The Impact of Data on the Stability of Learning-Based Control

Armin Lederer, Alexandre Capone, Thomas Beckers, Jonas Umlauft, Sandra Hirche
Proceedings of the 3rd Conference on Learning for Dynamics and Control, PMLR 144:623-635, 2021.

Abstract

Despite the existence of formal guarantees for learning-based control approaches, the relationship between data and control performance is still poorly understood. In this paper, we present a measure to quantify the value of data within the context of a predefined control task. Our approach is applicable to a wide variety of unknown nonlinear systems that are to be controlled by a generic learning-based control law. We model the unknown component of the system using Gaussian processes, which in turn allows us to directly assess the impact of model uncertainty on control. Results obtained in numerical simulations indicate the efficacy of the proposed measure.

Cite this Paper

BibTeX
@InProceedings{pmlr-v144-lederer21a, title = {The Impact of Data on the Stability of Learning-Based Control}, author = {Lederer, Armin and Capone, Alexandre and Beckers, Thomas and Umlauft, Jonas and Hirche, Sandra}, booktitle = {Proceedings of the 3rd Conference on Learning for Dynamics and Control}, pages = {623--635}, year = {2021}, editor = {Jadbabaie, Ali and Lygeros, John and Pappas, George J. and A. Parrilo, Pablo and Recht, Benjamin and Tomlin, Claire J. and Zeilinger, Melanie N.}, volume = {144}, series = {Proceedings of Machine Learning Research}, month = {07 -- 08 June}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v144/lederer21a/lederer21a.pdf}, url = {https://proceedings.mlr.press/v144/lederer21a.html}, abstract = {Despite the existence of formal guarantees for learning-based control approaches, the relationship between data and control performance is still poorly understood. In this paper, we present a measure to quantify the value of data within the context of a predefined control task. Our approach is applicable to a wide variety of unknown nonlinear systems that are to be controlled by a generic learning-based control law. We model the unknown component of the system using Gaussian processes, which in turn allows us to directly assess the impact of model uncertainty on control. Results obtained in numerical simulations indicate the efficacy of the proposed measure.} }
Endnote
%0 Conference Paper %T The Impact of Data on the Stability of Learning-Based Control %A Armin Lederer %A Alexandre Capone %A Thomas Beckers %A Jonas Umlauft %A Sandra Hirche %B Proceedings of the 3rd Conference on Learning for Dynamics and Control %C Proceedings of Machine Learning Research %D 2021 %E Ali Jadbabaie %E John Lygeros %E George J. Pappas %E Pablo A. Parrilo %E Benjamin Recht %E Claire J. Tomlin %E Melanie N. Zeilinger %F pmlr-v144-lederer21a %I PMLR %P 623--635 %U https://proceedings.mlr.press/v144/lederer21a.html %V 144 %X Despite the existence of formal guarantees for learning-based control approaches, the relationship between data and control performance is still poorly understood. In this paper, we present a measure to quantify the value of data within the context of a predefined control task. Our approach is applicable to a wide variety of unknown nonlinear systems that are to be controlled by a generic learning-based control law. We model the unknown component of the system using Gaussian processes, which in turn allows us to directly assess the impact of model uncertainty on control. Results obtained in numerical simulations indicate the efficacy of the proposed measure.
APA
Lederer, A., Capone, A., Beckers, T., Umlauft, J. & Hirche, S.. (2021). The Impact of Data on the Stability of Learning-Based Control. Proceedings of the 3rd Conference on Learning for Dynamics and Control, in Proceedings of Machine Learning Research 144:623-635 Available from https://proceedings.mlr.press/v144/lederer21a.html.

Related Material