In this paper we present a data-driven approach for synthesizing optimal switching controllers directly from experimental data, without the need of a global model of the dynamics of the process. The set of controllers and the switching law are learned by using a coordinate descent strategy: for a fixed switching law, the controllers are sequentially optimized by using stochastic gradient descent iterations, while for fixed controllers the switching law is iteratively refined by unsupervised learning. We report examples showing that the approach performs well when applied to control processes characterized by hybrid or nonlinear dynamics, outperforming control laws that are single-mode (no switching) or multi-mode but with the switching law defined a priori.

Learning optimal switching feedback controllers from data

Ferrarotti L.;Bemporad A.
2020-01-01

Abstract

In this paper we present a data-driven approach for synthesizing optimal switching controllers directly from experimental data, without the need of a global model of the dynamics of the process. The set of controllers and the switching law are learned by using a coordinate descent strategy: for a fixed switching law, the controllers are sequentially optimized by using stochastic gradient descent iterations, while for fixed controllers the switching law is iteratively refined by unsupervised learning. We report examples showing that the approach performs well when applied to control processes characterized by hybrid or nonlinear dynamics, outperforming control laws that are single-mode (no switching) or multi-mode but with the switching law defined a priori.
2020
Consensus and reinforcement learning control
Machine learning
Optimal control of hybrid systems
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S2405896320328597-main (1).pdf

non disponibili

Tipologia: Versione Editoriale (PDF)
Licenza: Nessuna licenza
Dimensione 642.23 kB
Formato Adobe PDF
642.23 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11771/20220
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
social impact