Asymptotic properties of constrained Markov decision processes

Abstract : We present in this paper several asymptotic properties of constrained Markov Decision Processes (MDPs) with a countable state space. We treat both the discounted and the expected average cost, with unbounded cost. We are interested in the convergence of finite horizon MDPs to the infinite horizon MDP, convergence of MDPs with a truncated state space to the problem with infinite state space, convergence of MDPs as the discount factor goes to a limit. In all these cases we establish the convergence of optimal values and policies. Moreover, based on the optimal policy for the limiting problem, we construct policies which are almost optimal for the other (approximating) problems.
Type de document :
[Research Report] RR-1598, INRIA. 1992
Liste complète des métadonnées
Contributeur : Rapport de Recherche Inria <>
Soumis le : mercredi 24 mai 2006 - 17:04:49
Dernière modification le : samedi 27 janvier 2018 - 01:31:00
Document(s) archivé(s) le : dimanche 4 avril 2010 - 22:03:40



  • HAL Id : inria-00074962, version 1



Eitan Altman. Asymptotic properties of constrained Markov decision processes. [Research Report] RR-1598, INRIA. 1992. 〈inria-00074962〉



Consultations de la notice


Téléchargements de fichiers