中文
相关论文

相关论文: Model-Free Design of Stochastic LQR Controller fro…

200 篇论文

Model-free or learning-based control, in particular, reinforcement learning (RL), is expected to be applied for complex robotic tasks. Traditional RL requires a policy to be optimized is state-dependent, that means, the policy is a kind of…

机器学习 · 计算机科学 2022-08-09 Taisuke Kobayashi , Kenta Yoshizawa

Model-free reinforcement learning methods lack an inherent mechanism to impose behavioural constraints on the trained policies. Although certain extensions exist, they remain limited to specific types of constraints, such as value…

机器学习 · 计算机科学 2025-04-28 Bram De Cooman , Johan Suykens

This article investigates the core mechanisms of indirect data-driven control for unknown systems, focusing on the application of policy iteration (PI) within the context of the linear quadratic regulator (LQR) optimal control problem.…

系统与控制 · 电气工程与系统科学 2025-04-14 Bowen Song , Andrea Iannelli

This paper considers a stochastic linear quadratic problem for discrete-time systems with multiplicative noises over an infinite horizon. To obtain the optimal solution, we propose an online iterative algorithm of reinforcement learning…

最优化与控制 · 数学 2023-11-22 Hongdan Li , Lucky Qiaofeng Li , Xun Li , Zhaorong Zhang

We investigate the problem of learning an $\epsilon$-approximate solution for the discrete-time Linear Quadratic Regulator (LQR) problem via a Stochastic Variance-Reduced Policy Gradient (SVRPG) approach. Whilst policy gradient methods have…

最优化与控制 · 数学 2023-09-20 Leonardo F. Toso , Han Wang , James Anderson

We present a heuristic policy and performance bound for risk-sensitive convex stochastic control that generalizes linear-exponential-quadratic regulator (LEQR) theory. Our heuristic policy extends standard, risk-neutral model predictive…

最优化与控制 · 数学 2022-05-30 Nicholas Moehle

We consider large-scale Markov decision processes with an unknown cost function and address the problem of learning a policy from a finite set of expert demonstrations. We assume that the learner is not allowed to interact with the expert…

机器学习 · 计算机科学 2021-12-30 Angeliki Kamoutsi , Goran Banjac , John Lygeros

We present a model-free reinforcement learning algorithm to find an optimal policy for a finite-horizon Markov decision process while guaranteeing a desired lower bound on the probability of satisfying a signal temporal logic (STL)…

系统与控制 · 电气工程与系统科学 2021-09-29 Krishna C. Kalagarla , Rahul Jain , Pierluigi Nuzzo

We study the discrete-time linear-quadratic (LQ) control model using reinforcement learning (RL). Using entropy to measure the cost of exploration, we prove that the optimal feedback policy for the problem must be Gaussian type. Then, we…

机器学习 · 统计学 2025-02-05 Lucky Li

This paper introduces a novel Model Predictive Control (MPC) implementation for legged robot locomotion that leverages GPU parallelization. Our approach enables both temporal and state-space parallelization by incorporating a parallel…

This paper presents a sample-efficient, data-driven control framework for finite-horizon linear quadratic (LQ) control of linear time-varying (LTV) systems. In contrast to the time-invariant case, the time-varying LQ problem involves a…

系统与控制 · 电气工程与系统科学 2025-09-30 Sahel Vahedi Noori , Maryam Babazadeh

We study model-free learning methods for the output-feedback Linear Quadratic (LQ) control problem in finite-horizon subject to subspace constraints on the control policy. Subspace constraints naturally arise in the field of distributed…

系统与控制 · 电气工程与系统科学 2021-07-14 Luca Furieri , Yang Zheng , Maryam Kamgarpour

The Linear Quadratic Regulator (LQR) framework considers the problem of regulating a linear dynamical system perturbed by environmental noise. We compute the policy regret between three distinct control policies: i) the optimal online…

最优化与控制 · 数学 2020-02-10 Gautam Goel , Babak Hassibi

Recent literature has made much progress in understanding \emph{online LQR}: a modern learning-theoretic take on the classical control problem in which a learner attempts to optimally control an unknown linear dynamical system with fully…

机器学习 · 计算机科学 2020-10-06 Max Simchowitz

Effective exploration remains a central challenge in model-based reinforcement learning (MBRL), particularly in high-dimensional continuous control tasks where sample efficiency is crucial. A prominent line of recent work leverages learned…

机器学习 · 计算机科学 2026-05-22 Álvaro Serra-Gomez , Daniel Jarne Ornia , Dhruva Tirumala , Thomas Moerland

We propose a new framework to design controllers for high-dimensional nonlinear systems. The control is designed through the iterative linear quadratic regulator (ILQR), an algorithm that computes control by iteratively applying the linear…

最优化与控制 · 数学 2021-10-12 Yizhe Huang , Boris Kramer

This paper addresses the joint state estimation and control problems for unknown linear time-invariant systems subject to both process and measurement noise. The aim is to redesign the linear quadratic Gaussian (LQG) controller based solely…

系统与控制 · 电气工程与系统科学 2023-05-03 Wenjie Liu , Jian Sun , Gang Wang , Francesco Bullo , Jie Chen

Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy. This problem has attracted a lot of attention recently, but most existing methods with strong…

机器学习 · 计算机科学 2023-05-23 Germano Gabbianelli , Gergely Neu , Nneka Okolo , Matteo Papini

Model-free Reinforcement Learning (RL) algorithms such as Q-learning [Watkins, Dayan 92] have been widely used in practice and can achieve human level performance in applications such as video games [Mnih et al. 15]. Recently, equipped with…

机器学习 · 计算机科学 2019-05-03 Zhao Song , Wen Sun

We study the exploration-exploitation dilemma in the linear quadratic regulator (LQR) setting. Inspired by the extended value iteration algorithm used in optimistic algorithms for finite MDPs, we propose to relax the optimistic optimization…

机器学习 · 统计学 2020-07-14 Marc Abeille , Alessandro Lazaric