Statistical learning theory for control: A finite-sample perspective

A Tsiamis, I Ziemann, N Matni… - IEEE Control Systems …, 2023 - ieeexplore.ieee.org
Learning algorithms have become an integral component to modern engineering solutions.
Examples range from self-driving cars and recommender systems to finance and even …

Certainty equivalence is efficient for linear quadratic control

H Mania, S Tu, B Recht - Advances in Neural Information …, 2019 - proceedings.neurips.cc
We study the performance of the certainty equivalent controller on Linear Quadratic (LQ)
control problems with unknown transition dynamics. We show that for both the fully and …

Policy optimization provably converges to Nash equilibria in zero-sum linear quadratic games

K Zhang, Z Yang, T Basar - Advances in Neural Information …, 2019 - proceedings.neurips.cc
We study the global convergence of policy optimization for finding the Nash equilibria (NE)
in zero-sum linear quadratic (LQ) games. To this end, we first investigate the landscape of …

[图书][B] Numerical solution of algebraic Riccati equations

DA Bini, B Iannazzo, B Meini - 2011 - SIAM
This monograph aims to provide a concise and comprehensive treatment of the basic theory
of algebraic Riccati equations and a description of both the classical and the more advanced …

[图书][B] Perturbation theory for matrix equations

M Konstantinov, DW Gu, V Mehrmann, P Petkov - 2003 - books.google.com
The book is devoted to the perturbation analysis of matrix equations. The importance of
perturbation analysis is that it gives a way to estimate the influence of measurement and/or …

Minimal expected regret in linear quadratic control

Y Jedra, A Proutiere - International Conference on Artificial …, 2022 - proceedings.mlr.press
We consider the problem of online learning in Linear Quadratic Control systems whose state
transition and state-action transition matrices $ A $ and $ B $ may be initially unknown. We …

Perturbation theory for algebraic Riccati equations

JG Sun - SIAM Journal on Matrix Analysis and Applications, 1998 - SIAM
Perturbation Theory for Algebraic Riccati Equations Page 1 PERTURBATION THEORY FOR
ALGEBRAIC RICCATI EQUATIONS∗ JI-GUANG SUN† SIAM J. MATRIX ANAL. APPL. c 1998 …

A data-driven Riccati equation

A Rantzer - 6th Annual Learning for Dynamics & Control …, 2024 - proceedings.mlr.press
Certainty equivalence adaptive controllers are analysed using a “data-driven Riccati
equation”, corresponding to the model-free Bellman equation used in Q-learning. The …

Benchmarks for the numerical solution of algebraic Riccati equations

P Benner, AJ Laub, V Mehrmann - IEEE Control Systems …, 1997 - ieeexplore.ieee.org
Two collections of benchmark examples are presented for the numerical solution of
continuous-time and discrete-time algebraic Riccati equations. These collections may serve …

[图书][B] Sample complexity bounds for the linear quadratic regulator

SL Tu - 2019 - search.proquest.com
Reinforcement learning (RL) has demonstrated impressive performance in various domains
such as video games, Go, robotic locomotion, and manipulation tasks. As we turn towards …