User: Guest  Login
Document type:
Zeitschriftenaufsatz 
Author(s):
A. Capone; A. Lederer; J. Umlauft; S. Hirche 
Title:
Data Selection for Multi-Task Learning Under Dynamic Constraints 
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 
Journal title:
IEEE Control Systems Letters 
Year:
2020 
Journal volume:
Journal issue:
Pages contribution:
959-964 
Publisher:
Institute of Electrical and Electronics Engineers (IEEE) 
E-ISSN:
2475-1456 
Date of publication:
01.07.2021