English
Related papers

Related papers: Convergence of policy gradient methods for finite-…

200 papers

This paper proposes a receding horizon active learning and control problem for dynamical systems in which Gaussian Processes (GPs) are utilized to model the system dynamics. The active learning objective in the optimization problem is…

Systems and Control · Electrical Eng. & Systems 2021-05-13 Viet-Anh Le , Truong X. Nghiem

The Linear Quadratic Gaussian (LQG) regulator is a cornerstone of optimal control theory, yet its performance can degrade significantly when the noise distributions deviate from the assumed Gaussian model. To address this limitation, this…

Systems and Control · Electrical Eng. & Systems 2026-03-27 Riccardo Cescon , Andrea Martin , Giancarlo Ferrari-Trecate

We consider direct policy optimization for the linear-quadratic Gaussian (LQG) setting. Over the past few years, it has been recognized that the landscape of dynamic output-feedback controllers of relevance to LQG has an intricate geometry,…

Optimization and Control · Mathematics 2024-08-19 Spencer Kraisler , Mehran Mesbahi

We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates across the action when estimating the…

Machine Learning · Statistics 2018-04-17 Kamil Ciosek , Shimon Whiteson

We study the estimation of policy gradients for continuous-time systems with known dynamics. By reframing policy learning in continuous-time, we show that it is possible construct a more efficient and accurate gradient estimator. The…

Machine Learning · Computer Science 2021-06-25 Samuel Ainsworth , Kendall Lowrey , John Thickstun , Zaid Harchaoui , Siddhartha Srinivasa

We study model-free learning methods for the output-feedback Linear Quadratic (LQ) control problem in finite-horizon subject to subspace constraints on the control policy. Subspace constraints naturally arise in the field of distributed…

Systems and Control · Electrical Eng. & Systems 2021-07-14 Luca Furieri , Yang Zheng , Maryam Kamgarpour

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

Machine Learning · Computer Science 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

Stabilizing a dynamical system is a fundamental problem that serves as a cornerstone for many complex tasks in the field of control systems. The problem becomes challenging when the system model is unknown. Among the Reinforcement Learning…

Systems and Control · Electrical Eng. & Systems 2026-01-30 Ankang Zhang , Ming Chi , Xiaoling Wang , Lintao Ye

In this work, we analyze the properties of the solution to the covariance steering problem for discrete time Gaussian linear systems with a squared Wasserstein distance terminal cost. In our previous work, we have shown that by utilizing…

Optimization and Control · Mathematics 2021-03-26 Isin M. Balci , Abhishek Halder , Efstathios Bakolas

This paper investigates an infinite-horizon linear quadratic stochastic (LQS) optimal control problem for a class of continuous-time stochastic systems. By employing the technique of adaptive dynamic programming (ADP), we propose a novel…

Optimization and Control · Mathematics 2022-10-11 Heng Zhang

Projected Gradient Descent denotes a class of iterative methods for solving optimization programs. Its applicability to convex optimization programs has gained significant popularity for its intuitive implementation that involves only…

Optimization and Control · Mathematics 2016-10-24 Giampaolo Torrisi , Sergio Grammatico , Roy S. Smith , Manfred Morari

We study the sequential decision making problem of maximizing the expected total reward while satisfying a constraint on the expected total utility. We employ the natural policy gradient method to solve the discounted infinite-horizon…

Optimization and Control · Mathematics 2025-10-16 Dongsheng Ding , Kaiqing Zhang , Jiali Duan , Tamer Başar , Mihailo R. Jovanović

Model-free reinforcement learning attempts to find an optimal control action for an unknown dynamical system by directly searching over the parameter space of controllers. The convergence behavior and statistical properties of these…

Optimization and Control · Mathematics 2021-03-17 Hesameddin Mohammadi , Armin Zare , Mahdi Soltanolkotabi , Mihailo R. Jovanović

This paper focuses on the linear quadratic control (LQC) design of systems corrupted by both stochastic noise and bounded noise simultaneously. When only of these noises are considered, the LQC strategy leads to stochastic or robust…

Optimization and Control · Mathematics 2025-12-15 Xuehui Ma , Shiliang Zhang , Xiaohui Zhang , Jing Xin , Hector Garcia de Marina

We study the global convergence of a Fisher-Rao policy gradient flow for infinite-horizon entropy-regularised Markov decision processes with Polish state and action space. The flow is a continuous-time analogue of a policy mirror descent…

Optimization and Control · Mathematics 2025-06-09 Bekzhan Kerimkulov , James-Michael Leahy , David Siska , Lukasz Szpruch , Yufei Zhang

Despite its nonconvexity, policy optimization for the Linear Quadratic Regulator (LQR) admits a favorable structural property known as gradient dominance, which facilitates linear convergence of policy gradient methods to the globally…

Optimization and Control · Mathematics 2026-02-27 Yuto Watanabe , Yang Zheng

We study the distributed Linear Quadratic Gaussian (LQG) control problem in discrete-time and finite-horizon, where the controller depends linearly on the history of the outputs and it is required to lie in a given subspace, e.g. to possess…

Systems and Control · Electrical Eng. & Systems 2021-07-14 Luca Furieri , Maryam Kamgarpour

Generalized Polynomial Chaos (gPC) theory has been widely used for representing parametric uncertainty in a system, thanks to its ability to propagate uncertainty evolution. In an optimal control context, gPC can be combined with several…

Optimization and Control · Mathematics 2021-10-05 Yuichiro Aoyama , Augustinos D. Saravanos , Evangelos A. Theodorou

This work explores generalizations of the Polyak-Lojasiewicz inequality (PLI) and their implications for the convergence behavior of gradient flows in optimization problems. Motivated by the continuous-time linear quadratic regulator…

Optimization and Control · Mathematics 2025-04-01 Arthur Castello B. de Oliveira , Leilei Cui , Eduardo D. Sontag

The enduring challenge in the field of artificial intelligence has been the control of systems to achieve desired behaviours. While for systems governed by straightforward dynamics equations, methods like Linear Quadratic Regulation (LQR)…

Machine Learning · Computer Science 2023-12-29 Jyothir S , Siddhartha Jalagam , Yann LeCun , Vlad Sobal
‹ Prev 1 4 5 6 7 8 10 Next ›