English
Related papers

Related papers: Approximate Midpoint Policy Iteration for Linear Q…

200 papers

This paper studies a class of continuous-time scalar-state stochastic Linear-Quadratic (LQ) optimal control problem with the linear control constraints. Applying the state separation theorem induced from its special structure, we develop…

Portfolio Management · Quantitative Finance 2018-06-12 Weiping Wu , Jianjun Gao , Junguo Lu , Xun Li

We present a policy iteration algorithm for the infinite-horizon N-player general-sum deterministic linear quadratic dynamic games and compare it to policy gradient methods. We demonstrate that the proposed policy iteration algorithm is…

Optimization and Control · Mathematics 2024-10-07 Yuxiang Guan , Giulio Salizzoni , Maryam Kamgarpour , Tyler H. Summers

This paper introduces a novel data-driven approach to design a linear quadratic regulator (LQR) using a reinforcement learning (RL) algorithm that does not require a system model. The key contribution is to perform policy iteration (PI) by…

Systems and Control · Electrical Eng. & Systems 2023-11-20 Soroush Asri , Luis Rodrigues

This work addresses the problem of risk-sensitive control for nonlinear systems with imperfect state observations, extending results for the linear case. In particular, we derive an algorithm that can compute local solutions with…

Optimization and Control · Mathematics 2021-10-22 Bilal Hammoud , Armand Jordana , Ludovic Righetti

This paper revisits and extends the convergence and robustness properties of value and policy iteration algorithms for discrete-time linear quadratic regulator problems. In the model-based case, we extend current results concerning the…

Systems and Control · Electrical Eng. & Systems 2025-04-11 Bowen Song , Chenxuan Wu , Andrea Iannelli

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

Data-enabled policy optimization (DeePO) is a newly proposed method to attack the open problem of direct adaptive LQR. In this work, we extend the DeePO framework to the linear quadratic tracking (LQT) with offline data. By introducing a…

Systems and Control · Electrical Eng. & Systems 2024-10-10 Shubo Kang , Feiran Zhao , Keyou You

This paper introduces an innovative approach based on policy iteration (PI), a reinforcement learning (RL) algorithm, to obtain an optimal observer with a quadratic cost function. This observer is designed for systems with a given…

Systems and Control · Electrical Eng. & Systems 2023-11-29 Soroush Asri , Luis Rodrigues

Many applications require solving non-linear control problems that are classically not well behaved. This paper develops a simple and efficient chattering algorithm that learns near optimal decision policies through an open-loop feedback…

Machine Learning · Computer Science 2017-03-21 Peeyush Kumar , Wolf Kohn , Zelda B. Zabinsky

A classical method for risk-sensitive nonlinear control is the iterative linear exponential quadratic Gaussian algorithm. We present its convergence analysis from a first-order optimization viewpoint. We identify the objective that the…

Optimization and Control · Mathematics 2019-10-21 Vincent Roulet , Maryam Fazel , Siddhartha Srinivasa , Zaid Harchaoui

Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a number of fields, from artificial intelligence and robotics, to medicine and finance. This paper concerns the problem of…

Machine Learning · Statistics 2018-06-04 Jack Umenberger , Thomas B. Schön

We develop an algorithm that combines model-based and model-free methods for solving a nonlinear optimal control problem with a quadratic cost in which the system model is given by a linear state-space model with a small additive nonlinear…

Optimization and Control · Mathematics 2022-03-23 Yansong Li , Shuo Han

Policy gradient methods are a powerful family of reinforcement learning algorithms for continuous control that optimize a policy directly. However, standard first-order methods often converge slowly. Second-order methods can accelerate…

Systems and Control · Electrical Eng. & Systems 2025-11-05 Amirreza Valaei , Arash Bahari Kordabad , Sadegh Soudjani

In this contribution, we introduce an efficient method for solving the optimal control problem for an unconstrained nonlinear switched system with an arbitrary cost function. We assume that the sequence of the switching modes are given but…

Systems and Control · Computer Science 2017-11-08 Farbod Farshidian , Maryam Kamgarpour , Diego Pardo , Jonas Buchli

This paper presents a constrained adaptive dynamic programming (CADP) algorithm to solve general nonlinear nonaffine optimal control problems with known dynamics. Unlike previous ADP algorithms, it can directly deal with problems with state…

Systems and Control · Electrical Eng. & Systems 2022-04-11 Jingliang Duan , Zhengyu Liu , Shengbo Eben Li , Qi Sun , Zhenzhong Jia , Bo Cheng

We present a proximal augmented Lagrangian based solver for general convex quadratic programs (QPs), relying on semismooth Newton iterations with exact line search to solve the inner subproblems. The exact line search reduces in this case…

Optimization and Control · Mathematics 2020-04-02 Ben Hermans , Andreas Themelis , Panagiotis Patrinos

This paper considers the linear-quadratic dual control problem where the system parameters need to be identified and the control objective needs to be optimized in the meantime. Contrary to existing works on data-driven linear-quadratic…

Systems and Control · Electrical Eng. & Systems 2021-11-22 Yiwen Lu , Yilin Mo

In this paper, we investigate a model-free optimal control design that minimizes an infinite horizon average expected quadratic cost of states and control actions subject to a probabilistic risk or chance constraint using input-output data.…

Systems and Control · Electrical Eng. & Systems 2024-11-11 Arunava Naha , Subhrakanti Dey

This paper studies the finite-horizon linear quadratic regulation problem where the dynamics of the system are assumed to be unknown and the state is accessible. Information on the system is given by a finite set of input-state data, where…

Systems and Control · Electrical Eng. & Systems 2020-08-13 Monica Rotulo , Claudio De Persis , Pietro Tesi

In this paper, we consider the adaptive linear quadratic Gaussian control problem, where both the linear transformation matrix of the state $A$ and the control gain matrix $B$ are unknown. The proposed adaptive optimal control only assumes…

Optimization and Control · Mathematics 2024-09-17 Nian Liu , Cheng Zhao , Shaolin Tan , Jinhu Lü