AN ALGORITHM FOR DETERMINING STATIONARY OPTIMAL STRATEGIES FOR STOCHASTIC DISCRETE OPTIMAL CONTROL PROBLEMS DEFINED ON NETWORKS WITH MULTIPLE RECURRENT CLASSES

Maria CAPCELEA, Titu CAPCELEA Universitatea de Stat din Moldova

Аннотация

An efficient algorithm for determining optimal stationary strategies for the stochastic discrete optimal control problems with infinite time horizon is developed and theoretically justified. The problems are defined on decision networks with multiple recurrent classes. The average costs convex combination optimization criterion is applied. We examine problems in which the costs of transitions between the states of the dynamic system and transition probabilities, defined on the uncontrollable states, are constants independent on time. The algorithm is based on the linear programming model developed for determining optimal strategies in control problems defined on perfect decision networks [3,4]. Keywords: discrete processes, stochastic discrete optimal control problem, multichain networks, stationary strategies, linear programming approach, polynomial time algorithm.