English
Related papers

Related papers: Certifying Stability of Reinforcement Learning Pol…

200 papers

In this work, we study model-based reinforcement learning (RL) in unknown stabilizable linear dynamical systems. When learning a dynamical system, one needs to stabilize the unknown dynamics in order to avoid system blow-ups. We propose an…

Machine Learning · Computer Science 2022-06-06 Sahin Lale , Kamyar Azizzadenesheli , Babak Hassibi , Anima Anandkumar

In a recent paper we have shown how to learn controllers for unknown linear systems using finite-sized noisy data by solving linear matrix inequalities. In this note we extend this approach to deal with unknown nonlinear polynomial systems…

Optimization and Control · Mathematics 2020-11-17 Meichen Guo , Claudio De Persis , Pietro Tesi

Recent methods using Reinforcement Learning (RL) have proven to be successful for training intelligent agents in unknown environments. However, RL has not been applied widely in real-world robotics scenarios. This is because current…

Systems and Control · Electrical Eng. & Systems 2024-03-20 Antonio Lopez , David Fridovich-Keil

This paper proposes a safe reinforcement learning (RL) framework based on forward-invariance-induced action-space design. The control problem is cast as a Markov decision process, but instead of relying on runtime shielding or penalty-based…

Systems and Control · Electrical Eng. & Systems 2026-04-10 Chieh Tsai , Muhammad Junayed Hasan Zahed , Salim Hariri , Hossein Rastgoftar

The automatic synthesis of a policy through reinforcement learning (RL) from a given set of formal requirements depends on the construction of a reward signal and consists of the iterative application of many policy-improvement steps. The…

Machine Learning · Computer Science 2022-10-21 Luigi Berducci , Radu Grosu

The notion of Lyapunov function plays a key role in design and verification of dynamical systems, as well as hybrid and cyber-physical systems. In this paper, to analyze the asymptotic stability of a dynamical system, we generalize standard…

Dynamical Systems · Mathematics 2011-03-18 Jiang Liu , Naijun Zhan , Hengjun Zhao

Ensuring safety is a crucial challenge when deploying reinforcement learning (RL) to real-world systems. We develop confidence-based safety filters, a control-theoretic approach for certifying state safety constraints for nominal policies…

Machine Learning · Computer Science 2022-07-05 Sebastian Curi , Armin Lederer , Sandra Hirche , Andreas Krause

Learning control strategies with provable stability guarantees continues to be a challenging problem. In this work, we examine a family of training-time behaviors exhibited by existing neural Lyapunov control methods under specific…

Systems and Control · Electrical Eng. & Systems 2026-05-12 Yuan Zhong , Jiaxin Cheng , Hefu Ye , Yicong Zhou

Control Lyapunov Functions (CLFs) have been extensively used in the control community. A well-known drawback is the absence of a systematic way to construct CLFs for general nonlinear systems, and the problem can become more complex with…

Optimization and Control · Mathematics 2026-03-06 Zheng Gong , Sylvia Herbert

We propose a simple, practical and intuitive approach to improve the performance of a conventional controller in uncertain environments using deep reinforcement learning while maintaining safe operation. Our approach is motivated by the…

Systems and Control · Electrical Eng. & Systems 2021-10-07 Tom Staessens , Tom Lefebvre , Guillaume Crevecoeur

We introduce the concept of sos-convex Lyapunov functions for stability analysis of both linear and nonlinear difference inclusions (also known as discrete-time switched systems). These are polynomial Lyapunov functions that have an…

Optimization and Control · Mathematics 2018-03-07 Amir Ali Ahmadi , Raphael M. Jungers

Reinforcement learning is commonly associated with training of reward-maximizing (or cost-minimizing) agents, in other words, controllers. It can be applied in model-free or model-based fashion, using a priori or online collected system…

Systems and Control · Electrical Eng. & Systems 2022-09-01 Lukas Beckenbach , Pavel Osinenko , Stefan Streif

Modelling real world systems involving humans such as biological processes for disease treatment or human behavior for robotic rehabilitation is a challenging problem because labeled training data is sparse and expensive, while high…

Systems and Control · Electrical Eng. & Systems 2020-06-16 Wenxin Xiao , Armin Lederer , Sandra Hirche

There are recent shifts in demand for design controllers from simplified to complex model-based. Although simplification approaches are successful in many areas of engineering control systems, high-fidelity simulation-based control design,…

Systems and Control · Electrical Eng. & Systems 2024-02-15 Jongrae Kim

Machine learning techniques have demonstrated their effectiveness in achieving autonomy and optimality for nonlinear and high-dimensional dynamical systems. However, traditional black-box machine learning methods often lack formal stability…

Systems and Control · Electrical Eng. & Systems 2025-01-03 Kun Wang , Roberto Armellin , Adam Evans , Harry Holt , Zheng Chen

We provide a computer-assisted approach to ensure that a given continuous or discrete-time polynomial system is (asymptotically) stable. Our framework relies on constructive analysis together with formally certified sums of squares Lyapunov…

Optimization and Control · Mathematics 2024-08-02 Grigory Devadze , Victor Magron , Stefan Streif

Decentralized multi-agent control has broad applications, ranging from multi-robot cooperation to distributed sensor networks. In decentralized multi-agent control, systems are complex with unknown or highly uncertain dynamics, where…

Systems and Control · Electrical Eng. & Systems 2020-09-22 Qingrui Zhang , Hao Dong , Wei Pan

Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs…

Machine Learning · Computer Science 2022-02-03 Michael Everett , Bjorn Lutjens , Jonathan P. How

We investigate the formal synthesis of global polynomial Lyapunov functions for polynomial vector fields. We establish that a sign-definite polynomial must satisfy specific algebraic constraints, which we leverage to develop a set of…

Systems and Control · Electrical Eng. & Systems 2025-06-24 Jun Liu , Maxwell Fitzsimmons

In the last decade, Reinforcement Learning (RL) has achieved remarkable success in the control and decision-making of complex dynamical systems. However, most RL algorithms rely on the Markov Decision Process assumption, which is violated…

Machine Learning · Statistics 2026-02-03 Armando Alves Neto