English
Related papers

Related papers: Stochastic Reinforcement Learning with Stability G…

200 papers

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently…

Machine Learning · Computer Science 2019-05-15 Andreas Doerr , Michael Volpp , Marc Toussaint , Sebastian Trimpe , Christian Daniel

The $Q$-learning algorithm is a simple and widely-used stochastic approximation scheme for reinforcement learning, but the basic protocol can exhibit instability in conjunction with function approximation. Such instability can be observed…

Machine Learning · Computer Science 2022-06-03 Andrea Zanette , Martin J. Wainwright

We draw on the latest advancements in the physics community to propose a novel method for discovering the governing non-linear dynamics of physical systems in reinforcement learning (RL). We establish that this method is capable of…

Machine Learning · Computer Science 2022-09-01 Rushiv Arora , Bruno Castro da Silva , Eliot Moss

Several works have addressed the problem of incorporating constraints in the reinforcement learning (RL) framework, however majority of them can only guarantee the satisfaction of soft constraints. In this work, we address the problem of…

Machine Learning · Computer Science 2020-06-16 Kwangyeon Kim , Akshita Gupta , Hong-Cheol Choi , Inseok Hwang

This paper considers the problem of real-time control and learning in dynamic systems subjected to parametric uncertainties. We propose a combination of a Reinforcement Learning (RL) based policy in the outer loop suitably chosen to ensure…

Machine Learning · Computer Science 2023-06-13 Anuradha M. Annaswamy , Anubhav Guha , Yingnan Cui , Sunbochen Tang , Peter A. Fisher , Joseph E. Gaudio

Quadratic programming is a workhorse of modern nonlinear optimization, control, and data science. Although regularized methods offer convergence guarantees under minimal assumptions on the problem data, they can exhibit the slow…

Optimization and Control · Mathematics 2026-05-18 Jeremy Bertoncini , Alberto De Marchi , Matthias Gerdts , Simon Gottschalk

Despite the success achieved by the analysis of supervised learning algorithms in the framework of statistical mechanics, reinforcement learning has remained largely untouched. Here we move towards closing the gap by analyzing the dynamics…

Statistical Mechanics · Physics 2022-09-02 Riccardo Fabbricatore , Vladimir V. Palyulin

Deep reinforcement learning (DRL) has been successfully used to solve various robotic manipulation tasks. However, most of the existing works do not address the issue of control stability. This is in sharp contrast to the control theory…

Robotics · Computer Science 2021-09-28 Shahbaz Abdul Khader , Hang Yin , Pietro Falco , Danica Kragic

We study the performance of stochastic first-order methods for finding saddle points of convex-concave functions. A notorious challenge faced by such methods is that the gradients can grow arbitrarily large during optimization, which may…

Machine Learning · Computer Science 2024-06-10 Gergely Neu , Nneka Okolo

A common pipeline in learning-based control is to iteratively estimate a model of system dynamics, and apply a trajectory optimization algorithm - e.g.~$\mathtt{iLQR}$ - on the learned model to minimize a target cost. This paper conducts a…

Machine Learning · Computer Science 2023-05-17 Daniel Pfrommer , Max Simchowitz , Tyler Westenbroek , Nikolai Matni , Stephen Tu

The transfer of reinforcement learning (RL) techniques into real-world applications is challenged by safety requirements in the presence of physical limitations. Most RL methods, in particular the most popular algorithms, do not support…

Systems and Control · Computer Science 2021-05-18 Kim P. Wabersich , Melanie N. Zeilinger

This paper presents a novel approach to reinforcement learning (RL) for control systems that provides probabilistic stability guarantees using finite data. Leveraging Lyapunov's method, we propose a probabilistic stability theorem that…

Machine Learning · Computer Science 2026-03-03 Minghao Han , Lixian Zhang , Chenliang Liu , Zhipeng Zhou , Jun Wang , Wei Pan

A key challenge in the field of reinforcement learning is to develop agents that behave cautiously in novel situations. It is generally impossible to anticipate all situations that an autonomous system may face or what behavior would best…

Artificial Intelligence · Computer Science 2025-10-14 Montaser Mohammedalamen , Dustin Morrill , Alexander Sieusahai , Yash Satsangi , Michael Bowling

Reinforcement learning (RL) agents need to be robust to variations in safety-critical environments. While system identification methods provide a way to infer the variation from online experience, they can fail in settings where fast…

Machine Learning · Computer Science 2022-03-07 Annie Xie , Shagun Sodhani , Chelsea Finn , Joelle Pineau , Amy Zhang

In order for reinforcement learning techniques to be useful in real-world decision making processes, they must be able to produce robust performance from limited data. Deep policy optimization methods have achieved impressive results on…

Machine Learning · Computer Science 2020-12-22 James Queeney , Ioannis Ch. Paschalidis , Christos G. Cassandras

Learning for control of dynamical systems with formal guarantees remains a challenging task. This paper proposes a learning framework to simultaneously stabilize an unknown nonlinear system with a neural controller and learn a neural…

Systems and Control · Electrical Eng. & Systems 2022-10-18 Ruikun Zhou , Thanin Quartz , Hans De Sterck , Jun Liu

This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Transformers. These algorithms performed competitively across…

We propose a principled method for projecting an arbitrary square matrix to the non-convex set of asymptotically stable matrices. Leveraging ideas from large deviations theory, we show that this projection is optimal in an…

Optimization and Control · Mathematics 2023-06-21 Wouter Jongeneel , Tobias Sutter , Daniel Kuhn

For safely applying reinforcement learning algorithms on high-dimensional nonlinear dynamical systems, a simplified system model is used to formulate a safe reinforcement learning framework. Based on the simplified system model, a…

Robotics · Computer Science 2021-09-09 Zhehua Zhou , Ozgur S. Oguz , Marion Leibold , Martin Buss

Approaches to keeping a dynamical system within state constraints typically rely on a model-based safety condition to limit the control signals. In the face of significant modeling uncertainty, the system can suffer from important…

Systems and Control · Electrical Eng. & Systems 2022-02-08 Marc-Antoine Beaudoin , Benoit Boulet
‹ Prev 1 4 5 6 7 8 10 Next ›