Online learning of parameterized uncertain dynamical environments with finite-sample guarantees

Dan Li, Dariush Fooladivanda, and Sonia Martínez
Proceedings of the 2021 American Control Conference, New Orleans, LA, USA, July 2021

Abstract:

We present a novel online learning algorithm for a class of unknown and uncertain dynamical environments that are fully observable. First, we obtain a novel probabilistic characterization of systems whose mean behavior is known but which are subject to additive, unknown subGaussian disturbances. This characterization relies on recent concentration of measure results and is given in terms of ambiguity sets. Second, we extend the results to environments whose mean behavior is also unknown but described by a parameterized class of possible mean behaviors. Our algorithm adapts the ambiguity set dynamically by learning the parametric dependence online, and retaining similar probabilistic guarantees with respect to the additive, unknown disturbance. We illustrate the results on a differential-drive robot subject to environmental uncertainty.

File: main.pdf

Bib-tex entry:

@InProceedings{DL-DF-SM:21-acc,
author = {D. Li and D. Fooladivanda and S. Mart{\'\i}nez},
title = {Online learning of parameterized uncertain dynamical environments with finite-sample guarantees},
booktitle = {2021 American Control Conference},
pages = {},
year = {2021},
address = {New Orleans, LA, USA},
month = {July}
}