English
Related papers

Related papers: End-to-End Learning Framework for Solving Non-Mark…

200 papers

We study reinforcement learning (RL) for a class of continuous-time linear-quadratic (LQ) control problems for diffusions, where states are scalar-valued and running control rewards are absent but volatilities of the state processes depend…

Machine Learning · Computer Science 2025-07-25 Yilie Huang , Yanwei Jia , Xun Yu Zhou

This paper investigates the performance of Newton's method, iterative Linear Quadratic Regulator (iLQR), and Differential Dynamic Programming (DDP) in solving discrete-time optimal control problems. We offer a unified perspective on these…

Optimization and Control · Mathematics 2026-05-26 Abhijeet , Suman Chakravorty

The paper studies a class of quadratic optimal control problems for partially observable linear dynamical systems. In contrast to the full information case, the control is required to be adapted to the filtration generated by the…

Optimization and Control · Mathematics 2022-03-01 Jingrui Sun , Jie Xiong

This paper presents a novel, Fourier series based numerical method of open-loop control optimization. Due to its flexible assumptions, it can be applied in a large variety of systems, including discontinuous ones or even so-called black…

Optimization and Control · Mathematics 2022-01-31 Sandra Zarychta , Tomasz Sagan , Marek Balcerzak , Artur Dabrowski , Andrzej Stefanski , Tomasz Kapitaniak

A self-learning optimal control algorithm for episodic fixed-horizon manufacturing processes with time-discrete control actions is proposed and evaluated on a simulated deep drawing process. The control model is built during consecutive…

Systems and Control · Computer Science 2020-01-07 Johannes Dornheim , Norbert Link , Peter Gumbsch

This chapter presents some numerical methods to solve problems in the fractional calculus of variations and fractional optimal control. Although there are plenty of methods available in the literature, we concentrate mainly on approximating…

Optimization and Control · Mathematics 2014-05-19 Shakoor Pooseh , Ricardo Almeida , Delfim F. M. Torres

In this paper, we study the use of state-of-the-art nonlinear system identification techniques for the optimal control of nonlinear systems. We show that the nonlinear systems identification problem is equivalent to estimating the…

Optimization and Control · Mathematics 2023-10-23 Aayushman Sharma , Suman Chakravorty

This paper studies the stochastic optimal control problem for systems with unknown dynamics. A novel decoupled data based control (D2C) approach is proposed, which solves the problem in a decoupled "open loop-closed loop" fashion that is…

Systems and Control · Computer Science 2018-09-11 Dan Yu , Mohammandhussen Rafieisakhaei , Suman Chakravorty

We consider the problem of stochastic optimal control, where the state-feedback control policies take the form of a probability distribution and where a penalty on the entropy is added. By viewing the cost function as a Kullback- Leibler…

Optimization and Control · Mathematics 2024-12-12 Marc Lambert , Francis Bach , Silvère Bonnabel

In this paper, we discuss a new general formulation of fractional optimal control problems whose performance index is in the fractional integral form and the dynamics are given by a set of fractional differential equations in the Caputo…

Optimization and Control · Mathematics 2016-08-24 H. M. Ali , F. Lobo Pereira , S. M. A. Gama

Reinforcement learning (RL) is a promising approach. However, success is limited to real-world applications, because ensuring safe exploration and facilitating adequate exploitation is a challenge for controlling robotic systems with…

Robotics · Computer Science 2022-08-29 Mingyu Cai , Cristian-Ioan Vasile

In this study, we present a purely data-driven method that uses the Loewner framework (LF) along with nonlinear optimization techniques to infer quadratic with affine control dynamical systems that admit Volterra series (VS) representations…

Dynamical Systems · Mathematics 2024-04-16 D. S. Karachalios , I. V. Gosea , L. Gkimisis , A. C. Antoulas

A general backward stochastic linear-quadratic optimal control problem is studied, in which both the state equation and the cost functional contain the nonhomogeneous terms. The main feature of the problem is that the weighting matrices in…

Optimization and Control · Mathematics 2022-03-01 Jingrui Sun , Jiaqiang Wen , Jie Xiong

This paper investigates a model-free solution to the stochastic linear quadratic regulation (LQR) problem for linear discrete-time systems with both multiplicative and additive noises. We formulate the stochastic LQR problem as a nonconvex…

Optimization and Control · Mathematics 2025-12-25 Jing Guo , Xiushan Jiang , Weihai Zhang

Reinforcement learning can acquire complex behaviors from high-level specifications. However, defining a cost function that can be optimized effectively and encodes the correct task is challenging in practice. We explore how inverse optimal…

Machine Learning · Computer Science 2016-05-30 Chelsea Finn , Sergey Levine , Pieter Abbeel

We consider transport processes that are modeled by first order hyperbolic partial differential equations. Our goal is to find a full state feedback that makes a given reference profile locally asymptotically stable. To accomplish this we…

Optimization and Control · Mathematics 2025-08-22 Arthur J. Krener

In this paper, we leverage existing statistical methods to better understand feature learning from data. We tackle this by modifying the model-free variable selection method, Feature Ordering by Conditional Independence (FOCI), which is…

Machine Learning · Statistics 2025-02-14 Krunoslav Lehman Pavasovic , David Lopez-Paz , Giulio Biroli , Levent Sagun

Reinforcement learning (RL) is a class of artificial intelligence algorithms being used to design adaptive optimal controllers through online learning. This paper presents a model-free, real-time, data-efficient Q-learning-based algorithm…

Systems and Control · Electrical Eng. & Systems 2023-10-11 Ali Aalipour , Alireza Khani

We propose Fractional Policy Gradients (FPG), a reinforcement learning framework incorporating fractional calculus for long-term temporal modeling in policy optimization. Standard policy gradient approaches face limitations from Markovian…

Machine Learning · Computer Science 2025-07-02 Urvi Pawar , Kunal Telangi

Manipulate and control of the complex quantum system with high precision are essential for achieving universal fault tolerant quantum computing. For a physical system with restricted control resources, it is a challenge to control the…

Quantum Physics · Physics 2021-01-20 Zheng An , Qi-Kai He , Hai-Jing Song , D. L. Zhou