Imperial College London
Portrait Picture

Dr Dante Kalise

Faculty of Natural Sciences, Department of Mathematics

Reader in Computational Optimisation and Control
 
 
 
//

Contact

 

d.kalise-balza Website CV

 
 
//

Location

 

742Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Albi:2021:10.1109/LCSYS.2021.3086697,
author = {Albi, G and Bicego, S and Kalise, D},
doi = {10.1109/LCSYS.2021.3086697},
journal = {IEEE Control Systems Letters},
pages = {836--841},
title = {Gradient-augmented supervised learning of optimal feedback laws using state-dependent Riccati equations},
url = {http://dx.doi.org/10.1109/LCSYS.2021.3086697},
volume = {6},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - A supervised learning approach for the solution of large-scale nonlinear stabilization problems is presented. A stabilizing feedback law is trained from a dataset generated from State-dependent Riccati Equation solvers. The training phase is enriched by the use of gradient information in the loss function, which is weighted through the use of hyperparameters. High-dimensional nonlinear stabilization tests demonstrate that real-time sequential large-scale Algebraic Riccati Equation solvers can be substituted by a suitably trained feedforward neural network.
AU  - Albi,G
AU  - Bicego,S
AU  - Kalise,D
DO  - 10.1109/LCSYS.2021.3086697
EP  - 841
PY  - 2021///
SN  - 2475-1456
SP  - 836
TI  - Gradient-augmented supervised learning of optimal feedback laws using state-dependent Riccati equations
T2  - IEEE Control Systems Letters
UR  - http://dx.doi.org/10.1109/LCSYS.2021.3086697
UR  - http://hdl.handle.net/10044/1/90900
VL  - 6
ER  -
Download