Model-free LQR design by Q-function learning

DOI10.1016/j.automatica.2021.110060zbMath1485.93031OpenAlexW4200561738MaRDI QIDQ2071928

Maryam Babazadeh, Milad Farjadnasab

Publication date: 31 January 2022

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2021.110060

zbMATH Keywords

convex optimizationdistributed controlQ-learningsemi-definite programming (SDP)linear quadratic regulation (LQR)

Mathematics Subject Classification ID

Semidefinite programming (90C22) Convex programming (90C25) Feedback control (93B52) Linear systems in control theory (93C05) Linear-quadratic optimal control problems (49N10) Large-scale systems (93A15)

Related Items (1)

Data‐assisted control: A framework development by exploiting NASA Generic Transport platform

Uses Software

• CVX

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Robust controllability assessment and optimal actuator placement in dynamic networks
• A note on persistency of excitation
• Linear Matrix Inequalities in System and Control Theory
• Linear matrix inequalities, Riccati equations, and indefinite stochastic linear quadratic controls
• Sparsity Promotion in State Feedback Controller Design
• Adaptive Leader–Follower Synchronization Over Heterogeneous and Uncertain Networks of Linear Systems Without Distributed Observer
• Formulas for Data-Driven Control: Stabilization, Optimality, and Robustness
• Primal-Dual Q-Learning Framework for LQR Design
• Distributed Adaptive Control of Synchronization in Complex Networks
• Design of Optimal Sparse Feedback Gains via the Alternating Direction Method of Multipliers
• On the Construction and Comparison of Difference Schemes

This page was built for publication: Model-free LQR design by Q-function learning