Model-free design of stochastic LQR controller from a primal-dual optimization perspective

DOI10.1016/j.automatica.2022.110253zbMath1485.93636arXiv2103.09407OpenAlexW4223502737MaRDI QIDQ2125546

Man Li, Yaonan Wang, Wei Xing Zheng, Jiahu Qin, Yu Kang

Publication date: 14 April 2022

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2103.09407

zbMATH Keywords

optimizationdualityreinforcement learningmodel-free designstochastic linear-quadratic regulator

Mathematics Subject Classification ID

Optimal stochastic control (93E20) Linear-quadratic optimal control problems (49N10)

Related Items (3)

An inertial neural network approach for loco-manipulation trajectory tracking of mobile robot with redundant manipulator ⋮ An adaptive dynamic programming-based algorithm for infinite-horizon linear quadratic stochastic optimal control problems ⋮ Model-free optimal control of discrete-time systems with additive and multiplicative noises

Cites Work

• Unnamed Item
• Unnamed Item
• Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics
• \(\mathrm{H}_\infty\) control of linear discrete-time systems: off-policy reinforcement learning
• Deep reinforcement learning for wireless sensor scheduling in cyber-physical systems
• On the sample complexity of the linear quadratic regulator
• Stochastic Linear-Quadratic Control via Semidefinite Programming
• Discrete-Time Linear Systems
• Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
• Primal-Dual Q-Learning Framework for LQR Design
• Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles
• Stability Analysis of Discrete-Time Infinite-Horizon Optimal Control With Discounted Cost

This page was built for publication: Model-free design of stochastic LQR controller from a primal-dual optimization perspective