English
Related papers

Related papers: A neural network based policy iteration algorithm …

200 papers

We study the policy iteration algorithm (PIA) for entropy-regularized stochastic control problems on an infinite time horizon with a large discount rate, focusing on two main scenarios. First, we analyze PIA with bounded coefficients where…

Optimization and Control · Mathematics 2025-05-28 Hung Vinh Tran , Zhenhua Wang , Yuming Paul Zhang

We study an inverse problem of the stochastic optimal control of general diffusions with performance index having the quadratic penalty term of the control process. Under mild conditions on the system dynamics, the cost functions, and the…

Optimization and Control · Mathematics 2022-11-17 Yumiharu Nakano

For a general entropy-regularized stochastic control problem on an infinite horizon, we prove that a policy iteration algorithm (PIA) converges to an optimal relaxed control. Contrary to the standard stochastic control literature, classical…

Optimization and Control · Mathematics 2026-05-14 Yu-Jui Huang , Zhenhua Wang , Zhou Zhou

Classically, the optimal control problem in the presence of an adversary is formulated as a two-player zero-sum differential game or an $H_\infty$ control problem. The solution to these problems can be obtained by solving the…

Optimization and Control · Mathematics 2022-04-26 Alexander Krolicki , Sarang Sutavani , Umesh Vaidya

The Hamilton Jacobi Bellman Equation (HJB) provides the globally optimal solution to large classes of control problems. Unfortunately, this generality comes at a price, the calculation of such solutions is typically intractible for systems…

Optimization and Control · Mathematics 2014-09-23 Matanya B. Horowitz , Anil Damle , Joel W. Burdick

Stochastic optimal principle leads to the resolution of a partial differential equation (PDE), namely the Hamilton-Jacobi-Bellman (HJB) equation. In general, this equation cannot be solved analytically, thus numerical algorithms are the…

Numerical Analysis · Mathematics 2021-09-14 Christelle Dleuna Nyoumbi , Antoine Tambue

A new algorithm for time dependent Hamilton Jacobi equations on networks, based on semi Lagrangian scheme, is proposed. It is based on the definition of viscosity solution for this kind of problems recently given in. A thorough convergence…

Numerical Analysis · Mathematics 2023-10-11 Elisabetta Carlini , Antonio Siconolfi

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

This paper introduces the Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO) algorithm into reinforcement learning. The Hamilton-Jacobi-Bellman (HJB) equation is used in control theory to evaluate the optimality of the value…

Machine Learning · Computer Science 2023-02-02 Amartya Mukherjee , Jun Liu

We establish a well-posedness and error-estimation framework that solves Hamilton-Jacobi equations by minimizing the least-squares residual of monotone finite-difference discretizations. This approach also applies naturally to second-order…

Numerical Analysis · Mathematics 2026-05-13 Olivier Bokanowski , Carlos Esteve-Yagüe , Richard Tsai

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 examine the problem of two-point boundary optimal control of nonlinear systems over finite-horizon time periods with unknown model dynamics by employing reinforcement learning. We use techniques from singular perturbation theory to…

Optimization and Control · Mathematics 2023-06-12 Vasanth Reddy , Hoda Eldardiry , Almuatazbellah Boker

In this article we study a finite horizon optimal control problem with monotone controls. We consider the associated Hamilton-Jacobi-Bellman (HJB) equation which characterizes the value function. We consider the totally discretized problem…

Optimization and Control · Mathematics 2014-07-08 Eduardo A. Philipp , Laura S. Aragone , Lisandro A. Parente

Solving the Hamilton-Jacobi-Bellman equation is important in many domains including control, robotics and economics. Especially for continuous control, solving this differential equation and its extension the Hamilton-Jacobi-Isaacs…

Robotics · Computer Science 2021-10-06 Michael Lutter , Boris Belousov , Shie Mannor , Dieter Fox , Animesh Garg , Jan Peters

An optimal control problem is considered for a stochastic differential equation containing a state-dependent regime switching, with a recursive cost functional. Due to the non-exponential discounting in the cost functional, the problem is…

Optimization and Control · Mathematics 2017-12-29 Hongwei Mei , Jiongmin Yong

We propose a novel numerical method for high dimensional Hamilton--Jacobi--Bellman (HJB) type elliptic partial differential equations (PDEs). The HJB PDEs, reformulated as optimal control problems, are tackled by the actor-critic framework…

Optimization and Control · Mathematics 2022-01-07 Mo Zhou , Jiequn Han , Jianfeng Lu

We study a stochastic optimal control problem with the state constrained to a smooth, compact domain. The control influences both the drift and a possibly degenerate, control-dependent dispersion matrix, leading to a fully nonlinear,…

Optimization and Control · Mathematics 2025-08-08 Anderson O. Calixto , Bernardo Freitas Paulo da Costa , Glauco Valle

In this paper we study a first extension of the theory of mild solutions for HJB equations in Hilbert spaces to the case when the domain is not the whole space. More precisely, we consider a half-space as domain, and a semilinear…

Optimization and Control · Mathematics 2022-09-30 Alessandro Calvia , Gianluca Cappa , Fausto Gozzi , Enrico Priola

The goal of this thesis is to provide efficient and provably convergent numerical methods for solving partial differential equations (PDEs) coming from impulse control problems motivated by finance. Impulses, which are controlled jumps in a…

Numerical Analysis · Mathematics 2018-02-05 Parsiad Azimzadeh

We propose a parallel algorithm for the numerical solution of a class of second order semi-linear equations coming from stochastic optimal control problems, by means of a dynamic domain decomposition technique. The new method is an…

Numerical Analysis · Mathematics 2016-02-11 Simone Cacace , Maurizio Falcone