La plateforme OSKAR Bordeaux évolue pour rejoindre l'archive ouverte HAL. Retrouvez tous vos dépôts sur le nouveau portail HAL UB : https://u-bordeaux.hal.science/. Pour toute aide ou information, contactez-nous info@oskar-bordeaux.fr
Conditions for the Solvability of the Linear Programming Formulation for Constrained Discounted Markov Decision Processes
Langue
en
Article de revue
Ce document a été publié dans
Applied Mathematics and Optimization. 2016, vol. 74, n° 1, p. 27 - 51
Springer Verlag (Germany)
Résumé en anglais
We consider a discrete-time constrained discounted Markov decision process (MDP) with Borel state and action spaces, compact action sets, and lower semi-continuous cost functions. We introduce a set of hypotheses related ...Lire la suite >
We consider a discrete-time constrained discounted Markov decision process (MDP) with Borel state and action spaces, compact action sets, and lower semi-continuous cost functions. We introduce a set of hypotheses related to a positive weight function which allow us to consider cost functions that might not be bounded below by a constant, and which imply the solvability of the linear programming formulation of the constrained MDP. In particular, we establish the existence of a constrained optimal stationary policy. Our results are illustrated with an application to a fishery management problem.< Réduire
Mots clés en anglais
Constrained problems
Linear programming formulation
Markov decision processes
Origine
Importé de halUnités de recherche