No abstract

No abstract

No abstract

No abstract

We consider the negative dynamic programming mQClel of Strauch [10] and prove that the optimal reward function can be obtained by a transfinite iteration of the optimal reward operator. A departure from all previous treatments of this model is that we allow nonmeasurable policies. We prove that a player loses nothing by restricting himself to measurable policies, if the returns from nonmeasurable policies are evaluated by lower integrals.