English
Related papers

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

200 papers

The theory of continuous-time reinforcement learning (RL) has progressed rapidly in recent years. While the ultimate objective of RL is typically to learn deterministic control policies, most existing continuous-time RL methods rely on…

Machine Learning · Computer Science 2026-03-17 Ziheng Cheng , Xin Guo , Yufei Zhang

The stochastic linear--quadratic regulator problem subject to Gaussian disturbances is well known and usually addressed via a moment-based reformulation. Here, we leverage polynomial chaos expansions, which model random variables via series…

Optimization and Control · Mathematics 2025-02-14 Ruchuan Ou , Jonas Schießl , Michael Heinrich Baumann , Lars Grüne , Timm Faulwasser

There has been substantial recent progress on the theoretical understanding of model-free approaches to Linear Quadratic Regulator (LQR) problems. Much attention has been devoted to the special case when the goal is to drive the state close…

Optimization and Control · Mathematics 2021-04-13 Zhaolin Ren , Aoxiao Zhong , Na Li

We consider the policy gradient adaptive control (PGAC) framework, which adaptively updates a control policy in real time, by performing data-based gradient descent steps on the linear quadratic regulator cost. This method has empirically…

Optimization and Control · Mathematics 2026-01-07 Felix Laurent , Feiran Zhao , Jaap Eising , Florian Dörfler

Solutions of optimization problems, including policy optimization in reinforcement learning, typically rely upon some variant of gradient descent. There has been much recent work in the machine learning, control, and optimization…

Machine Learning · Computer Science 2025-07-17 Eduardo D. Sontag

We consider the problem of computing optimal linear control policies for linear systems in finite-horizon. The states and the inputs are required to remain inside pre-specified safety sets at all times despite unknown disturbances. In this…

Systems and Control · Computer Science 2019-12-17 Luca Furieri , Maryam Kamgarpour

Existing work in multi-agent collision prediction and avoidance typically assumes discrete-time trajectories with Gaussian uncertainty or that are completely deterministic. We propose an approach that allows detection of collisions even…

Artificial Intelligence · Computer Science 2014-05-13 Jan-Peter Calliess , Michael Osborne , Stephen Roberts

Introducing inequality constraints in Gaussian process (GP) models can lead to more realistic uncertainties in learning a great variety of real-world problems. We consider the finite-dimensional Gaussian approach from Maatouk and Bay (2017)…

Machine Learning · Statistics 2021-11-04 Andrés F. López-Lopera , François Bachoc , Nicolas Durrande , Olivier Roustant

This paper investigates a class of unified stochastic linear quadratic Gaussian (LQG) social optima problems involving a large number of weakly-coupled interactive agents under a {generalized} setting. For each individual agent, the control…

Optimization and Control · Mathematics 2020-05-15 Zhenghong Qiu , Jianhui Huang , Tinghan Xie

We present a midpoint policy iteration algorithm to solve linear quadratic optimal control problems in both model-based and model-free settings. The algorithm is a variation of Newton's method, and we show that in the model-based setting it…

Optimization and Control · Mathematics 2022-02-16 Benjamin Gravell , Iman Shames , Tyler Summers

Entropy regularization is an efficient technique for encouraging exploration and preventing a premature convergence of (vanilla) policy gradient methods in reinforcement learning (RL). However, the theoretical understanding of…

Machine Learning · Computer Science 2024-07-16 Yuhao Ding , Junzi Zhang , Hyunin Lee , Javad Lavaei

We study stochastic optimal control problems for (possibly degenerate) McKean-Vlasov controlled diffusions and obtain discrete-time as well as finite interacting particle approximations. (i) Under mild assumptions, we first prove the…

Optimization and Control · Mathematics 2025-10-27 Somnath Pradhan , Serdar Yuksel

Data-driven Model Predictive Control (MPC), where the system model is learned from data with machine learning, has recently gained increasing interests in the control community. Gaussian Processes (GP), as a type of statistical models, are…

Systems and Control · Computer Science 2019-10-03 Truong X. Nghiem

This paper concerns discrete-time infinite-horizon stochastic control systems with Borel state and action spaces and universally measurable policies. We study optimization problems on strategic measures induced by the policies in these…

Optimization and Control · Mathematics 2023-12-22 Huizhen Yu

We investigate the problem of learning an $\epsilon$-approximate solution for the discrete-time Linear Quadratic Regulator (LQR) problem via a Stochastic Variance-Reduced Policy Gradient (SVRPG) approach. Whilst policy gradient methods have…

Optimization and Control · Mathematics 2023-09-20 Leonardo F. Toso , Han Wang , James Anderson

We propose a method for finding approximate compilations of quantum unitary transformations, based on techniques from policy gradient reinforcement learning. The choice of a stochastic policy allows us to rephrase the optimization problem…

Quantum Physics · Physics 2022-09-14 David A. Herrera-Martí

This paper develops a general approach to characterize the long-time trajectory behavior of nonconvex gradient descent in generalized single-index models in the large aspect ratio regime. In this regime, we show that for each iteration the…

Machine Learning · Computer Science 2025-09-16 Qiyang Han

Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate the gradient, which…

Machine Learning · Computer Science 2026-05-01 Mohammad Ghavamzadeh , Yaakov Engel , Michal Valko

This paper introduces two variational inference approaches for infinite-dimensional inverse problems, developed through gradient descent with a constant learning rate. The proposed methods enable efficient approximate sampling from the…

Numerical Analysis · Mathematics 2026-03-05 Jiaming Sui , Junxiong Jia , Jinglai Li

This paper develops a policy gradient method for entropy-regularized mean-field control in the discounted infinite-horizon setting. We consider randomized feedback policies and a coupled representative-particle/population system, in which…

Optimization and Control · Mathematics 2026-05-21 Erhan Bayraktar , Martin Hernandez , Qinxin Yan , Yuhua Zhu