Publikation: Evolving Dynamic Collective Behaviors by Minimizing Surprise
Lade...
Dateien
Datum
2023
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
DOI (zitierfähiger Link)
Internationale Patentnummer
Link zur Lizenz
oops
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Open Access Bookpart
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
IIZUKA, Hiroyuki, ed., Keisuke SUZUKI, ed., Ryoko UNO, ed. and others. ALIFE 2023 : Ghost in the Machine : Proceedings of the 2023 Artificial Life Conference. Cambridge, MA: MIT Press, 2023, 50. Available under: doi: 10.1162/isal_a_00650
Zusammenfassung
Our minimize surprise method evolves swarm robot controllers using a task-independent reward for prediction accuracy. Since no specific task is rewarded during optimization, various collective behaviors can emerge, as has also been shown in previous work. But so far, all generated behaviors were static or repetitive allowing for easy sensor predictions due to mostly constant sensor input. Our goal is to generate more dynamic behaviors that vary behavior based on changes in sensor input. We modify environment and agent capabilities, and extend the minimize surprise reward with additional components rewarding homing or curiosity. In preliminary experiments, we were able to generate first dynamic behaviors through our modifications, providing a promising basis for future work.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
ALIFE 2023 : Ghost in the Machine : 2023 Artificial Life Conference (online), 24. Juli 2023 - 28. Juli 2023
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690
KAISER, Tanja Katharina, Christopher KLUTH, Heiko HAMANN, 2023. Evolving Dynamic Collective Behaviors by Minimizing Surprise. ALIFE 2023 : Ghost in the Machine : 2023 Artificial Life Conference (online), 24. Juli 2023 - 28. Juli 2023. In: IIZUKA, Hiroyuki, ed., Keisuke SUZUKI, ed., Ryoko UNO, ed. and others. ALIFE 2023 : Ghost in the Machine : Proceedings of the 2023 Artificial Life Conference. Cambridge, MA: MIT Press, 2023, 50. Available under: doi: 10.1162/isal_a_00650BibTex
@inproceedings{Kaiser2023Evolv-67659,
year={2023},
doi={10.1162/isal_a_00650},
title={Evolving Dynamic Collective Behaviors by Minimizing Surprise},
url={https://direct.mit.edu/isal/proceedings/isal/35/50/116922},
publisher={MIT Press},
address={Cambridge, MA},
booktitle={ALIFE 2023 : Ghost in the Machine : Proceedings of the 2023 Artificial Life Conference},
editor={Iizuka, Hiroyuki and Suzuki, Keisuke and Uno, Ryoko},
author={Kaiser, Tanja Katharina and Kluth, Christopher and Hamann, Heiko},
note={Article Number: 50}
}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/123456789/67659">
<dcterms:title>Evolving Dynamic Collective Behaviors by Minimizing Surprise</dcterms:title>
<dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-08-23T12:15:40Z</dcterms:available>
<dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:contributor>Kluth, Christopher</dc:contributor>
<dc:creator>Kluth, Christopher</dc:creator>
<bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/67659"/>
<foaf:homepage rdf:resource="http://localhost:8080/"/>
<dc:creator>Hamann, Heiko</dc:creator>
<dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-08-23T12:15:40Z</dc:date>
<dcterms:abstract>Our minimize surprise method evolves swarm robot controllers using a task-independent reward for prediction accuracy. Since no specific task is rewarded during optimization, various collective behaviors can emerge, as has also been shown in previous work. But so far, all generated behaviors were static or repetitive allowing for easy sensor predictions due to mostly constant sensor input. Our goal is to generate more dynamic behaviors that vary behavior based on changes in sensor input. We modify environment and agent capabilities, and extend the minimize surprise reward with additional components rewarding homing or curiosity. In preliminary experiments, we were able to generate first dynamic behaviors through our modifications, providing a promising basis for future work.</dcterms:abstract>
<dc:contributor>Kaiser, Tanja Katharina</dc:contributor>
<dcterms:issued>2023</dcterms:issued>
<dc:creator>Kaiser, Tanja Katharina</dc:creator>
<dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/67659/1/Kaiser_2-uq0rd734yig42.pdf"/>
<dc:contributor>Hamann, Heiko</dc:contributor>
<dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/67659/1/Kaiser_2-uq0rd734yig42.pdf"/>
<dc:language>eng</dc:language>
<void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
<dcterms:isPartOf 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
URL der Originalveröffentl.
Prüfdatum der URL
2023-08-01
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
