Optimal replacement policy for a Partially Observable Markov Decision Process model

Abstract

The control of deterioration processes for which only incomplete state information is available is examined in this study. When the deterioration is governed by a Markov process, such processes are known as Partially Observable Markov Decision Processes (POMDP) which eliminate the assumption that the state or level of deterioration of the system is known exactly. This research investigates a two state partially observable Markov chain in which only deterioration can occur and for which the only actions possible are to replace or to leave alone. The goal of this research is to develop optimal replacement policies under a new approach which has the potential for solving other problems dealing with continuous state space Markov chains. Finally, computational comparisons are carried out to demonstrate the efficiency of the proposed algorithm.