English
Related papers

Related papers: Neural Actor-Critic Methods for Hamilton-Jacobi-Be…

200 papers

We study a structured bi-level optimization problem where the upper-level objective is a smooth function and the lower-level problem is policy optimization in a Markov decision process (MDP). The upper-level decision variable parameterizes…

Machine Learning · Computer Science 2026-04-23 Sihan Zeng , Sujay Bhatt , Sumitra Ganesh , Alec Koppel

This paper presents a mathematical formulation to perform temporal parallelisation of continuous-time optimal control problems, which can be solved via the Hamilton--Jacobi--Bellman (HJB) equation. We divide the time interval of the control…

Optimization and Control · Mathematics 2024-12-18 Simo Särkkä , Ángel F. García-Fernández

We introduce a new and efficient numerical method for multicriterion optimal control and single criterion optimal control under integral constraints. The approach is based on extending the state space to include information on a "budget"…

Optimization and Control · Mathematics 2016-01-06 Ajeet Kumar , Alexander Vladimirsky

A tensor decomposition approach for the solution of high-dimensional, fully nonlinear Hamilton-Jacobi-Bellman equations arising in optimal feedback control of nonlinear dynamics is presented. The method combines a tensor train approximation…

Optimization and Control · Mathematics 2021-03-17 Sergey Dolgov , Dante Kalise , Karl Kunisch

This work is devoted to the study of optimal control of stochastic functional differential equations (SFDEs) and its application to mathematical finance. By using the Dynkin formula and solution of the Dirichlet-Poisson problem, the…

Optimization and Control · Mathematics 2014-04-04 Edson A. Coayla-Teran , Anatoly Swishchuk

We present a kernel-based linear matrix inequality (LMI) approach for the approximate solution of Hamilton--Jacobi--Bellman (HJB) equations arising in nonlinear optimal control. The method represents the gradient of the value function in a…

Dynamical Systems · Mathematics 2026-05-19 Boumediene Hamzi , Umesh Vaidya

This paper deals with a family of stochastic control problems in Hilbert spaces which arises in typical applications (such as boundary control and control of delay equations with delay in the control) and for which is difficult to apply the…

Optimization and Control · Mathematics 2022-10-14 Federica Masiero , Fausto Gozzi

Continuous-time reinforcement learning offers an appealing formalism for describing control problems in which the passage of time is not naturally divided into discrete increments. Here we consider the problem of predicting the distribution…

Machine Learning · Computer Science 2022-06-20 Harley Wiltzer , David Meger , Marc G. Bellemare

Multi-agent reinforcement learning has been successfully applied to a number of challenging problems. Despite these empirical successes, theoretical understanding of different algorithms is lacking, primarily due to the curse of…

Machine Learning · Computer Science 2021-12-28 Yuwei Luo , Zhuoran Yang , Zhaoran Wang , Mladen Kolar

This paper presents a novel method of global adaptive dynamic programming (ADP) for the adaptive optimal control of nonlinear polynomial systems. The strategy consists of relaxing the problem of solving the Hamilton-Jacobi-Bellman (HJB)…

Dynamical Systems · Mathematics 2017-01-11 Yu Jiang , Zhong-Ping Jiang

In this paper, we focus on the stochastic representation of a system of coupled Hamilton-Jacobi-Bellman-Isaacs (HJB-Isaacs (HJBI), for short) equations which is in fact a system of coupled Isaacs' type integral-partial differential…

Optimization and Control · Mathematics 2023-07-12 Sheng Luo , Wenqiang Li , Xun Li , Qingmeng Wei

This study investigates a stochastic production planning problem with a running cost composed of quadratic production costs and inventory-dependent costs. The objective is to minimize the expected cost until production stops when inventory…

Optimization and Control · Mathematics 2025-05-20 Dragos-Patru Covei

We establish, for the first time, explicit a priori and regularity estimates for solutions of the Dirichlet problem for Hamilton-Jacobi-Bellman operators from stochastic control, whose principal half-eigenvalues have opposite signs. In…

Analysis of PDEs · Mathematics 2026-01-21 Maria Luísa Pasinato , Boyan Sirakov

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

This paper presents an implicit solution formula for the Hamilton-Jacobi partial differential equation (HJ PDE). The formula is derived using the method of characteristics and is shown to coincide with the Hopf and Lax formulas in the case…

Machine Learning · Computer Science 2025-02-03 Yesom Park , Stanley Osher

We study the properties of the value function associated with an optimal control problem with uncertainties, known as average or Riemann-Stieltjes problem. Uncertainties are assumed to belong to a compact metric probability space, and…

Optimization and Control · Mathematics 2024-07-19 M. Soledad Aronna , Michele Palladino , Oscar Sierra

We address two major challenges in scientific machine learning (SciML): interpretability and computational efficiency. We increase the interpretability of certain learning processes by establishing a new theoretical connection between…

Machine Learning · Computer Science 2024-05-08 Paula Chen , Tingwei Meng , Zongren Zou , Jérôme Darbon , George Em Karniadakis

We introduce a novel extension to robust control theory that explicitly addresses uncertainty in the value function's gradient, a form of uncertainty endemic to applications like reinforcement learning where value functions are…

Machine Learning · Computer Science 2025-07-22 Qian Qi

Deterministic policy gradient algorithms are foundational for actor-critic methods in controlling continuous systems, yet they often encounter inaccuracies due to their dependence on the derivative of the critic's value estimates with…

Machine Learning · Computer Science 2025-02-11 Baturay Saglam , Dionysis Kalogerias

This paper establishes the existence and uniqueness of mild solutions to stationary Hamilton-Jacobi-Bellman (HJB) equations associated with infinite-horizon stochastic optimal control problems in separable Hilbert spaces. Our framework…

Optimization and Control · Mathematics 2026-05-08 Gabriele Bolli , Fabian Fuchs