A MINIMUM AVERAGE-VARIANCE IN MARKOV DECISION PROCESSES
Yoshinobu Kadota · Bulletin of informatics and cybernetics · 1997
This paper is concerned with the averagevariance of Markov decision processes with countable states and finite actions. Sufficient conditions will be given to assure that there is a stationary deterministic policy which minimizes the averagevariance in a class of the meanoptimal policies. The class of the policies is detetermined by the quantity of the actions which do not satisfy the meanoptimal equation.