Computing optimal feedback controls for nonlinear systems generally requires solving Hamilton--Jacobi--Bellman (HJB) equations, which are notoriously difficult when the state …
Computing optimal feedback controls for nonlinear systems generally requires solving Hamilton-Jacobi-Bellman (HJB) equations, which, in high dimensions, are notoriously …
In this letter we propose a new computational method for designing optimal regulators for high-dimensional nonlinear systems. The proposed approach leverages physics-informed …
JY Lee, Y Kim - arXiv preprint arXiv:2406.10920, 2024 - arxiv.org
The framework of deep operator network (DeepONet) has been widely exploited thanks to its capability of solving high dimensional partial differential equations. In this paper, we …
M Zhou, J Han, J Lu - SIAM Journal on Scientific Computing, 2021 - SIAM
We propose a novel numerical method for high dimensional Hamilton--Jacobi--Bellman (HJB) type elliptic partial differential equations (PDEs). The HJB PDEs, reformulated as …
W Cai, S Fang, T Zhou - arXiv preprint arXiv:2405.03169, 2024 - arxiv.org
In this work, we propose a martingale based neural network, SOC-MartNet, for solving high- dimensional Hamilton-Jacobi-Bellman (HJB) equations where no explicit expression is …
Recent research reveals that deep learning is an effective way of solving high dimensional Hamilton–Jacobi–Bellman equations. The resulting feedback control law in the form of a …
JW Kim, BJ Park, H Yoo, JH Lee… - 2018 57th Annual …, 2018 - ieeexplore.ieee.org
Approximate dynamic programming (ADP) aims to obtain an approximate numerical solution to the discrete-time Hamilton-Jacobi-Bellman (HJB) equation. Heuristic dynamic …
Abstract We extend the Deep Galerkin Method (DGM) introduced in Sirignano and Spiliopoulos (2018) to solve a number of partial differential equations (PDEs) that arise in …