A Non-Parametric Approach to Dynamic Programming

Kroemer, O; Peters, J

Lokale TagsFreigabegeschichteDetailsÜbersicht

A Non-Parametric Approach to Dynamic Programming

Kroemer, O., & Peters, J. (2012). A Non-Parametric Approach to Dynamic Programming. In J. Shawe-Taylor (Ed.), Advances in Neural Information Processing Systems 24 (pp. 1719-1727). Red Hook, NY, USA: Curran.

Item is Freigegeben

einblenden: alle

Basisdaten

ausblenden:

Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-B872-6 Versions-Permalink: https://hdl.handle.net/21.11116/0000-0001-19C8-2

Genre: Konferenzbeitrag

Dateien

einblenden: Dateien

Externe Referenzen

ausblenden:

externe Referenz:
https://papers.nips.cc/paper/4182-a-non-parametric-approach-to-dynamic-programming.pdf (Verlagsversion) Open Access Status unbekannt

Beschreibung:
-

OA-Status:

Urheber

ausblenden:

Urheber:
Kroemer, O¹, Autor
Peters, J¹, Autor

Affiliations:
1Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647

Inhalt

ausblenden:

Schlagwörter: -

Zusammenfassung: In this paper, we consider the problem of policy evaluation for continuousstate systems. We present a non-parametric approach to policy evaluation, which uses kernel density estimation to represent the system. The true form of the value function for this model can be determined, and can be computed using Galerkin’s method. Furthermore, we also present a unified view of several well-known policy evaluation methods. In particular, we show that the same Galerkin method can be used to derive Least-Squares Temporal Difference learning, Kernelized Temporal Difference learning, and a discrete-state Dynamic Programming solution, as well as our proposed method. In a numerical evaluation of these algorithms, the proposed approach performed better than the other methods.

Details

ausblenden:

Sprache(n):

Datum: Erschienen: 2012-01

Publikationsstatus: Erschienen

Seiten: -

Ort, Verlag, Ausgabe: -

Inhaltsverzeichnis: -

Art der Begutachtung: -

Identifikatoren: BibTex Citekey: KroemerP2011

Art des Abschluß: -

Veranstaltung

ausblenden:

Titel: Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS 2011)

Veranstaltungsort: Granada, Spain

Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

ausblenden:

Titel: Advances in Neural Information Processing Systems 24

Genre der Quelle: Konferenzband

Urheber:
Shawe-Taylor, J, Herausgeber
Zemel, RS, Autor
Bartlett, P, Autor
Pereira, F, Autor
Weinberger, KQ, Autor

Affiliations:
-

Ort, Verlag, Ausgabe: Red Hook, NY, USA : Curran

Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 1719 - 1727 Identifikator: ISBN: 978-1-618-39599-3