English
Related papers

Related papers: Stabilized neural Hamilton--Jacobi--Bellman solver…

200 papers

This paper studies the continuous-time reinforcement learning (RL) for optimal switching problems across multiple regimes. We consider a type of exploratory formulation under entropy regularization where the agent randomizes both the timing…

Optimization and Control · Mathematics 2025-12-23 Yijie Huang , Mengge Li , Xiang Yu , Zhou Zhou

A control theoretic approach is presented in this paper for both batch and instantaneous updates of weights in feed-forward neural networks. The popular Hamilton-Jacobi-Bellman (HJB) equation has been used to generate an optimal weight…

Neural and Evolutionary Computing · Computer Science 2015-04-29 Vipul Arora , Laxmidhar Behera , Ajay Pratap Yadav

We present a framework to \emph{certify} Hamilton--Jacobi (HJ) reachability learned by reinforcement learning (RL). Building on a discounted initial time \emph{travel-cost} formulation that makes small-step RL value iteration provably…

Systems and Control · Electrical Eng. & Systems 2026-02-19 Prashant Solanki , Isabelle El-Hajj , Jasper J. van Beers , Erik-Jan van Kampen , Coen C. de Visser

To sidestep the curse of dimensionality when computing solutions to Hamilton-Jacobi-Bellman partial differential equations (HJB PDE), we propose an algorithm that leverages a neural network to approximate the value function. We show that…

Machine Learning · Computer Science 2017-03-28 Frank Jiang , Glen Chou , Mo Chen , Claire J. Tomlin

We study policy iteration (PI) for deterministic infinite-horizon discounted optimal control problems, whose value function is characterized by a stationary Hamilton--Jacobi--Bellman (HJB) equation. At the PDE level, PI is fundamentally…

Optimization and Control · Mathematics 2026-04-14 Namkyeong Cho , Yeoneung Kim

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

This paper presents a physics-informed machine learning approach for synthesizing optimal feedback control policy for infinite-horizon optimal control problems by solving the Hamilton-Jacobi-Bellman (HJB) partial differential equation(PDE).…

Systems and Control · Electrical Eng. & Systems 2025-11-24 Tanay Raghunandan Srinivasa , Suraj Kumar

In this paper, we introduce Hamilton-Jacobi-Bellman (HJB) equations for Q-functions in continuous time optimal control problems with Lipschitz continuous controls. The standard Q-function used in reinforcement learning is shown to be the…

Optimization and Control · Mathematics 2020-05-05 Jeongho Kim , Insoon Yang

Optimal feedback controllers for nonlinear systems can be derived by solving the Hamilton-Jacobi-Bellman (HJB) equation. However, because the HJB is a nonlinear partial differential equation, numerical methods typically provide only…

Optimization and Control · Mathematics 2026-03-25 Morgan Jones , Matthew Peet

In this paper, we present a novel algorithm named synchronous integral Q-learning, which is based on synchronous policy iteration, to solve the continuous-time infinite horizon optimal control problems of input-affine system dynamics. The…

Systems and Control · Electrical Eng. & Systems 2021-05-20 Lei Guo , Han Zhao

Existing reinforcement learning (RL) methods struggle with complex dynamical systems that demand interactions at high frequencies or irregular time intervals. Continuous-time RL (CTRL) has emerged as a promising alternative by replacing…

Machine Learning · Computer Science 2026-02-20 Xuefeng Wang , Lei Zhang , Henglin Pu , Ahmed H. Qureshi , Husheng Li

We propose and analyze a randomization scheme for a general class of impulse control problems. The solution to this randomized problem is characterized as the fixed point of a compound operator which consists of a regularized nonlocal…

Optimization and Control · Mathematics 2026-05-26 Haoyang Cao , Yuchao Dong , Zhouhao Yang

We propose a mesh-free policy iteration framework based on physics-informed neural networks (PINNs) for solving entropy-regularized stochastic control problems. The method iteratively alternates between soft policy evaluation and…

Numerical Analysis · Mathematics 2025-11-18 Yeongjong Kim , Namkyeong Cho , Minseok Kim , Yeoneung Kim

The purpose of this paper is to describe the numerical solution of the Hamilton-Jacobi-Bellman (HJB) for an optimal control problem for quantum spin systems. This HJB equation is a first order nonlinear partial differential equation defined…

Quantum Physics · Physics 2011-10-05 Srinivas Sridharan , Matthew R. James

In this paper, training a neural network is identified, exactly, as a search through Hamilton--Jacobi initial-value problems: each gradient step selects the initial data of a viscous Hamilton--Jacobi equation whose Hopf--Cole propagator…

Machine Learning · Computer Science 2026-05-29 Jose Marie Antonio Miñoza , Erika Fille T. Legara , Christopher P. Monterola

In this paper, we propose Q-learning algorithms for continuous-time deterministic optimal control problems with Lipschitz continuous controls. Our method is based on a new class of Hamilton-Jacobi-Bellman (HJB) equations derived from…

Machine Learning · Computer Science 2020-10-28 Jeongho Kim , Jaeuk Shin , Insoon Yang

We consider a deterministic optimal control problem with a maximum running cost functional, in a finite horizon context, and propose deep neural network approximations for Bellman's dynamic programming principle, corresponding also to some…

Optimization and Control · Mathematics 2022-10-11 Olivier Bokanowski , Xavier Warin , Averil Prost

Maximum entropy reinforcement learning (RL) methods have been successfully applied to a range of challenging sequential decision-making and control tasks. However, most of existing techniques are designed for discrete-time systems. As a…

Optimization and Control · Mathematics 2020-09-29 Jeongho Kim , Insoon Yang

Hamilton-Jacobi (HJ) reachability analysis is a widely used method for ensuring the safety of robotic systems. Traditional approaches compute reachable sets by numerically solving an HJ Partial Differential Equation (PDE) over a grid, which…

Robotics · Computer Science 2025-05-08 Zeyuan Feng , Le Qiu , Somil Bansal

This paper addresses the model-free nonlinear optimal problem with generalized cost functional, and a data-based reinforcement learning technique is developed. It is known that the nonlinear optimal control problem relies on the solution of…

Systems and Control · Computer Science 2013-11-20 Biao Luo , Huai-Ning Wu , Tingwen Huang , Derong Liu