no code implementations • 5 Nov 2023 • Archith Athrey, Othmane Mazhar, Meichen Guo, Bart De Schutter, Shengling Shi
In this paper, we analyze the regret incurred by a computationally efficient exploration strategy, known as naive exploration, for controlling unknown partially observable systems within the Linear Quadratic Gaussian (LQG) framework.
no code implementations • 18 Mar 2022 • Shengling Shi, Othmane Mazhar, Bart De Schutter
To capture the effect of the parameters of the switching strategies on the LS estimation error, finite-sample error bounds are developed in this work.
no code implementations • 3 Feb 2022 • Boualem Djehiche, Othmane Mazhar
Finally, we propose an estimation algorithm for the minimal realization that uses both the Hankel penalized least square estimator and the Ho-Kalman based estimation procedure and guarantees with high probability that we recover the correct order of the system and satisfies a new fast rate in the $S_2$-norm with a polynomial reduction in the dependence on the dimension and other parameters of the problem.
no code implementations • 17 Sep 2021 • Boualem Djehiche, Othmane Mazhar
Our results extend and improve existing lower bounds to lower bounds in expectation of the mean square estimation risk and to systems with a general noise covariance.
no code implementations • ICML 2018 • Othmane Mazhar, Cristian R. Rojas, Carlo Fischione, Mohammad R. Hesamzadeh
We address the new problem of estimating a piece-wise constant signal with the purpose of detecting its change points and the levels of clusters.