Evolving Diverse Collective Behaviors Independent of Swarm Density

Zahadat, Payam; Hamann, Heiko; Schmickl, Thomas

Evolving Diverse Collective Behaviors Independent of Swarm Density

Files

There are no files associated with this item.

Date

2015

Authors

Zahadat, Payam

Hamann, Heiko

Schmickl, Thomas

Publication type

Contribution to a conference collection

Publication status

Published

Published in

GECCO Companion '15 : Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation / Silva, Sara et al. (ed.). - New York, NY : ACM, 2015. - pp. 1245-1246. - ISBN 978-1-4503-3488-4

Abstract

There are multiple different ways of implementing artificial evolution of collective behaviors. Besides a classical offline evolution approach, there is, for example, the option of environment-driven distributed evolutionary adaptation in the form of an artificial ecology [2] and more generally there is the approach of embodied evolution [1,3,6]. Another recently reported approach is the application of novelty search to swarm robotics [5]. In the following, we report an extension of the approach of [7]. The underlying concept is an information-theoretic analogon to thermodynamic (Helmholtz) free energy [8]. The assumption is that the brain is permanently trying to predict future perceptions and that minimizing the prediction error is basically inherent to brains. This is defined by the 'free-energy principle' of [4]. The struggle for prediction success requires a complementary force that represents curiosity and exploration. In this abstract we present an extended method called diverse-prediction that rewards not only for correct predictions but also for each visited sensory state. This proves to be a better approach compared to the method prediction that was reported before[7].

Subject (DDC)

004 Computer Science

Conference

GECCO '15 : Annual Conference on Genetic and Evolutionary Computation, Jul 11, 2015 - Jul 15, 2015, Madrid, Spain

Cite This

ISO 690

ZAHADAT, Payam, Heiko HAMANN, Thomas SCHMICKL, 2015. Evolving Diverse Collective Behaviors Independent of Swarm Density. GECCO '15 : Annual Conference on Genetic and Evolutionary Computation. Madrid, Spain, Jul 11, 2015 - Jul 15, 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, pp. 1245-1246. ISBN 978-1-4503-3488-4. Available under: doi: 10.1145/2739482.2768492

BibTex

@inproceedings{Zahadat2015Evolv-59889,
  year={2015},
  doi={10.1145/2739482.2768492},
  title={Evolving Diverse Collective Behaviors Independent of Swarm Density},
  isbn={978-1-4503-3488-4},
  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={1245--1246},
  editor={Silva, Sara},
  author={Zahadat, Payam and Hamann, Heiko and Schmickl, Thomas}
}

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/123456789/59889">
    <dc:contributor>Hamann, Heiko</dc:contributor>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dcterms:issued>2015</dcterms:issued>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/59889"/>
    <dc:language>eng</dc:language>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-01-23T11:43:23Z</dc:date>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Schmickl, Thomas</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Zahadat, Payam</dc:creator>
    <dcterms:title>Evolving Diverse Collective Behaviors Independent of Swarm Density</dcterms:title>
    <dc:creator>Hamann, Heiko</dc:creator>
    <dc:creator>Schmickl, Thomas</dc:creator>
    <dcterms:abstract xml:lang="eng">There are multiple different ways of implementing artificial evolution of collective behaviors. Besides a classical offline evolution approach, there is, for example, the option of environment-driven distributed evolutionary adaptation in the form of an artificial ecology [2] and more generally there is the approach of embodied evolution [1,3,6]. Another recently reported approach is the application of novelty search to swarm robotics [5]. In the following, we report an extension of the approach of [7]. The underlying concept is an information-theoretic analogon to thermodynamic (Helmholtz) free energy [8]. The assumption is that the brain is permanently trying to predict future perceptions and that minimizing the prediction error is basically inherent to brains. This is defined by the 'free-energy principle' of [4]. The struggle for prediction success requires a complementary force that represents curiosity and exploration. In this abstract we present an extended method called diverse-prediction that rewards not only for correct predictions but also for each visited sensory state. This proves to be a better approach compared to the method prediction that was reported before[7].</dcterms:abstract>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Zahadat, Payam</dc:contributor>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-01-23T11:43:23Z</dcterms:available>
  </rdf:Description>
</rdf:RDF>

Bibliography of Konstanz

No