ARBITRARY STATE MARKOVIAN DECISION PROCESSES
Abstract
Arbitrary state, finite action Markovian decision processes are studied with respect to the (long-run) average cost criterion. The problem is treated both as a limiting case of the discounted cost problem and also as a limit of the n-stage problem. Sufficient conditions are given for the existence of an optimal rule and for it to be of stationary deterministic type.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 08, 1968
- Accession Number
- AD0664459
Entities
People
- Sheldon M. Ross
Organizations
- Stanford University