Existence of optimal stationary policies in discounted Markov decision processes: Approaches by occupation measures (Q1327188)

From MaRDI portal
scientific article
Language Label Description Also known as
English
Existence of optimal stationary policies in discounted Markov decision processes: Approaches by occupation measures
scientific article

    Statements

    Existence of optimal stationary policies in discounted Markov decision processes: Approaches by occupation measures (English)
    0 references
    0 references
    15 June 1994
    0 references
    In discounted Markov decision processes with general state and action spaces with bounded Borel measurable cost functions, the occupation measure associated with a sequence of policies is constructed. Without assumptions of continuity or compactness, the existence of optimal stationary Borel measurable policies is demonstrated.
    0 references
    0 references
    general state and action spaces
    0 references
    bounded Borel measurable cost functions
    0 references
    optimal stationary Borel measurable policies
    0 references
    0 references