ROBUSTNESS INEQUALITY FOR MARKOV CONTROL PROCESSES WITH UNBOUNDED COSTS

The paper discusses the robustness of discrete-time Markov control pro cesses whose transition probabilities are known up to certain degree o f accuracy. Upper bounds of increase of a discounted cost are derived when using an optimal control policy of the approximating process in o rder to control the original one. Bounds are given in terms of weighte d total variation distance between transition probabilities. They hold for processes on Borel spaces with unbounded one-stage costs function s. (C) 1998 Elsevier Science B.V. All rights reserved.