Online identification and control of PDEs via reinforcement learning methods
Advances in Computational Mathematics · 2024-08 · 50 (4)
DOI: 10.1007/s10444-024-10167-y ↗Kurz gefasst
Fachartikel in der Zeitschrift Advances in Computational Mathematics, online erschienen am 01.08.2024. Verfasst von Alessandro Alla und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: Gruppo Nazionale per l’Analisi Matematica, la Probabilitá e le loro Applicazioni, Gruppo Nazionale per il Calcolo Scientifico, Ministero dell’Istruzione, dell’Universitá e della Ricerca.
Abstract (Originalsprache)
We focus on the control of unknown partial differential equations (PDEs). The system dynamics is unknown, but we assume we are able to observe its evolution for a given control input, as typical in a reinforcement learning framework. We propose an algorithm based on the idea to control and identify on the fly the unknown system configuration. In this work, the control is based on the state-dependent Riccati approach, whereas the identification of the model on Bayesian linear regression. At each iteration, based on the observed data, we obtain an estimate of the a-priori unknown parameter configuration of the PDE and then we compute the control of the correspondent model. We show by numerical evidence the convergence of the method for infinite horizon control problems.
Förderung
- Gruppo Nazionale per l’Analisi Matematica, la Probabilitá e le loro Applicazioni
- Gruppo Nazionale per il Calcolo Scientifico
- Ministero dell’Istruzione, dell’Universitá e della Ricerca
Zitieren
APA
Alla, A., Pacifico, A., Palladino, M., & Pesare, A. (2024). Online identification and control of PDEs via reinforcement learning methods. Advances in Computational Mathematics, 50(4). https://doi.org/10.1007/s10444-024-10167-y
Vancouver
Alla A, Pacifico A, Palladino M, Pesare A. Online identification and control of PDEs via reinforcement learning methods. Advances in Computational Mathematics. 2024;50(4). doi:10.1007/s10444-024-10167-y
BibTeX
@article{Alla2024,
author = {Alla, Alessandro and Pacifico, Agnese and Palladino, Michele and Pesare, Andrea},
title = {Online identification and control of PDEs via reinforcement learning methods},
journal = {Advances in Computational Mathematics},
year = {2024},
volume = {50},
number = {4},
doi = {10.1007/s10444-024-10167-y}
}
EUVIMED