Data-driven robust linear quadratic regulator: A minimax design using reinforcement learning
Authors:
- Haoran MaHMHaoran Ma
- Zhengen ZhaoZZZhengen Zhao
- Ying YangYYYing Yang
- 10 April 2025
- journal article
- Published by Elsevier in Automatica
- Vol. 177
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (T2121002, 62173003, 62473195)
This publication has 34 references indexed in Scilit:
- Output‐feedback Q‐learning for discrete‐time linear H∞ tracking control: A Stackelberg game approachInternational Journal of Robust and Nonlinear Control, 2022
- Model-free LQR design by Q-function learningAutomatica, 2022
- Low-complexity learning of Linear Quadratic Regulators from noisy dataAutomatica, 2021
- On the Sample Complexity of the Linear Quadratic RegulatorFoundations of Computational Mathematics, 2019
- control of linear discrete-time systems: Off-policy reinforcement learningAutomatica, 2017
- Model-free Q-learning designs for linear discrete-time zero-sum games with application to H-infinity controlAutomatica, 2007
- A note on persistency of excitationSystems & Control Letters, 2005
- From experiment design to closed-loop controlAutomatica, 2005
- A convex approach to robust performance analysisAutomatica, 2002
- LQG control with an H/sup infinity / performance bound: a Riccati equation approachIEEE Transactions on Automatic Control, 1989