Communication Dans Un Congrès Année : 2024

Policy iteration for discrete-time systems with discounted costs: stability and near-optimality guarantees

Résumé

Given a discounted cost, we study deterministic discrete-time systems whose inputs are generated by policy iteration (PI). We provide novel near-optimality and stability properties, while allowing for non-stabilizing initial policies. That is, we first give novel bounds on the mismatch between the value function generated by PI and the optimal value function, which are less conservative in general than those encountered in the dynamic programming literature for the considered class of systems. Then, we show that the systems in closed-loop with policies generated by PI are stabilizing under mild conditions, after a finite (and known) number of iterations.

Fichier principal
Vignette du fichier
CDC24 - final version.pdf (355.55 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04736076 , version 1 (14-10-2024)

Licence

Identifiants

  • HAL Id : hal-04736076 , version 1

Citer

Jonathan de Brusse, Mathieu Granzotto, Romain Postoyan, Dragan Nesic. Policy iteration for discrete-time systems with discounted costs: stability and near-optimality guarantees. 63rd IEEE Conference on Decision and Control, CDC 2024, Dec 2024, Milan, Italy. ⟨hal-04736076⟩
183 Consultations
170 Téléchargements

Partager

  • More