Some stages in the implementation of Markov decision processes

The paper is concerned with applicational aspects of discrete random systems. Such systems appear in a large number of practical areas ranging from purely technical to social and demographic systems. For analyzing such systems the models to be used range from purely descriptive models to optimization models. We will use a simplified example to illustrate how the organizational requirements determine the type of models to be used as well as the way in which they should be incorporated in a system to support the decision making process