State Space Compression with Predictive Representations

Boularias, A; Izadi, M; Chaib-Draa, B

Lokale TagsFreigabegeschichteDetailsÜbersicht

State Space Compression with Predictive Representations

Boularias, A., Izadi, M., & Chaib-Draa, B. (2008). State Space Compression with Predictive Representations. In D. Wilson, & H. Lane (Eds.), Twenty-First International Florida Artificial Intelligence Research Society Conference (pp. 41-46). Menlo Park, CA, USA: AAAI Press.

Item is Freigegeben

einblenden: alle

Basisdaten

ausblenden:

Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C983-6 Versions-Permalink: https://hdl.handle.net/21.11116/0000-0003-7FA3-7

Genre: Konferenzbeitrag

Dateien

ausblenden: Dateien

:

FLAIRS-2008-Boularias.pdf (beliebiger Volltext), 148KB

Öffnen Speichern

Datei-Permalink:
https://hdl.handle.net/21.11116/0000-0003-7FA4-6

Name:
FLAIRS-2008-Boularias.pdf

Beschreibung:
-

OA-Status:

Sichtbarkeit:
Öffentlich

MIME-Typ / Prüfsumme:
application/pdf / [MD5]

Technische Metadaten:

Öffnen

Copyright Datum:
-

Copyright Info:
-

Lizenz:
-

Externe Referenzen

einblenden:

Urheber

ausblenden:

Urheber:
Boularias, A¹, Autor
Izadi, M, Autor
Chaib-Draa, B, Autor

Affiliations:
1External Organizations, ou_persistent22

Inhalt

ausblenden:

Schlagwörter: -

Zusammenfassung: Current studies have demonstrated that the representational power of predictive state representations (PSRs) is at least
equal to the one of partially observable Markov decision
processes (POMDPs). This is while early steps in planning
and generalization with PSRs suggest substantial improvements
compared to POMDPs. However, lack of practical algorithms
for learning these representations severely restricts
their applicability. The computational inefficiency of exact
PSR learning methods naturally leads to the exploration of
various approximation methods that can provide a good set
of core tests through less computational effort. In this paper,
we address this problem in an optimization framework. In
particular, our approach aims to minimize the potential error
that may be caused by missing a number of core tests. We
provide analysis of the error caused by this compression and
present an empirical evaluation illustrating the performance
of this approach.

Details

ausblenden:

Sprache(n):

Datum: Erschienen: 2008-05

Publikationsstatus: Erschienen

Seiten: -

Ort, Verlag, Ausgabe: -

Inhaltsverzeichnis: -

Art der Begutachtung: -

Identifikatoren: BibTex Citekey: 6831

Art des Abschluß: -

Veranstaltung

ausblenden:

Titel: 21st International Florida Artificial Intelligence Research Society Conference (FLAIRS 2008)

Veranstaltungsort: Coconut Grove, FL, USA

Start-/Enddatum: 2008-05-15 - 2008-05-17

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

ausblenden:

Titel: Twenty-First International Florida Artificial Intelligence Research Society Conference

Genre der Quelle: Konferenzband

Urheber:
Wilson, DC, Herausgeber
Lane, HC, Herausgeber

Affiliations:
-

Ort, Verlag, Ausgabe: Menlo Park, CA, USA : AAAI Press

Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 41 - 46 Identifikator: ISBN: 978-1-57735-365-2