Publikation: Rage against the machines : how subjects play against learning algorithms
Dateien
Datum
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
DOI (zitierfähiger Link)
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Sammlungen
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
We use a large-scale internet experiment to explore how subjects learn to play against computers that are programmed to follow one of a number of standard learning algorithms. The learning theories are (unbeknown to subjects) a best response process, fictitious play, imitation, reinforcement learning, and a trial & error process. We explore how subjects' performances depend on their opponents' learning algorithm. Furthermore, we test whether subjects try to influence those algorithms to their advantage in a forward-looking way (strategic teaching). We find that strategic teaching occurs frequently and that all learning algorithms are subject to exploitation with the notable exception of imitation.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
DÜRSCH, Peter, Albert KOLB, Jörg OECHSSLER, Burkhard C. SCHIPPER, 2009. Rage against the machines : how subjects play against learning algorithms. In: Economic Theory. 2009, 43(3), pp. 407-430. ISSN 0938-2259. eISSN 1432-0479. Available under: doi: 10.1007/s00199-009-0446-0BibTex
@article{Dursch2009again-23212, year={2009}, doi={10.1007/s00199-009-0446-0}, title={Rage against the machines : how subjects play against learning algorithms}, number={3}, volume={43}, issn={0938-2259}, journal={Economic Theory}, pages={407--430}, author={Dürsch, Peter and Kolb, Albert and Oechssler, Jörg and Schipper, Burkhard C.} }
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/123456789/23212"> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dc:contributor>Kolb, Albert</dc:contributor> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-05-07T11:26:27Z</dcterms:available> <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/> <dc:creator>Kolb, Albert</dc:creator> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-05-07T11:26:27Z</dc:date> <dc:creator>Dürsch, Peter</dc:creator> <dc:contributor>Schipper, Burkhard C.</dc:contributor> <dcterms:bibliographicCitation>Economic Theory ; 43 (2010), 3. - S. 407-430</dcterms:bibliographicCitation> <dcterms:title>Rage against the machines : how subjects play against learning algorithms</dcterms:title> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/46"/> <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/23212"/> <dc:contributor>Oechssler, Jörg</dc:contributor> <dc:contributor>Dürsch, Peter</dc:contributor> <dc:creator>Schipper, Burkhard C.</dc:creator> <dc:language>eng</dc:language> <dc:rights>terms-of-use</dc:rights> <dcterms:abstract xml:lang="eng">We use a large-scale internet experiment to explore how subjects learn to play against computers that are programmed to follow one of a number of standard learning algorithms. The learning theories are (unbeknown to subjects) a best response process, fictitious play, imitation, reinforcement learning, and a trial & error process. We explore how subjects' performances depend on their opponents' learning algorithm. Furthermore, we test whether subjects try to influence those algorithms to their advantage in a forward-looking way (strategic teaching). We find that strategic teaching occurs frequently and that all learning algorithms are subject to exploitation with the notable exception of imitation.</dcterms:abstract> <dcterms:issued>2009</dcterms:issued> <dc:creator>Oechssler, Jörg</dc:creator> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/46"/> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> </rdf:Description> </rdf:RDF>