About: Reinforcement learning for spoken dialogue systems using off-policy natural gradient method

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Reinforcement learning for spoken dialogue systems using off-policy natural gradient method Goto Sponge NotDistinct Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

Attributes	Values
rdf:type	skos:Concept http://linked.opendata.cz/ontology/domain/vavai/Vysledek
rdfs:seeAlso	http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6424161
Description	Reinforcement learning methods have been successfully used to optimise dialogue strategies in statistical dialogue systems. Typically, reinforcement techniques learn on-policy i.e., the dialogue strategy is updated online while the system is interacting with a user. An alternative to this approach is off-policy reinforcement learning, which estimates an optimal dialogue strategy offline from a fixed corpus of previously collected dialogues. This paper proposes a novel off-policy reinforcement learning method based on natural policy gradients and importance sampling. The algorithm is evaluated on a spoken dialogue system in the tourist information domain. The experiments indicate that the proposed method learns a dialogue strategy, which significantly outperforms the baseline handcrafted dialogue policy Reinforcement learning methods have been successfully used to optimise dialogue strategies in statistical dialogue systems. Typically, reinforcement techniques learn on-policy i.e., the dialogue strategy is updated online while the system is interacting with a user. An alternative to this approach is off-policy reinforcement learning, which estimates an optimal dialogue strategy offline from a fixed corpus of previously collected dialogues. This paper proposes a novel off-policy reinforcement learning method based on natural policy gradients and importance sampling. The algorithm is evaluated on a spoken dialogue system in the tourist information domain. The experiments indicate that the proposed method learns a dialogue strategy, which significantly outperforms the baseline handcrafted dialogue policy (en)
Title	Reinforcement learning for spoken dialogue systems using off-policy natural gradient method Reinforcement learning for spoken dialogue systems using off-policy natural gradient method (en)
skos:prefLabel	Reinforcement learning for spoken dialogue systems using off-policy natural gradient method Reinforcement learning for spoken dialogue systems using off-policy natural gradient method (en)
skos:notation	RIV/00216208:11320/12:10194751!RIV14-MSM-11320___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(LK11221)
http://linked.open...vai/riv/dodaniDat	2014
http://linked.open...aciTvurceVysledku	Jurčíček, Filip
http://linked.open.../riv/druhVysledku	D - Článek ve sborníku
http://linked.open...iv/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open...titaPredkladatele	Univerzita Karlova v Praze / Matematicko-fyzikální fakulta
http://linked.open...dnocenehoVysledku	164727
http://linked.open...ai/riv/idVysledku	RIV/00216208:11320/12:10194751
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	method; gradient; natural; policy; using; systems; dialogue; spoken; learning; reinforcement (en)
http://linked.open.../riv/klicoveSlovo	dialogue spoken using gradient learning method policy reinforcement systems natural
http://linked.open...ontrolniKodProRIV	[D27A876D735D]
http://linked.open...v/mistoKonaniAkce	Miami, FL, USA
http://linked.open...i/riv/mistoVydani	Miami, FL, USA
http://linked.open...i/riv/nazevZdroje	IEEE SLT '12: Proc. IEEE Spoken Language Technology Workshop
http://linked.open...in/vavai/riv/obor	IN
http://linked.open...ichTvurcuVysledku	1 (xsd:int)
http://linked.open...cetTvurcuVysledku	1 (xsd:int)
http://linked.open...vavai/riv/projekt	Development of statistical methods for spoken dalogue systems
http://linked.open...UplatneniVysledku	2012
http://linked.open...iv/tvurceVysledku	Jurčíček, Filip
http://linked.open...vavai/riv/typAkce	CST - Celostátní
http://linked.open.../riv/zahajeniAkce	2012-12-02 (xsd:date)
number of pages	6 (xsd:int)
http://purl.org/ne...btex#hasPublisher	IEEE
https://schema.org/isbn	978-1-4673-5126-3
http://localhost/t...ganizacniJednotka	11320

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 58 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software