User: Guest  Login
Title:

Data Selection for Multi-Task Learning Under Dynamic Constraints

Document type:
Zeitschriftenaufsatz
Author(s):
A. Capone; A. Lederer; J. Umlauft; S. Hirche
Abstract:
Learning-based techniques are increasingly effective at controlling complex systems. However, most work done so far has focused on learning control laws for individual tasks. Simultaneously learning multiple tasks on the same system is still a largely unaddressed research question. In particular, no efficient state space exploration schemes have been designed for multi-task control settings. Using this research gap as our main motivation, we present an algorithm that approximates the smallest da...     »
Keywords:
data_driven_control; coman
Journal title:
IEEE Control Systems Letters
Year:
2020
Journal volume:
5
Year / month:
2020-07
Journal issue:
3
Pages contribution:
959-964
Fulltext / DOI:
doi:10.1109/lcsys.2020.3006279
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
E-ISSN:
2475-1456
Date of publication:
01.07.2021
 BibTeX