English
Related papers

Related papers: A Globally Convergent Policy Gradient Method for L…

200 papers

Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. They learn stochastic parametric (hyper)policies by either exploring in the space of actions or in the space of parameters.…

Machine Learning · Computer Science 2024-05-31 Alessandro Montenegro , Marco Mussi , Alberto Maria Metelli , Matteo Papini

This paper presents a one-shot learning approach with performance and robustness guarantees for the linear quadratic regulator (LQR) control of stochastic linear systems. Even though data-based LQR control has been widely considered,…

Systems and Control · Electrical Eng. & Systems 2024-10-29 Ramin Esmzad , Hamidreza Modares

The Linear Quadratic Gaussian (LQG) controller is known to be inherently fragile to model misspecifications common in real-world situations. We consider discrete-time partially observable stochastic linear systems and provide a…

Optimization and Control · Mathematics 2025-07-31 Marta Fochesato , Lucia Falconi , Mattia Zorzi , Augusto Ferrante , John Lygeros

Natural policy gradient (NPG) and its variants are widely-used policy search methods in reinforcement learning. Inspired by prior work, a new NPG variant coined NPG-HM is developed in this paper, which utilizes the Hessian-aided momentum…

Machine Learning · Computer Science 2024-01-23 Jie Feng , Ke Wei , Jinchi Chen

Linear Quadratic Regulator (LQR) design is one of the most classical optimal control problems, whose well-known solution is an input sequence expressed as a state-feedback. In this work, finite-horizon and discrete-time LQR is solved under…

Optimization and Control · Mathematics 2020-01-17 Anna Scampicchio , Aleksandr Aravkin , Gianluigi Pillonetto

In recent times, significant advancements have been made in delving into the optimization landscape of policy gradient methods for achieving optimal control in linear time-invariant (LTI) systems. Compared with state-feedback control,…

Optimization and Control · Mathematics 2023-10-31 Jingliang Duan , Jie Li , Xuyang Chen , Kai Zhao , Shengbo Eben Li , Lin Zhao

Policy gradient (PG) methods are popular and efficient for large-scale reinforcement learning due to their relative stability and incremental nature. In recent years, the empirical success of PG methods has led to the development of a…

Machine Learning · Computer Science 2022-05-24 Yuhao Ding , Junzi Zhang , Javad Lavaei

In networked control systems, often the sensory signals are quantized before being transmitted to the controller. Consequently, performance is affected by the coarseness of this quantization process. Modern communication technologies allow…

Systems and Control · Electrical Eng. & Systems 2021-02-23 Dipankar Maity , Panagiotis Tsiotras

Most of the real-time implementations of the stabilizing optimal control actions suffer from the necessity to provide high computational effort. This paper presents a cutting-edge approach for real-time evaluation of linear-quadratic model…

Systems and Control · Electrical Eng. & Systems 2023-09-11 Kristína Fedorová , Yuning Jiang , Juraj Oravec , Colin N. Jones , Michal Kvasnica

Risk-aware control, though with promise to tackle unexpected events, requires a known exact dynamical model. In this work, we propose a model-free framework to learn a risk-aware controller with a focus on the linear system. We formulate it…

Systems and Control · Electrical Eng. & Systems 2021-06-01 Feiran Zhao , Keyou You

This paper presents a state and state-input constrained variant of the discrete-time iterative Linear Quadratic Regulator (iLQR) algorithm, with linear time-complexity in the number of time steps. The approach is based on a projection of…

Robotics · Computer Science 2018-05-25 Markus Giftthaler , Jonas Buchli

We develop a variational approach to address risk-sensitive optimal control problems with an exponential-of-integral cost functional in a general linear-quadratic-Gaussian (LQG) single-agent setup, offering new insights into such problems.…

Optimization and Control · Mathematics 2025-03-28 Hanchao Liu , Dena Firoozi , Michèle Breton

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

We present an algorithm which combines recent advances in model based path integral control with machine learning approaches to learning forward dynamics models. We take advantage of the parallel computing power of a GPU to quickly take a…

Robotics · Computer Science 2015-03-03 Grady Williams , Eric Rombokas , Tom Daniel

We present an output feedback stochastic model predictive control (SMPC) approach for linear systems subject to Gaussian disturbances and measurement noise and probabilistic constraints on system states and inputs. The presented approach…

Systems and Control · Electrical Eng. & Systems 2023-11-20 Simon Muntwiler , Kim P. Wabersich , Robert Miklos , Melanie N. Zeilinger

We consider a variant of the classical linear quadratic Gaussian regulator (LQG) in which penalties on the endpoint state are replaced by the specification of the terminal state distribution. The resulting theory considerably differs from…

Optimization and Control · Mathematics 2015-03-18 Yongxin Chen , Tryphon Georgiou , Michele Pavon

In this paper, we propose a novel linear quadratic Gaussian controller whose parameters can be automatically tuned. While linear quadratic regulator method has been widely used in adaptive cruise control system design, researchers have not…

Systems and Control · Electrical Eng. & Systems 2020-12-01 Yuncheng Jiang , Lilong Cai , Xiaofeng Jin

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

A controller design technique for shaping the frequency response of a process is described. A general linear model (GLM) is used to define the form of a lag or lead compensator in discrete time using a prescribed set of basis functions. The…

Systems and Control · Computer Science 2015-07-21 Hugh L. Kennedy

Data-driven control benefits from rich datasets, but constructing such datasets becomes challenging when gathering data is limited. We consider an offline experiment design approach to gathering data where we design a control input to…

Systems and Control · Electrical Eng. & Systems 2024-05-22 Sean Anderson , João Pedro Hespanha