Variability sensitive Markov decision processes

Melike Baykal-Gursoy, Keith W. Ross

    Research output: Contribution to journalConference articlepeer-review


    Time-average Markov decision processes with finite state and action spaces are considered. Several definitions of variability are introduced and compared. It is shown that a stationary policy maximizes one of these criteria, namely, the expected long-run average variability. An algorithm that produces such an optimal stationary policy is given.

    Original languageEnglish (US)
    Pages (from-to)1261-1262
    Number of pages2
    JournalProceedings of the IEEE Conference on Decision and Control
    StatePublished - 1989
    EventProceedings of the 28th IEEE Conference on Decision and Control. Part 2 (of 3) - Tampa, FL, USA
    Duration: Dec 13 1989Dec 15 1989

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Modeling and Simulation
    • Control and Optimization


    Dive into the research topics of 'Variability sensitive Markov decision processes'. Together they form a unique fingerprint.

    Cite this