English
Related papers

Related papers: Data-driven initialization of deep learning solver…

200 papers

The objective of designing a control system is to steer a dynamical system with a control signal, guiding it to exhibit the desired behavior. The Hamilton-Jacobi-Bellman (HJB) partial differential equation offers a framework for optimal…

Machine Learning · Computer Science 2025-10-22 Jostein Barry-Straume , Adwait D. Verulkar , Arash Sarshar , Andrey A. Popov , Adrian Sandu

We introduce a new numerical method to approximate the solution of a finite horizon deterministic optimal control problem. We exploit two Hamilton-Jacobi-Bellman PDE, arising by considering the dynamics in forward and backward time. This…

Optimization and Control · Mathematics 2023-04-21 Marianne Akian , Stéphane Gaubert , Shanqing Liu

We present a semi-real-time algorithm for minimal-time optimal path planning based on optimal control theory, dynamic programming, and Hamilton-Jacobi (HJ) equations. Partial differential equation (PDE) based optimal path planning methods…

Optimization and Control · Mathematics 2023-09-06 Christian Parkinson , Kyle Polage

In this paper we establish a connection between non-convex optimization methods for training deep neural networks and nonlinear partial differential equations (PDEs). Relaxation techniques arising in statistical physics which have already…

Machine Learning · Computer Science 2017-06-05 Pratik Chaudhari , Adam Oberman , Stanley Osher , Stefano Soatto , Guillaume Carlier

Recent results in the study of the Hamilton Jacobi Bellman (HJB) equation have led to the discovery of a formulation of the value function as a linear Partial Differential Equation (PDE) for stochastic nonlinear systems with a mild…

Optimization and Control · Mathematics 2014-02-13 Matanya B. Horowitz , Joel W. Burdick

This paper applies a reinforcement learning (RL) method to solve infinite horizon continuous-time stochastic linear quadratic problems, where drift and diffusion terms in the dynamics may depend on both the state and control. Based on…

Optimization and Control · Mathematics 2021-09-17 Na Li , Xun Li , Jing Peng , Zuo Quan Xu

Uncertainty quantification (UQ) in scientific machine learning (SciML) combines the powerful predictive power of SciML with methods for quantifying the reliability of the learned models. However, two major challenges remain: limited…

Machine Learning · Computer Science 2024-04-16 Zongren Zou , Tingwei Meng , Paula Chen , Jérôme Darbon , George Em Karniadakis

In this paper we study a class of HJB equations which solve for equilibria for general time-inconsistent deterministic linear quadratic control problems within the intra-personal game theoretic framework, where the inconsistency arises from…

Optimization and Control · Mathematics 2025-05-21 Yunfei Peng , Wei Wei

We address the problem of computing a control for a time-dependent nonlinear system to reach a target set in a minimal time. To solve this minimal time control problem, we introduce a hierarchy of linear semi-infinite programs, the values…

Optimization and Control · Mathematics 2023-07-04 Antoine Oustry , Matteo Tacchi

Developing algorithms for solving high-dimensional partial differential equations (PDEs) has been an exceedingly difficult task for a long time, due to the notoriously difficult problem known as the "curse of dimensionality". This paper…

Numerical Analysis · Mathematics 2020-07-17 Jiequn Han , Arnulf Jentzen , Weinan E

We present a novel direct data-driven algorithm that learns an optimal control policy for the Bilinear Biquadratic Regulator (BBR) for an unknown bilinear system. The BBR is difficult to solve owing to the presence of the nonlinear…

Systems and Control · Electrical Eng. & Systems 2024-10-10 Shanelle G. Clarke , Omanshu Thapliyal , Inseok Hwang

The method of generalized Hamilton-Jacobi-Bellman equations (GHJB) is a powerful way of creating near-optimal controllers by learning. It is based on the fact that if we have a feedback controller, and we learn to compute the gradient…

Optimization and Control · Mathematics 2009-08-21 Douglas Tweed

We propose a supervised learning scheme for the first order Hamilton--Jacobi PDEs in high dimensions. The scheme is designed by using the geometric structure of Wasserstein Hamiltonian flows via a density coupling strategy. It is…

Numerical Analysis · Mathematics 2025-11-05 Jianbo Cui , Shu Liu , Haomin Zhou

We mathematically analyze and numerically study an actor-critic machine learning algorithm for solving high-dimensional Hamilton-Jacobi-Bellman (HJB) partial differential equations from stochastic control theory. The architecture of the…

Optimization and Control · Mathematics 2026-05-20 Samuel N. Cohen , Jackson Hebner , Deqing Jiang , Justin Sirignano

An optimized variant of the State Dependent Riccati Equations (SDREs) approach for nonlinear optimal feedback stabilization is presented. The proposed method is based on the construction of equivalent semilinear representations associated…

Optimization and Control · Mathematics 2022-07-20 Sergey Dolgov , Dante Kalise , Luca Saluzzi

Solving high-dimensional parabolic partial differential equations (PDEs) with deep learning methods is often computationally and memory intensive, primarily due to the need for automatic differentiation (AD) to compute large Hessian…

Numerical Analysis · Mathematics 2026-01-13 Wei Cai , Shuixin Fang , Tao Zhou

In this paper, we introduce a reduced order model-based reinforcement learning (MBRL) approach, utilizing the Iterative Linear Quadratic Regulator (ILQR) algorithm for the optimal control of nonlinear partial differential equations (PDEs).…

Systems and Control · Electrical Eng. & Systems 2025-01-14 Aayushman Sharma , Suman Chakravorty

Surrogate modeling and uncertainty quantification tasks for PDE systems are most often considered as supervised learning problems where input and output data pairs are used for training. The construction of such emulators is by definition a…

Computational Physics · Physics 2019-06-26 Yinhao Zhu , Nicholas Zabaras , Phaedon-Stelios Koutsourelakis , Paris Perdikaris

Hamilton-Jacobi (HJ) reachability analysis is an important formal verification method for guaranteeing performance and safety properties of dynamical control systems. Its advantages include compatibility with general nonlinear system…

Robotics · Computer Science 2020-11-05 Somil Bansal , Claire Tomlin

Considering that the decision-making environment faced by reinforcement learning (RL) agents is full of Knightian uncertainty, this paper describes the exploratory state dynamics equation in Knightian uncertainty to study the…

Optimization and Control · Mathematics 2026-01-27 Ziyu Li , Chen Fei , Weiyin Fei