On terminating Markov decision processes with a risk-averse objective function (Q5947647)

From MaRDI portal
scientific article; zbMATH DE number 1661399
Language Label Description Also known as
English
On terminating Markov decision processes with a risk-averse objective function
scientific article; zbMATH DE number 1661399

    Statements

    On terminating Markov decision processes with a risk-averse objective function (English)
    0 references
    0 references
    0 references
    17 October 2002
    0 references
    This paper deals with terminating risk-sensitive finite states Markov decision processes with an absorbing and cost-free extra state. So the terminating problem is to seek stochastic shortest paths. Introducing two dynamic programming operators, the author gives the following results. (i) The existence and characterization of an optimal policy. (ii) Convergence properties for value iteration and policy iteration. Moreover, he illustrates the results with two computational examples.
    0 references
    0 references
    risk-sensitive finite states Markov decision processes
    0 references
    terminating problem
    0 references
    stochastic shortest paths
    0 references
    dynamic programming
    0 references
    convergence
    0 references
    value iteration
    0 references
    policy iteration
    0 references

    Identifiers

    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references