Approximation of Infinite Horizon Discounted Cost Markov Decision Processes

Abstract : 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.
Document type :
Book sections
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00759719
Contributor : François Dufour <>
Submitted on : Sunday, December 2, 2012 - 2:59:31 PM
Last modification on : Monday, January 15, 2018 - 4:10:01 PM

Identifiers

  • HAL Id : hal-00759719, version 1

Collections

Citation

François Dufour, Tomas Prieto-Rumeau. Approximation of Infinite Horizon Discounted Cost Markov Decision Processes. Optimization, Control, and Applications of Stochastic Systems, Birkhäuser, pp.59-76, 2012. ⟨hal-00759719⟩

Share

Metrics

Record views

163