Online greedy identification of linear dynamical systems - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Online greedy identification of linear dynamical systems

Résumé

This work addresses the problem of exploration in an unknown environment. For multi-input multi-output, linear time-invariant dynamical systems, we use an experimental design framework and introduce an online greedy policy where the control maximizes the information of the next step. We evaluate our approach experimentally and compare it with more elaborate gradient-based methods. In a setting with a limited number of observations, our algorithm has low complexity and shows competitive performances.
Fichier principal
Vignette du fichier
greedy_CDC-2022.pdf (558.31 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03938609 , version 1 (13-01-2023)

Identifiants

Citer

Matthieu Blanke, Marc Lelarge. Online greedy identification of linear dynamical systems. CDC 2022 - 61st Conference on Decision and Control, IEEE, Dec 2022, Cancun, Mexico. pp.5363-5368, ⟨10.1109/CDC51059.2022.9993030⟩. ⟨hal-03938609⟩
37 Consultations
50 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More