Strongly consistent estimation in a controlled Markov renewal model
- 1 September 1982
- journal article
- Published by Cambridge University Press (CUP) in Journal of Applied Probability
- Vol. 19 (3) , 532-545
- https://doi.org/10.2307/3213512
Abstract
The optimal control of dynamic models which are not completely known to the controller often requires some kind of estimation of the unknown parameters. We present conditions under which a minimum contrast estimator will be strongly consistent independently of the control used. This kind of estimator is appropriate for the adaptive or ‘estimation and control' approach in dynamic programming under uncertainty. We consider a countable-state Markov renewal model and we impose bounding and recurrence conditions of the so-called Liapunov type.Keywords
This publication has 10 references indexed in Scilit:
- The average-optimal adaptive control of a Markov renewal model in presence of an unknown parameterMathematische Operationsforschung und Statistik. Series Optimization, 1982
- Gradient approach for recursive estimation and control in finite Markov chainsAdvances in Applied Probability, 1981
- Strong consistency of a modified maximum likelihood estimator for controlled Markov chainsJournal of Applied Probability, 1980
- Stationary Markovian Decision Problems and Perturbation Theory of Quasi-Compact Linear OperatorsMathematics of Operations Research, 1977
- Regenerative Markov decision modelsPublished by Springer Nature ,1976
- On dynamic programming: Compactness of the space of policiesStochastic Processes and their Applications, 1975
- Estimation and control in Markov chainsAdvances in Applied Probability, 1974
- Foundations of Non-stationary Dynamic Programming with Discrete Time ParameterPublished by Springer Nature ,1970
- On the measurability and consistency of minimum contrast estimatesMetrika, 1969
- InequalitiesPublished by Springer Nature ,1961