Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms

Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms

Off-line neuro-evolution produces robot swarms whose good performance in simulation does not often transfer to the real word. With an extensive empirical study, Hasselmann et al. substantiate overfitting as the dominant cause.

Bibliographic Details
Main Authors: Ken Hasselmann, Antoine Ligot, Julian Ruddick, Mauro Birattari
Format: Article
Language:English
Published: Nature Publishing Group 2021-07-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-021-24642-3
id doaj-d3ec80f81eaf4edb9cabe5d2a8fda60d
record_format Article
spelling doaj-d3ec80f81eaf4edb9cabe5d2a8fda60d2021-07-18T11:42:53ZengNature Publishing GroupNature Communications2041-17232021-07-0112111110.1038/s41467-021-24642-3Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarmsKen Hasselmann0Antoine Ligot1Julian Ruddick2Mauro Birattari3IRIDIA, Université libre de BruxellesIRIDIA, Université libre de BruxellesIRIDIA, Université libre de BruxellesIRIDIA, Université libre de BruxellesOff-line neuro-evolution produces robot swarms whose good performance in simulation does not often transfer to the real word. With an extensive empirical study, Hasselmann et al. substantiate overfitting as the dominant cause.https://doi.org/10.1038/s41467-021-24642-3
collection DOAJ
language English
format Article
sources DOAJ
author Ken Hasselmann
Antoine Ligot
Julian Ruddick
Mauro Birattari
spellingShingle Ken Hasselmann
Antoine Ligot
Julian Ruddick
Mauro Birattari
Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms
Nature Communications
author_facet Ken Hasselmann
Antoine Ligot
Julian Ruddick
Mauro Birattari
author_sort Ken Hasselmann
title Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms
title_short Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms
title_full Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms
title_fullStr Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms
title_full_unstemmed Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms
title_sort empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms
publisher Nature Publishing Group
series Nature Communications
issn 2041-1723
publishDate 2021-07-01
description Off-line neuro-evolution produces robot swarms whose good performance in simulation does not often transfer to the real word. With an extensive empirical study, Hasselmann et al. substantiate overfitting as the dominant cause.
url https://doi.org/10.1038/s41467-021-24642-3
work_keys_str_mv AT kenhasselmann empiricalassessmentandcomparisonofneuroevolutionarymethodsfortheautomaticofflinedesignofrobotswarms
AT antoineligot empiricalassessmentandcomparisonofneuroevolutionarymethodsfortheautomaticofflinedesignofrobotswarms
AT julianruddick empiricalassessmentandcomparisonofneuroevolutionarymethodsfortheautomaticofflinedesignofrobotswarms
AT maurobirattari empiricalassessmentandcomparisonofneuroevolutionarymethodsfortheautomaticofflinedesignofrobotswarms
_version_ 1721295946921279488

Similar Items