Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
 
 
DownloadE-Mail
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  Efficient data reuse in value function approximation

Hachiya, H., Akiyama, T., Sugiyama, M., & Peters, J. (2009). Efficient data reuse in value function approximation. In 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (pp. 8-15). Piscataway, NJ, USA: IEEE Service Center.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C4EB-A Versions-Permalink: https://hdl.handle.net/21.11116/0000-0002-F929-8
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4927519 (Verlagsversion)
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Hachiya, H, Autor           
Akiyama, T, Autor
Sugiyama, M, Autor
Peters, J1, 2, Autor           
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a policy that is different from the currently optimized policy. A common approach is to use importance sampling techniques for compensating for the bias of value function estimators caused by the difference between the data-sampling policy and the target policy. However, existing off-policy methods often do not take the variance of the value function estimators explicitly into account and therefore their performance tends to be unstable. To cope with this problem, we propose using an adaptive importance sampling technique which allows us to actively control the trade-off between bias and variance. We further provide a method for optimally determining the trade-off parameter based on a variant of cross-validation. The usefulness of the proposed approach is demonstrated through simulated swing-up inverted-pendulum problem.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2009-05
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: DOI: 10.1109/ADPRL.2009.4927519
BibTex Citekey: 5771
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL 2009)
Veranstaltungsort: Nashville, TN, USA
Start-/Enddatum: 2009-03-30 - 2009-04-02

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Piscataway, NJ, USA : IEEE Service Center
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 8 - 15 Identifikator: ISBN: 978-1-4244-2761-1