Chapter 8 Markov decision processes
Author:
- Martin L. PutermanMPMartin L. Puterman
- 1 January 1990
- book chapter
- Published by Elsevier
- p. 331-434
Abstract
No abstract availableThis publication has 93 references indexed in Scilit:
- A unified approach to adaptive control of average reward Markov decision processesOR Spectrum, 1988
- Decision Processes with Total-Cost CriteriaThe Annals of Probability, 1981
- A simple proof of Whittle's bridging condition in dynamic programmingJournal of Applied Probability, 1980
- Stability and characterisation conditions in negative programmingJournal of Applied Probability, 1980
- A simple condition for regularity in negative programmingJournal of Applied Probability, 1979
- Estimation and control in Markov chainsAdvances in Applied Probability, 1974
- Markov Decision Processes with a New Optimality Criterion: Discrete TimeThe Annals of Statistics, 1973
- Denumerable State Markovian Decision Processes-Average Cost CriterionThe Annals of Mathematical Statistics, 1966
- On Finding Optimal Policies in Discrete Dynamic Programming with No DiscountingThe Annals of Mathematical Statistics, 1966
- On the Iterative Method of Dynamic Programming on a Finite Space Discrete Time Markov ProcessThe Annals of Mathematical Statistics, 1965