Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark

Riedmiller, M., Peters, J., & Schaal, S. (2007). Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark. In 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (pp. 254-261). Los Alamitos, CA, USA: IEEE Computer Society.

Item is

Externe Referenzen

ausblenden:
Beschreibung:
-
OA-Status:

Urheber

ausblenden:
 Urheber:
Riedmiller, M, Autor
Peters, J1, Autor           
Schaal, S, Autor           
Affiliations:
1External Organizations, ou_persistent22              

Inhalt

ausblenden:
Schlagwörter: -
 Zusammenfassung: In this paper, we evaluate different versions from the three main kinds of model-free policy gradient methods, i.e., finite difference gradients, ‘vanilla‘ policy gradients and natural policy gradients. Each of these methods is first presented in its simple form and subsequently refined and optimized. By carrying out numerous experiments on the cart pole regulator benchmark we aim to provide a useful baseline for future research on parameterized policy search algorithms. Portable C++ code is provided for both plant and algorithms; thus, the results in this paper can be reevaluated, reused and new algorithms can be inserted with ease.

Details

ausblenden:
Sprache(n):
 Datum: 2007-04
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: DOI: 10.1109/ADPRL.2007.368196
BibTex Citekey: 4727
 Art des Abschluß: -

Veranstaltung

ausblenden:
Titel: IEEE Internatinal Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 2007)
Veranstaltungsort: Honolulu, HI, USA
Start-/Enddatum: 2007-04-01 - 2007-04-05

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

ausblenden:
Titel: 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Los Alamitos, CA, USA : IEEE Computer Society
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 254 - 261 Identifikator: ISBN: 1-4244-0706-0