Constrained Markov Decision Chains.
Abstract
Consider a finite state and action discrete time parameter Markov decision chains. The objective is to provide an algorithm for finding a policy that minimizes the long run expected average cost when there are linear side conditions on the limit points of the expected state-action frequencies. This problem has been solved previously only for the case where every deterministic stationary policy has at most one ergodic class. The note removes that restriction by applying the Dantzig-Wolfe decomposition principle. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 22, 1971
- Accession Number
- AD0737644
Entities
People
- Arthur F. Veinott Jr.
- Cyrus Derman
Organizations
- Stanford University