Approximation of Infinite Horizon Discounted Cost Markov Decision Processes
DUFOUR, François
Institut de Mathématiques de Bordeaux [IMB]
Quality control and dynamic reliability [CQFD]
Institut de Mathématiques de Bordeaux [IMB]
Quality control and dynamic reliability [CQFD]
DUFOUR, François
Institut de Mathématiques de Bordeaux [IMB]
Quality control and dynamic reliability [CQFD]
< Réduire
Institut de Mathématiques de Bordeaux [IMB]
Quality control and dynamic reliability [CQFD]
Langue
en
Chapitre d'ouvrage
Ce document a été publié dans
Optimization, Control, and Applications of Stochastic Systems, Optimization, Control, and Applications of Stochastic Systems. 2012p. 59-76
Birkhäuser
Résumé en anglais
In this work, we deal with a discrete-time infinite horizon Markov decision process with locally compact Borel state and action spaces, and possibly unbounded cost function. Based on Lipschitz continuity of the elements ...Lire la suite >
In this work, we deal with a discrete-time infinite horizon Markov decision process with locally compact Borel state and action spaces, and possibly unbounded cost function. Based on Lipschitz continuity of the elements of the control model, we propose a state and action discretization procedure for approximating the optimal value function and an optimal policy of the original control model. We provide explicit bounds on the approximation errors.< Réduire
Origine
Importé de halUnités de recherche