The Effect of Fitness Function Design on Performance in Evolutionary Robotics : The Influence of a Priori Knowledge

Lade...
Vorschaubild
Dateien
Zu diesem Dokument gibt es keine Dateien.
Datum
2015
Autor:innen
Divband Soorati, Mohammad
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
ArXiv-ID
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
SILVA, Sara, ed. and others. GECCO Companion '15 : Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation. New York, NY: ACM, 2015, pp. 153-160. ISBN 978-1-4503-3472-3. Available under: doi: 10.1145/2739480.2754676
Zusammenfassung

Fitness function design is known to be a critical feature of the evolutionary-robotics approach. Potentially, the complexity of evolving a successful controller for a given task can be reduced by integrating a priori knowledge into the fitness function which complicates the comparability of studies in evolutionary robotics. Still, there are only few publications that study the actual effects of different fitness functions on the robot's performance. In this paper, we follow the fitness function classification of Nelson et al. (2009) and investigate a selection of four classes of fitness functions that require different degrees of a priori knowledge. The robot controllers are evolved in simulation using NEAT and we investigate different tasks including obstacle avoidance and (periodic) goal homing. The best evolved controllers were then post-evaluated by examining their potential for adaptation, determining their convergence rates, and using cross-comparisons based on the different fitness function classes. The results confirm that the integration of more a priori knowledge can simplify a task and show that more attention should be paid to fitness function classes when comparing different studies.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
GECCO '15 : Annual Conference on Genetic and Evolutionary Computation, 11. Juli 2015 - 15. Juli 2015, Madrid, Spain
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690DIVBAND SOORATI, Mohammad, Heiko HAMANN, 2015. The Effect of Fitness Function Design on Performance in Evolutionary Robotics : The Influence of a Priori Knowledge. GECCO '15 : Annual Conference on Genetic and Evolutionary Computation. Madrid, Spain, 11. Juli 2015 - 15. Juli 2015. In: SILVA, Sara, ed. and others. GECCO Companion '15 : Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation. New York, NY: ACM, 2015, pp. 153-160. ISBN 978-1-4503-3472-3. Available under: doi: 10.1145/2739480.2754676
BibTex
@inproceedings{DivbandSoorati2015Effec-59891,
  year={2015},
  doi={10.1145/2739480.2754676},
  title={The Effect of Fitness Function Design on Performance in Evolutionary Robotics : The Influence of a Priori Knowledge},
  isbn={978-1-4503-3472-3},
  publisher={ACM},
  address={New York, NY},
  booktitle={GECCO Companion '15 : Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation},
  pages={153--160},
  editor={Silva, Sara},
  author={Divband Soorati, Mohammad and Hamann, Heiko}
}
RDF
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/59891">
    <dc:contributor>Hamann, Heiko</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/59891"/>
    <dcterms:title>The Effect of Fitness Function Design on Performance in Evolutionary Robotics : The Influence of a Priori Knowledge</dcterms:title>
    <dcterms:abstract xml:lang="eng">Fitness function design is known to be a critical feature of the evolutionary-robotics approach. Potentially, the complexity of evolving a successful controller for a given task can be reduced by integrating a priori knowledge into the fitness function which complicates the comparability of studies in evolutionary robotics. Still, there are only few publications that study the actual effects of different fitness functions on the robot's performance. In this paper, we follow the fitness function classification of Nelson et al. (2009) and investigate a selection of four classes of fitness functions that require different degrees of a priori knowledge. The robot controllers are evolved in simulation using NEAT and we investigate different tasks including obstacle avoidance and (periodic) goal homing. The best evolved controllers were then post-evaluated by examining their potential for adaptation, determining their convergence rates, and using cross-comparisons based on the different fitness function classes. The results confirm that the integration of more a priori knowledge can simplify a task and show that more attention should be paid to fitness function classes when comparing different studies.</dcterms:abstract>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-01-23T13:21:34Z</dc:date>
    <dc:language>eng</dc:language>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-01-23T13:21:34Z</dcterms:available>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Divband Soorati, Mohammad</dc:contributor>
    <dc:creator>Hamann, Heiko</dc:creator>
    <dc:creator>Divband Soorati, Mohammad</dc:creator>
    <dcterms:issued>2015</dcterms:issued>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
URL der Originalveröffentl.
Prüfdatum der URL
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Nein
Begutachtet
Diese Publikation teilen