Linear quadratic control of nonlinear systems with Koopman operator learning and the Nyström method

In this paper, we study how the Koopman operator framework can be combined with kernel methods to effectively control nonlinear dynamical systems. While kernel methods have typically large computational requirements, we show how random subspaces (Nystr\"om approximation) can be used to achieve...

Descripción completa

Detalles Bibliográficos
Autores: Caldarelli, Edoardo, Chatalic, Antoine, Colomé, Adrià, Molinari, Cesare, Ocampo-Martínez, Carlos, Torras, Carme, Rosasco, Lorenzo
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/396254
Acceso en línea:http://hdl.handle.net/10261/396254
http://arxiv.org/abs/2403.02811v4
Access Level:acceso abierto
Palabra clave:Data-driven methods
Kernel methods
Koopman operator
Linear quadratic regulator
Nyström method
Mathematics - Optimization and Control
cs.SY
eess.SY
Statistics - Machine Learning
Descripción
Sumario:In this paper, we study how the Koopman operator framework can be combined with kernel methods to effectively control nonlinear dynamical systems. While kernel methods have typically large computational requirements, we show how random subspaces (Nystr\"om approximation) can be used to achieve huge computational savings while preserving accuracy. Our main technical contribution is deriving theoretical guarantees on the effect of the Nystr\"om approximation. More precisely, we study the linear quadratic regulator problem, showing that the approximated Riccati operator converges at the rate $m^{-1/2}$, and the regulator objective, for the associated solution of the optimal control problem, converges at the rate $m^{-1}$, where $m$ is the random subspace size. Theoretical findings are complemented by numerical experiments corroborating our results.