Interpreting the dual Riccati equation through the LQ reproducing kernel - École des Ponts ParisTech Access content directly
Journal Articles Comptes Rendus. Mathématique Year : 2020

Interpreting the dual Riccati equation through the LQ reproducing kernel

Abstract

In this study, we provide an interpretation of the dual differential Riccati equation of Linear-Quadratic (LQ) optimal control problems. Adopting a novel viewpoint, we show that LQ optimal control can be seen as a regression problem over the space of controlled trajectories, and that the latter has a very natural structure as a reproducing kernel Hilbert space (RKHS). The dual Riccati equation then describes the evolution of the values of the LQ reproducing kernel when the initial time changes. This unveils new connections between control theory and kernel methods, a field widely used in machine learning.
Fichier principal
Vignette du fichier
AUBIN_LQR_Riccati_CRAS.pdf (409.79 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03090198 , version 1 (29-12-2020)

Identifiers

  • HAL Id : hal-03090198 , version 1

Cite

Pierre-Cyril Aubin-Frankowski. Interpreting the dual Riccati equation through the LQ reproducing kernel. Comptes Rendus. Mathématique, In press. ⟨hal-03090198⟩
30 View
72 Download

Share

Gmail Mastodon Facebook X LinkedIn More