Markovian Decision Processes with Limited State Observability and Unobservable Costs
Abstract
Consider a finite-state finite-action Markovian Decision Process for which the state space has been partitioned into subsets. The decision maker 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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 01, 1972
- Accession Number
- ADA032231
Entities
People
- James D. Steele
Organizations
- RAND Corporation