Estimation and control in multichain processes (Q1176867)

From MaRDI portal
scientific article
Language Label Description Also known as
English
Estimation and control in multichain processes
scientific article

    Statements

    Estimation and control in multichain processes (English)
    0 references
    0 references
    0 references
    25 June 1992
    0 references
    The paper considers Markovian decision processes in discrete time with transition probabilities depending on an unknown parameter which may change step by step. In the case of convergence of such a parameter sequence a policy maximizing the average expected reward over an infinite horizon is looked for. Under continuity conditions, the uniform optimality of a policy based on ``estimation and control'' for some multichain models is shown.
    0 references
    adaptive controls
    0 references
    discrete time
    0 references
    average expected reward
    0 references

    Identifiers