Data-driven initialization of deep learning solvers for Hamilton-Jacobi-Bellman PDEs

IFAC-PapersOnLine, 2022 - Elsevier
A deep learning approach for the approximation of the Hamilton-Jacobi-Bellman partial
differential equation (HJB PDE) associated to the Nonlinear Quadratic Regulator (NLQR) …

Data-driven initialization of deep learning solvers for Hamilton-Jacobi-Bellman PDEs

A Borovykh, D Kalise, A Laignelet, P Parpas - arXiv preprint arXiv …, 2022 - arxiv.org
A deep learning approach for the approximation of the Hamilton-Jacobi-Bellman partial
differential equation (HJB PDE) associated to the Nonlinear Quadratic Regulator (NLQR) …

Data-driven initialization of deep learning solvers for Hamilton-Jacobi-Bellman PDEs

A Borovykh, D Kalise, A Laignelet, P Parpas - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
A deep learning approach for the approximation of the Hamilton-Jacobi-Bellman partial
differential equation (HJB PDE) associated to the Nonlinear Quadratic Regulator (NLQR) …

[PDF][PDF] Data-driven initialization of deep learning solvers for Hamilton-Jacobi-Bellman PDEs

ABD Kalise, A Laignelet, P Parpas, A Borovykh… - Sciences, 2022 - researchgate.net
Over the last years there has been remarkable progress on the solution of high-dimensional
nonlinear optimal control problems, see eg Dolgov et al.(2021); Onken et al.(2021); Kunisch …