Logarithmic regret in online linear quadratic control using Riccati updates
An online policy learning problem of linear control systems is studied. In this problem, the
control system is known and linear, and a sequence of quadratic cost functions is revealed …
control system is known and linear, and a sequence of quadratic cost functions is revealed …
Achieving logarithmic regret via hints in online learning of noisy lqr systems
M Akbari, B Gharesifard, T Linder - 2022 IEEE 61st Conference …, 2022 - ieeexplore.ieee.org
We consider the problem of online adaptive control of a linear-quadratic system, where the
true system transition parameters (matrices A and B) are unknown. The objective is to …
true system transition parameters (matrices A and B) are unknown. The objective is to …
Logarithmic Regret in Adaptive Control of Noisy Linear Quadratic Regulator Systems Using Hints
M Akbari, B Gharesifard, T Linder - arXiv preprint arXiv:2210.16303, 2022 - arxiv.org
The problem of regret minimization for online adaptive control of linear-quadratic systems is
studied. In this problem, the true system transition parameters (matrices $ A $ and $ B $) are …
studied. In this problem, the true system transition parameters (matrices $ A $ and $ B $) are …
Online Learning in Control Theory
M Akbari Varnousfaderani - 2022 - qspace.library.queensu.ca
In this thesis, we study two classes of problems in optimal control theory involving unknown
parameters, with focus on Linear-Quadratic-Gaussian systems. In the first problem, the …
parameters, with focus on Linear-Quadratic-Gaussian systems. In the first problem, the …
Online Learning in Control Theory
MA Varnousfaderani - 2022 - search.proquest.com
Online Learning in Control Theory Page 1 Online Learning in Control Theory by Mohammad
Akbari Varnousfaderani A thesis submitted to the Department of Mathematics and Statistics in …
Akbari Varnousfaderani A thesis submitted to the Department of Mathematics and Statistics in …