Markov decision processes with a minimum-variance criterion (Q1090254): Difference between revisions

The paper considers the optimization of the variance of the sum of costs as well as that of an average expected cost in Markov decision processes with unbounded cost. In case of general state and action space, the stationary policy which makes the average variances as small as possible in the class of policies which are \(\epsilon\)-optimal in an average expected cost is found.