Credibilistic Markov decision processes: The average case

摘要

Using a concept of random fuzzy variables in credibility theory, we formulate a credibilistic model for unichain Markov decision processes under average criteria. And a credibilistically optimal policy is defined and obtained by solving the corresponding non-linear mathematical programming. Also we give a computational example to illustrate the effectiveness of our new model. (C) 2008 Elsevier B.V. All rights reserved.