Analysis of the optimization landscape of Linear Quadratic Gaussian (LQG) control
From MaRDI portal
Publication:6052067
DOI10.1007/s10107-023-01938-4zbMath1525.49029arXiv2102.04393OpenAlexW3128710479MaRDI QIDQ6052067
Publication date: 23 October 2023
Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2102.04393
Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30) Feedback control (93B52) Optimal stochastic control (93E20) Linear-quadratic optimal control problems (49N10)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- A geometric analysis of phase retrieval
- On the optimization landscape of tensor decompositions
- On the sample complexity of the linear quadratic regulator
- Introduction to Smooth Manifolds
- The optimal projection equations for fixed-order dynamic compensation
- A note on balanced controller reduction
- Optimal constant controllers for stochastic linear systems
- Modern Wiener-Hopf design of optimal controllers--Part II: The multivariable case
- LMI-based controller synthesis: a unified formulation and solution
- A linear matrix inequality approach to H∞ control
- Linear Matrix Inequalities in System and Control Theory
- Multiobjective output-feedback control via LMI optimization
- Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
- Convergence and Sample Complexity of Gradient Methods for the Model-Free Linear–Quadratic Regulator Problem
- Connectivity Properties of the Set of Stabilizing Static Decentralized Controllers
- Optimizing Static Linear Feedback: Gradient Method
- A System-Level Approach to Controller Synthesis
- Symmetry, Saddle Points, and Global Optimization Landscape of Nonconvex Matrix Factorization
- Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
- Convergence of the Iterates of Descent Methods for Analytic Cost Functions
- On the Equivalence of Youla, System-Level, and Input–Output Parameterizations
- On Topological Properties of the Set of Stabilizing Feedback Gains
- Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach
