<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-01251606v2</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-14T01:16:01+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">On Bayesian index policies for sequential resource allocation</title>
            <author role="aut">
              <persName>
                <forename type="first">Emilie</forename>
                <surname>Kaufmann</surname>
              </persName>
              <email type="md5">8a4874bf36cdf75d4368683c6a73105d</email>
              <email type="domain">univ-lille.fr</email>
              <idno type="idhal" notation="string">emilie-kaufmann</idno>
              <idno type="idhal" notation="numeric">10422</idno>
              <idno type="halauthorid" notation="string">18258-10422</idno>
              <idno type="IDREF">https://www.idref.fr/197040810</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-5496-824X</idno>
              <affiliation ref="#struct-432036"/>
              <affiliation ref="#struct-441569"/>
              <affiliation ref="#struct-410272"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Emilie</forename>
                <surname>Kaufmann</surname>
              </persName>
              <email type="md5">61b799430ccac221f5bff841d3d66d69</email>
              <email type="domain">gmail.com</email>
            </editor>
            <funder ref="#projanr-36340"/>
            <funder ref="#projanr-34510"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1">
              <date type="whenSubmitted">2016-01-06 14:41:38</date>
            </edition>
            <edition n="v2" type="current">
              <date type="whenSubmitted">2016-09-12 10:14:03</date>
              <date type="whenWritten">2016-09-12</date>
              <date type="whenModified">2025-02-26 15:33:49</date>
              <date type="whenReleased">2016-09-13 15:48:33</date>
              <date type="whenProduced">2016-09-12</date>
              <date type="whenEndEmbargoed">2016-09-12</date>
              <ref type="file" target="https://hal.science/hal-01251606v2/document">
                <date notBefore="2016-09-12"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01251606v2/file/BayesianHaL.pdf" id="file-1363914-1446671">
                <date notBefore="2016-09-12"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/1601.01190"/>
            </edition>
            <edition n="v3">
              <date type="whenSubmitted">2017-11-06 09:52:16</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="200307">
                <persName>
                  <forename>Emilie</forename>
                  <surname>Kaufmann</surname>
                </persName>
                <email type="md5">61b799430ccac221f5bff841d3d66d69</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01251606</idno>
            <idno type="halUri">https://hal.science/hal-01251606</idno>
            <idno type="halBibtex">kaufmann:hal-01251606</idno>
            <idno type="halRefHtml">2016</idno>
            <idno type="halRef">2016</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1363914-1446671"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt/>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">On Bayesian index policies for sequential resource allocation</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Emilie</forename>
                    <surname>Kaufmann</surname>
                  </persName>
                  <email type="md5">8a4874bf36cdf75d4368683c6a73105d</email>
                  <email type="domain">univ-lille.fr</email>
                  <idno type="idhal" notation="string">emilie-kaufmann</idno>
                  <idno type="idhal" notation="numeric">10422</idno>
                  <idno type="halauthorid" notation="string">18258-10422</idno>
                  <idno type="IDREF">https://www.idref.fr/197040810</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-5496-824X</idno>
                  <affiliation ref="#struct-432036"/>
                  <affiliation ref="#struct-441569"/>
                  <affiliation ref="#struct-410272"/>
                </author>
              </analytic>
              <monogr>
                <imprint/>
              </monogr>
              <idno type="arxiv">1601.01190</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en"> Bayesian algorithms</term>
                <term xml:lang="en">multi-armed bandits</term>
              </keywords>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halOldTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halTreeTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>This paper is about index policies for minimizing (frequentist) regret in a stochastic multi-armed bandit model, that are inspired by a Bayesian view on the problem. Our main contribution is to prove that the Bayes-UCB algorithm, which relies on quantiles of posterior distributions, is asymptotically optimal when the rewards distributions belong to a one-dimensional exponential family, for a large class of prior distributions. We also show that the Bayesian literature gives new insight on what kind of exploration rates could be used in frequentist, UCB-type algorithms. Indeed, approximations of the Bayesian optimal solution or the Finite Horizon Gittins indices provide a justification for the kl-UCB+ and kl-UCB-H+ algorithms, whose asymptotic optimality is also established.  </p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-432036" status="OLD">
          <idno type="RNSR">200718281V</idno>
          <orgName>Sequential Learning</orgName>
          <orgName type="acronym">SEQUEL</orgName>
          <date type="start">2015-01-01</date>
          <date type="end">2020-10-31</date>
          <desc>
            <address>
              <addrLine>Centre Inria de l'Université de Lille ,170 Av. de Bretagne, 59000 Lille</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/sequel</ref>
          </desc>
          <listRelation>
            <relation active="#struct-104752" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-410272" type="direct"/>
            <relation name="UMR9189" active="#struct-120930" type="indirect"/>
            <relation name="UMR9189" active="#struct-374570" type="indirect"/>
            <relation name="UMR9189" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-410272" status="VALID">
          <idno type="IdRef">18388695X</idno>
          <idno type="RNSR">201521249L</idno>
          <idno type="ROR">https://ror.org/05vrs3189</idno>
          <idno type="Wikidata">Q116959497</idno>
          <orgName>Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189</orgName>
          <orgName type="acronym">CRIStAL</orgName>
          <date type="start">2015-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lille - Campus scientifique - Bâtiment ESPRIT - Avenue Henri Poincaré - 59655 Villeneuve d’Ascq</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cristal.univ-lille.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR9189" active="#struct-120930" type="direct"/>
            <relation name="UMR9189" active="#struct-374570" type="direct"/>
            <relation name="UMR9189" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-104752" status="VALID">
          <idno type="RNSR">200818245B</idno>
          <idno type="ROR">https://ror.org/04eej9726</idno>
          <orgName>Centre Inria de l'Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>Parc Scientifique de la Haute Borne 40, avenue Halley Bât.A, Park Plaza 59650 Villeneuve d'Ascq</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/lille/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-120930" status="VALID">
          <idno type="IdRef">256304629</idno>
          <idno type="ISNI">0000000122034461</idno>
          <idno type="ROR">https://ror.org/01x441g73</idno>
          <orgName>Centrale Lille</orgName>
          <desc>
            <address>
              <addrLine>École Centrale de Lille - Cité Scientifique - CS 20048 59651 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://centralelille.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-374570" status="VALID">
          <idno type="IdRef">223446556</idno>
          <idno type="ISNI">0000 0001 2242 6780</idno>
          <idno type="ROR">https://ror.org/02kzqn938</idno>
          <idno type="Wikidata">Q3551621</idno>
          <orgName>Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>EPE Université de Lille. -- 42 rue Paul Duez, 59000 Lille</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-lille.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-36340" status="VALID">
          <idno type="anr">ANR-13-BS01-0005</idno>
          <idno type="program">Blanc 2013</idno>
          <orgName>SPADRO</orgName>
          <desc>Statistique Semi-Paramétrique pour l'Allocation Dynamique de Ressources et l'Optimisation</desc>
          <date type="start">2013</date>
        </org>
        <org type="anrProject" xml:id="projanr-34510" status="VALID">
          <idno type="anr">ANR-11-JS02-0005</idno>
          <idno type="program">Jeunes Chercheuses et Jeunes Chercheurs</idno>
          <orgName>GAP</orgName>
          <desc>Graphes, Algorithmes et Probabilités</desc>
          <date type="start">2011</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>