Abstract
In this article we study Markov decision process (MDP) problems with the restriction that at decision epochs, only a finite number of given Markov decision rules are admissible. For example, the set of admissible Markov decision rules D could consist of some easy-implementable decision rules. Additionally, many open-loop control problems can be modeled as an MDP with such a restriction on the admissible decision rules. Within the class of available policies, optimal policies are generally nonstationary and it is difficult to prove that some policy is optimal. We give an example with two admissible decision rules - D={d
Original language | English |
---|---|
Pages (from-to) | 307-342 |
Journal | Probability in the Engineering and Informational Sciences |
Volume | 25 |
Issue number | 3 |
DOIs | |
Publication status | Published - 2011 |