Guo, Xianping - In: Mathematical Methods of Operations Research 49 (1999) 1, pp. 87-96
. In this paper, we consider the nonstationary Markov decision processes (MDP, for short) with average variance … provided in this paper, we translate the average variance criterion into a new average expected cost criterion. Then we prove … average variance in the class of optimal policies for the original average expected reward criterion. Copyright Springer …