English
Related papers

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

200 papers

Solving Hamilton-Jacobi-Isaacs (HJI) PDEs numerically enables equilibrial feedback control in two-player differential games, yet faces the curse of dimensionality (CoD). While physics-informed neural networks (PINNs) have shown promise in…

Robotics · Computer Science 2024-05-08 Lei Zhang , Mukesh Ghimire , Wenlong Zhang , Zhe Xu , Yi Ren

Several works have addressed the problem of incorporating constraints in the reinforcement learning (RL) framework, however majority of them can only guarantee the satisfaction of soft constraints. In this work, we address the problem of…

Machine Learning · Computer Science 2020-06-16 Kwangyeon Kim , Akshita Gupta , Hong-Cheol Choi , Inseok Hwang

We propose a mathematical framework to explain implicit regularization from early stopping during the training of overparametrized neural networks. In the mean-field limit, the parameter distribution evolves according to a gradient flow on…

Optimization and Control · Mathematics 2026-03-24 Beatrice Acciaio , Jakob Heiss , Gudmund Pammer , Qinxin Yan

The control of relaxation-type systems of ordinary differential equations is investigated using the Hamilton-Jacobi-Bellman equation. First, we recast the model as a singularly perturbed dynamics which we embed in a family of controlled…

Optimization and Control · Mathematics 2024-04-23 Michael Herty , Hicham Kouhkouh

Stochastic optimal control problems governed by delay equations with delay in the control are usually more difficult to study than the the ones when the delay appears only in the state. This is particularly true when we look at the…

Probability · Mathematics 2015-06-22 Fausto Gozzi , Federica Masiero

The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the uncertainty in model parameters. Parameter uncertainty commonly occurs in many real-world RL applications due to simulator modeling errors,…

Machine Learning · Computer Science 2022-10-19 Kishan Panaganti , Zaiyan Xu , Dileep Kalathil , Mohammad Ghavamzadeh

In this paper, we study the optimal stopping problem in the so-called exploratory framework, in which the agent takes actions randomly conditioning on current state and an entropy-regularized term is added to the reward functional. Such a…

Optimization and Control · Mathematics 2023-09-04 Yuchao Dong

A learning technique for finite horizon optimal control problems and its approximation based on polynomials is analyzed. It allows to circumvent, in part, the curse dimensionality which is involved when the feedback law is constructed by…

Optimization and Control · Mathematics 2023-02-21 Karl Kunisch , Donato Vásquez-Varas

Safety assurance is a fundamental requirement for deploying learning-enabled autonomous systems. Hamilton-Jacobi (HJ) reachability analysis is a fundamental method for formally verifying safety and generating safe controllers. However,…

Machine Learning · Computer Science 2025-11-21 Ihab Tabbara , Yuxuan Yang , Hussein Sibai

Stochastic optimal control problems governed by delay equations with delay in the control are usually more difficult to study than the the ones when the delay appears only in the state. This is particularly true when we look at the…

Probability · Mathematics 2021-03-22 F. Gozzi , F. Masiero

In this paper, we propose a hybrid MPC local planner that uses a learning-based approximation of a time-varying safe set, derived from local observations and applied as the MPC terminal constraint. This set can be represented as a…

Robotics · Computer Science 2025-08-29 Bojan Derajić , Mohamed-Khalil Bouzidi , Sebastian Bernhard , Wolfgang Hönig

We consider a robust switching control problem. The controller only observes the evolution of the state process, and thus uses feedback (closed-loop) switching strategies, a non standard class of switching controls introduced in this paper.…

Probability · Mathematics 2016-07-04 Erhan Bayraktar , Andrea Cosso , Huyen Pham

In this note, we demonstrate that a locally semiconvex viscosity supersolution to a possibly degenerate fully nonlinear elliptic Hamilton-Jacobi-Bellman (HJB) equation is differentiable along the directions spanned by the range of the…

Optimization and Control · Mathematics 2025-01-28 Salvatore Federico , Giorgio Ferrari , Mauro Rosestolato

The State-Dependent Riccati Equation (SDRE) approach is extensively utilized in nonlinear optimal control as a reliable framework for designing robust feedback control strategies. This work provides an analysis of the SDRE approach,…

Numerical Analysis · Mathematics 2026-03-10 Luca Saluzzi

Physics-Informed Neural Networks (PINNs) have been recognized as a mesh-free alternative to solve partial differential equations where physics information is incorporated. However, in dealing with problems characterized by high stiffness or…

Machine Learning · Computer Science 2026-03-04 Divyavardhan Singh , Shubham Kamble , Dimple Sonone , Kishor Upla

Learning-based control of linear systems received a lot of attentions recently. In popular settings, the true dynamical models are unknown to the decision-maker and need to be interactively learned by applying control inputs to the systems.…

Systems and Control · Electrical Eng. & Systems 2022-01-06 Mohamad Kazem Shirani Faradonbeh , Aditya Modi

Recent research has shown that supervised learning can be an effective tool for designing optimal feedback controllers for high-dimensional nonlinear dynamic systems. But the behavior of these neural network (NN) controllers is still not…

Optimization and Control · Mathematics 2022-10-10 Tenavi Nakamura-Zimmerer , Qi Gong , Wei Kang

Safety is a primary concern when applying reinforcement learning to real-world control tasks, especially in the presence of external disturbances. However, existing safe reinforcement learning algorithms rarely account for external…

Machine Learning · Computer Science 2023-10-12 Zeyang Li , Chuxiong Hu , Shengbo Eben Li , Jia Cheng , Yunan Wang

We study a class of backward stochastic differential equations (BSDEs) driven by a random measure or, equivalently, by a marked point process. Under appropriate assumptions we prove well-posedness and continuous dependence of the solution…

Probability · Mathematics 2012-05-24 Fulvia Confortola , Marco Fuhrman

We study the solution theory of the whole-space static (elliptic) Hamilton-Jacobi-Bellman (HJB) equation in spectral Barron spaces. We prove that under the assumption that the coefficients involved are spectral Barron functions and the…

Analysis of PDEs · Mathematics 2025-09-18 Ye Feng , Jianfeng Lu