer Science

    ER -