Convergence and Sample Complexity of Gradient Methods for the Model-Free Linear–Quadratic Regulator Problem

DOI10.1109/TAC.2021.3087455MaRDI QIDQ5092135

Armin Zare, Mihailo R. Jovanović, Mahdi Soltanolkotabi, Hesameddin Mohammadi

Publication date: 28 July 2022

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1912.11899

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Related Items (7)

Analysis of the optimization landscape of Linear Quadratic Gaussian (LQG) control ⋮ A Lyapunov characterization of robust policy optimization ⋮ Minimum input design for direct data-driven property identification of unknown linear systems ⋮ Optimizing Static Linear Feedback: Gradient Method ⋮ Policy Optimization for $\mathcal{H}_2$ Linear Control with $\mathcal{H}_\infty$ Robustness Guarantee: Implicit Regularization and Global Convergence ⋮ Model-free linear quadratic regulator ⋮ Controlled interacting particle algorithms for simulation-based reinforcement learning

This page was built for publication: Convergence and Sample Complexity of Gradient Methods for the Model-Free Linear–Quadratic Regulator Problem