English
Related papers

Related papers: Imitation and Transfer Learning for LQG Control

200 papers

This manuscript surveys reinforcement learning from the perspective of optimization and control with a focus on continuous control applications. It surveys the general formulation, terminology, and typical experimental implementations of…

Optimization and Control · Mathematics 2018-11-13 Benjamin Recht

Tensor Gaussian graphical models (GGMs), interpreting conditional independence structures within tensor data, have important applications in numerous areas. Yet, the available tensor data in one single study is often limited due to high…

Machine Learning · Statistics 2022-11-18 Mingyang Ren , Yaoming Zhen , Junhui Wang

Iterative learning control (ILC) is a powerful technique for high performance tracking in the presence of modeling errors for optimal control applications. There is extensive prior work showing its empirical effectiveness in applications…

Robotics · Computer Science 2021-12-10 Anirudh Vemula , Wen Sun , Maxim Likhachev , J. Andrew Bagnell

Imitation learning is an effective and safe technique to train robot policies in the real world because it does not depend on an expensive random exploration process. However, due to the lack of exploration, learning policies that…

Robotics · Computer Science 2021-06-24 Ajay Mandlekar , Danfei Xu , Roberto Martín-Martín , Silvio Savarese , Li Fei-Fei

Transformers trained on modular arithmetic exhibit sharp transitions between memorization, generalization, and collapse. We show that weight decay acts as a scalar empirical control parameter for these regimes, and introduce two cheap…

Machine Learning · Computer Science 2026-05-21 Lucky Verma

Reinforcement learning (RL) has seen significant research and application results but often requires large amounts of training data. This paper proposes two data-efficient off-policy RL methods that use parametrized Q-learning. In these…

Systems and Control · Electrical Eng. & Systems 2025-04-09 J. S. van Hulst , W. P. M. H. Heemels , D. J. Antunes

This paper studies the partially observed stochastic optimal control problem for systems with state dynamics governed by partial differential equations (PDEs) that leads to an extremely large problem. First, an open-loop deterministic…

Optimization and Control · Mathematics 2017-11-06 Dan Yu , Mohammadhussein Rafieisakhaei , Suman Chakravorty

It is well-known that linear dynamical systems with Gaussian noise and quadratic cost (LQG) satisfy a separation principle. Finding the optimal controller amounts to solving separate dual problems; one for control and one for estimation.…

Systems and Control · Computer Science 2013-09-10 Laurent Lessard , Ashutosh Nayyar

The purpose of this paper is to present a theoretic and numerical study of utilizing squeezing and phase shift in coherent feedback control of linear quantum optical systems. A quadrature representation with built-in phase shifters is…

Quantum Physics · Physics 2012-06-19 Guofeng Zhang , Heung Wing Joseph Lee , Bo Huang , Hu Zhang

Transfer learning for high-dimensional Gaussian graphical models (GGMs) is studied with the goal of estimating the target GGM by utilizing the data from similar and related auxiliary studies. The similarity between the target graph and each…

Methodology · Statistics 2020-10-22 Sai Li , T. Tony Cai , Hongzhe Li

We propose an online learning algorithm that adaptively designs a decentralized linear quadratic regulator when the system model is unknown a priori and new data samples from a single system trajectory become progressively available. The…

Optimization and Control · Mathematics 2024-07-08 Lintao Ye , Ming Chi , Ruiquan Liao , Vijay Gupta

We consider the task of learning to control a linear dynamical system under fixed quadratic costs, known as the Linear Quadratic Regulator (LQR) problem. While model-free approaches are often favorable in practice, thus far only model-based…

Machine Learning · Computer Science 2021-02-26 Asaf Cassel , Tomer Koren

This research paper introduces a model-free optimal controller for discrete-time Markovian jump linear systems (MJLSs), employing principles from the methodology of reinforcement learning (RL). While Q-learning methods have demonstrated…

Systems and Control · Electrical Eng. & Systems 2024-08-07 Ehsan Badfar , Babak Tavassoli

In this paper, we study the linear quadratic (LQ) optimal control problem of linear systems with private input and measurement information. The main challenging lies in the unavailability of other regulators' historical input information.…

Optimization and Control · Mathematics 2023-05-29 Juanjuan Xu , Huanshui Zhang

Recent developments in Reinforcement learning have significantly enhanced sequential decision-making in uncertain environments. Despite their strong performance guarantees, most existing work has focused primarily on improving the…

Statistics Theory · Mathematics 2025-08-13 Bo Pan , Jianya Lu , Yafei Wang , Hao Li , Bei Jiang , Linglong Kong

In this paper, we study the statistical difficulty of learning to control linear systems. We focus on two standard benchmarks, the sample complexity of stabilization, and the regret of the online learning of the Linear Quadratic Regulator…

Machine Learning · Computer Science 2022-05-30 Anastasios Tsiamis , Ingvar Ziemann , Manfred Morari , Nikolai Matni , George J. Pappas

Imitation learning approaches achieve good generalization within the range of the training data, but tend to generate unpredictable motions when querying outside this range. We present a novel approach to imitation learning with enhanced…

Robotics · Computer Science 2022-12-19 Hector Villeda , Justus Piater , Matteo Saveriano

Unlike traditional model-based reinforcement learning approaches that estimate system parameters from data, non-model-based data-driven control learns the optimal policy directly from input-state data without any intermediate model…

Optimization and Control · Mathematics 2026-05-05 Leilei Cui , Zhong-Ping Jiang , Petter N. Kolm , Grégoire G. Macqueron

This paper studies an infinite horizon optimal control problem for discrete-time linear systems and quadratic criteria, both with random parameters which are independent and identically distributed with respect to time. A classical approach…

Optimization and Control · Mathematics 2020-11-11 Kai Du , Qingxin Meng , Fu Zhang

We study transfer learning for estimation in latent variable network models. In our setting, the conditional edge probability matrices given the latent variables are represented by $P$ for the source and $Q$ for the target. We wish to…

Machine Learning · Computer Science 2024-06-07 Akhil Jalan , Arya Mazumdar , Soumendu Sundar Mukherjee , Purnamrita Sarkar