On strong average optimality of markov decision processes with unbounded costs
- 31 March 1992
- journal article
- research article
- Published by Elsevier in Operations Research Letters
- Vol. 11 (2) , 99-104
- https://doi.org/10.1016/0167-6377(92)90040-a
Abstract
No abstract availableKeywords
This publication has 14 references indexed in Scilit:
- Comparing recent assumptions for the existence of average optimal stationary policiesOperations Research Letters, 1992
- Average cost Markov Decision Processes: Optimality conditionsJournal of Mathematical Analysis and Applications, 1991
- Ergodic and adaptive control of nearest-neighbor motionsMathematics of Control, Signals, and Systems, 1991
- Control of Markov Chains with Long-Run Average Cost Criterion: The Dynamic Programming EquationsSIAM Journal on Control and Optimization, 1989
- Necessary conditions for the optimality equation in average-reward Markov decision processesApplied Mathematics & Optimization, 1989
- On Minimum Cost Per Unit Time Control of Markov ChainsSIAM Journal on Control and Optimization, 1984
- Denumerable Undiscounted Semi-Markov Decision Processes with Unbounded RewardsMathematics of Operations Research, 1983
- On optimality criteria for dynamic programs with long finite horizonsJournal of Mathematical Analysis and Applications, 1980
- A Solution to a Countable System of Equations Arising in Markovian Decision ProcessesThe Annals of Mathematical Statistics, 1967
- Denumerable State Markovian Decision Processes-Average Cost CriterionThe Annals of Mathematical Statistics, 1966