Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
 
 
DownloadE-Mail
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  Compositional generalization in multi-armed bandits

Saanum, T., Schulz, E., & Speekenbrink, M. (2021). Compositional generalization in multi-armed bandits. In 43rd Annual Conference of the Cognitive Science Society (CogSci 2021): Workshop 2 Using Games to Understand Intelligence (pp. 1320-1326). Red Hook, NY, USA: Curran.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/21.11116/0000-0007-FF3C-8 Versions-Permalink: https://hdl.handle.net/21.11116/0000-000A-E9EF-3
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
https://cognitivesciencesociety.org/wp-content/uploads/2021/07/CSSPosterListingJuly15.pdf (Zusammenfassung)
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Saanum, T1, 2, Autor           
Schulz, E1, 2, Autor           
Speekenbrink, M, Autor
Affiliations:
1Research Group Computational Principles of Intelligence, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_3189356              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: To what extent do human reward learning and decision-making
rely on the ability to represent and generate richly structured
relationships between options? We provide evidence that
structure learning and the principle of compositionality play
crucial roles in human reinforcement learning. In a new multiarmed
bandit paradigm, we found evidence that participants
are able to learn representations of different reward structures
and combine them to make correct generalizations about options
in novel contexts. Moreover, we found substantial evidence
that participants transferred knowledge of simpler reward
structures to make compositional generalizations about
rewards in complex contexts. This allowed participants to
accumulate more rewards earlier, and to explore less whenever
such knowledge transfer was possible. We also provide
a computational model which is able to generalize and compose
knowledge for complex reward structures. This model describes
participant behaviour in the compositional generalization
task better than various other models of decision-making
and transfer learning.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2021-072021-11
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: -
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 43rd Annual Conference of the Cognitive Science Society (CogSci 2021)
Veranstaltungsort: Wien, Austria
Start-/Enddatum: 2021-07-26 - 2021-07-29

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: 43rd Annual Conference of the Cognitive Science Society (CogSci 2021): Workshop 2 Using Games to Understand Intelligence
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Red Hook, NY, USA : Curran
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 1320 - 1326 Identifikator: ISBN: 978-1-7138-3525-7