Consider a finite-state, finite-action Markovian Decision Process for which the state space has been partitioned into subsets. The decisionmaker can only observe the subset to which the states of the process belong, and not the actual states of the process. In addition, the costs are unobservable in the sense that the total discounted cost is to be assessed at infinity. An approach to this problem, which makes use of the probability distributions over the state space, is developed. 13 pp. Bibliog.
This report is part of the RAND Corporation paper series. The paper was a product of the RAND Corporation from 1948 to 2003 that captured speeches, memorials, and derivative research, usually prepared on authors' own time and meant to be the scholarly or scientific contribution of individual authors to their professional fields. Papers were less formal than reports and did not require rigorous peer review.
The RAND Corporation is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.