English
Related papers

Related papers: Reinforcement Learning for Linear Quadratic Contro…

200 papers

This paper studies reinforcement learning (RL) under malicious falsification on cost signals and introduces a quantitative framework of attack models to understand the vulnerabilities of RL. Focusing on $Q$-learning, we show that…

Machine Learning · Computer Science 2019-08-20 Yunhan Huang , Quanyan Zhu

This chapter studies emerging cyber-attacks on reinforcement learning (RL) and introduces a quantitative approach to analyze the vulnerabilities of RL. Focusing on adversarial manipulation on the cost signals, we analyze the performance…

Machine Learning · Computer Science 2020-07-22 Yunhan Huang , Quanyan Zhu

Systems operating in adversarial environments may inadvertently leak sensitive information to adversaries. To address this challenge, we revisit the linear-quadratic control framework and introduce deception to actively mislead adversaries.…

Optimization and Control · Mathematics 2026-04-02 Yerin Kim , Haosheng Zhou , Alexander Benvenuti , Ruimeng Hu , Matthew Hale

We study the problem of state representation learning for control from partial and potentially high-dimensional observations. We approach this problem via cost-driven state representation learning, in which we learn a dynamical model in a…

Machine Learning · Computer Science 2026-03-10 Yi Tian , Kaiqing Zhang , Russ Tedrake , Suvrit Sra

We study the task of learning state representations from potentially high-dimensional observations, with the goal of controlling an unknown partially observable system. We pursue a cost-driven approach, where a dynamic model in some latent…

Machine Learning · Computer Science 2026-03-10 Yi Tian , Kaiqing Zhang , Russ Tedrake , Suvrit Sra

Deception is a common defense mechanism against adversaries with an information disadvantage. It can force such adversaries to select suboptimal policies for a defender's benefit. We consider a setting where an adversary tries to learn the…

Systems and Control · Electrical Eng. & Systems 2026-02-20 Filippos Fotiadis , Aris Kanellopoulos , Kyriakos G. Vamvoudakis , Ufuk Topcu

Motivated by recent works addressing adversarial attacks on deep reinforcement learning, a deception attack on linear quadratic Gaussian control is studied in this paper. In the considered attack model, the adversary can manipulate the…

Systems and Control · Electrical Eng. & Systems 2020-09-11 Zuxing Li , György Dán , Dong Liu

Learning methods are increasingly used to synthesize controllers from data, yet existing sample-complexity characterizations for continuous control are sharp only in the fully observed setting. This paper studies the partially observed case…

Systems and Control · Electrical Eng. & Systems 2026-05-19 Bruce D. Lee , Anastasios Tsiamis , Nikolai Matni , Manfred Morari , John Lygeros

We study the linear quadratic Gaussian (LQG) control problem, in which the controller's observation of the system state is such that a desired cost is unattainable. To achieve the desired LQG cost, we introduce a communication link from the…

Optimization and Control · Mathematics 2021-09-28 Oron Sabag , Peida Tian , Victoria Kostina , Babak Hassibi

We study the problem of learning-based attacks in linear systems, where the communication channel between the controller and the plant can be hijacked by a malicious attacker. We assume the attacker learns the dynamics of the system from…

Systems and Control · Electrical Eng. & Systems 2021-05-21 Anshuka Rangi , Mohammad Javad Khojasteh , Massimo Franceschetti

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…

Machine Learning · Statistics 2025-02-05 Lucky Li

This paper studies the robustness of reinforcement learning algorithms to errors in the learning process. Specifically, we revisit the benchmark problem of discrete-time linear quadratic regulation (LQR) and study the long-standing open…

Optimization and Control · Mathematics 2021-03-16 Bo Pang , Zhong-Ping Jiang

We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…

Machine Learning · Computer Science 2020-08-20 Amin Rakhsha , Goran Radanovic , Rati Devidze , Xiaojin Zhu , Adish Singla

In safety-critical applications, reinforcement learning (RL) needs to consider safety constraints. However, theoretical understandings of constrained RL for continuous control are largely absent. As a case study, this paper presents a…

Optimization and Control · Mathematics 2024-06-07 Feiran Zhao , Keyou You

This paper proposes a safe reinforcement learning (RL) algorithm that approximately solves the state-constrained optimal control problem for continuous-time uncertain nonlinear systems. We formulate the safe RL problem as the minimization…

Systems and Control · Electrical Eng. & Systems 2025-06-26 Soutrik Bandyopadhyay , Shubhendu Bhasin

We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…

Machine Learning · Computer Science 2020-11-24 Amin Rakhsha , Goran Radanovic , Rati Devidze , Xiaojin Zhu , Adish Singla

This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process. Policies are synthesised to satisfy a goal,…

Machine Learning · Computer Science 2020-03-24 Mohammadhosein Hasanbeig , Alessandro Abate , Daniel Kroening

In this work, we study policy poisoning through state manipulation, also known as sensor spoofing, and focus specifically on the case of an agent forming a control policy through batch learning in a linear-quadratic (LQ) system. In this…

Systems and Control · Electrical Eng. & Systems 2023-04-18 Courtney M. King , Son Tung Do , Juntao Chen

The linear-quadratic-Gaussian (LQG) control paradigm is well-known in literature. The strategy of minimizing the cost function is available, both for the case where the state is known and where it is estimated through an observer. The…

Systems and Control · Computer Science 2018-12-10 Hildo Bijl , Thomas B. Schön

This paper concerns the problem of learning control policies for an unknown linear dynamical system to minimize a quadratic cost function. We present a method, based on convex optimization, that accomplishes this task robustly: i.e., we…

Optimization and Control · Mathematics 2019-06-05 Jack Umenberger , Mina Ferizbegovic , Thomas B. Schön , Håkan Hjalmarsson
‹ Prev 1 2 3 10 Next ›