A forecast horizon and a stopping rule for general Markov decision processes
- 1 June 1988
- journal article
- Published by Elsevier in Journal of Mathematical Analysis and Applications
- Vol. 132 (2) , 388-400
- https://doi.org/10.1016/0022-247x(88)90069-8
Abstract
No abstract availableThis publication has 5 references indexed in Scilit:
- An on-line procedure in discounted infinite-horizon stochastic optimal controlJournal of Optimization Theory and Applications, 1986
- Denumerable Undiscounted Semi-Markov Decision Processes with Unbounded RewardsMathematics of Operations Research, 1983
- Conditions for the Equivalence of Optimality Criteria in Dynamic ProgrammingThe Annals of Statistics, 1976
- On Two Recent Papers on Ergodicity in Nonhomogeneous Markov ChainsThe Annals of Mathematical Statistics, 1972
- Arbitrary State Markovian Decision ProcessesThe Annals of Mathematical Statistics, 1968