HAL - INRIA :: [inria-00369787, version 1] Upper Conﬁdence Trees and Billiards for Optimal Active Learning

inria-00369787, version 1

Upper Conﬁdence Trees and Billiards for Optimal Active Learning

Philippe Rolet () ^1, 2, Michèle Sebag () ^1, 2, Olivier Teytaud () ^1, 2

CAP09 (2009)

Résumé : This paper focuses on Active Learning (AL) with bounded compu- tational resources. AL is formalized as a ﬁnite horizon Reinforcement Learning problem, and tackled as a single-player game. An approximate optimal AL strat- egy based on tree-structured multi-armed bandit algorithms and billiard-based sampling is presented together with a proof of principle of the approach.

1 : Laboratoire de Recherche en Informatique (LRI)
CNRS : UMR8623 – Université Paris XI - Paris Sud
2 : TAO (INRIA Saclay - Ile de France)
INRIA – CNRS : UMR8623 – Université Paris XI - Paris Sud

inria-00369787, version 1
http://hal.inria.fr/inria-00369787
oai:hal.inria.fr:inria-00369787
Contributeur : Olivier Teytaud <>
Soumis le : Samedi 21 Mars 2009, 09:58:28
Dernière modification le : Lundi 23 Mars 2009, 14:51:47

Voir la fiche détaillée

Documents associés

PDF :

Exporter

Bibtex EndNote TEI RefWorks

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="inproceedings"><head>Communications avec actes</head>
<biblStruct type="inproceedings" xml:id="inria-00369787"><analytic>
<author><persName><forename>Philippe</forename><surname>Rolet</surname></persName>
<affiliation>
<orgName type="laboratory">LRI</orgName>
<orgName type="team">Laboratoire de Recherche en Informatique</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR8623</orgName>
<orgName type="institution">Université Paris XI - Paris Sud</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">INRIA Saclay - Ile de France</orgName>
<orgName type="team">TAO</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR8623</orgName>
<orgName type="institution">Université Paris XI - Paris Sud</orgName>
</affiliation>
</author>
<author><persName><forename>Michèle</forename><surname>Sebag</surname></persName>
<affiliation>
<orgName type="laboratory">LRI</orgName>
<orgName type="team">Laboratoire de Recherche en Informatique</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR8623</orgName>
<orgName type="institution">Université Paris XI - Paris Sud</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">INRIA Saclay - Ile de France</orgName>
<orgName type="team">TAO</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR8623</orgName>
<orgName type="institution">Université Paris XI - Paris Sud</orgName>
</affiliation>
</author>
<author><persName><forename>Olivier</forename><surname>Teytaud</surname></persName>
<affiliation>
<orgName type="laboratory">LRI</orgName>
<orgName type="team">Laboratoire de Recherche en Informatique</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR8623</orgName>
<orgName type="institution">Université Paris XI - Paris Sud</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">INRIA Saclay - Ile de France</orgName>
<orgName type="team">TAO</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR8623</orgName>
<orgName type="institution">Université Paris XI - Paris Sud</orgName>
</affiliation>
</author>
<title type="main" level="a">Upper Conﬁdence Trees and Billiards for Optimal Active Learning</title></analytic><monogr><meeting>CAP09</meeting><imprint><pubPlace><settlement>Hammamet, Tunisie</settlement><country>Tunisie</country></pubPlace><biblScope type="publicationDate">2009-00-00</biblScope></imprint></monogr><idno type="HALid">http://hal.inria.fr/inria-00369787</idno><idno type="HALFile">http://hal.inria.fr/inria-00369787/PDF/capfinal.pdf</idno></biblStruct>
</listBibl>
</listBibl>