Efficient Learning of Distributed Linear-Quadratic Control Policies

DOI10.1137/19M1291108zbMath1450.49017arXiv1909.09895OpenAlexW3089959184MaRDI QIDQ5130900

Nikolai Matni, Salar Fattahi, Somayeh Sojoudi

Publication date: 29 October 2020

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1909.09895

zbMATH Keywords

constrained optimizationnetworked systemsoptimal distributed control

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Numerical methods based on nonlinear programming (49M37) Discrete-time control/observation systems (93C55) Linear-quadratic optimal control problems (49N10) Linear optimal control problems (49N05)

Related Items (3)

Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon ⋮ Model-based and model-free designs for an extended continuous-time LQR with exogenous inputs ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Dynamic system identification. Experiment design and data analysis
• On the sample complexity of the linear quadratic regulator
• A convex characterization of distributed control problems in spatially invariant systems with communication constraints
• On the complexity of decentralized decision making and detection problems
• Sparse and Redundant Representations
• Separable and Localized System-Level Synthesis for Large-Scale Systems
• A System-Level Approach to Controller Synthesis
• Distributed Control of Heterogeneous Systems
• A Characterization of Convex Problems in Decentralized Control$^ast$

This page was built for publication: Efficient Learning of Distributed Linear-Quadratic Control Policies