On terminating Markov decision processes with a risk-averse objective function (Q5947647): Difference between revisions

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.