<?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-00771646</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="2026-05-19T03:29:26+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A Comprehensive Reinforcement Learning Framework for Dialogue Management Optimisation</title>
            <author role="aut">
              <persName>
                <forename type="first">Lucie</forename>
                <surname>Daubigney</surname>
              </persName>
              <email type="md5">4e18289de1a5214cb7462274758c1d67</email>
              <email type="domain">supelec.fr</email>
              <idno type="idhal" notation="numeric">908990</idno>
              <idno type="halauthorid" notation="string">580624-908990</idno>
              <affiliation ref="#struct-205124"/>
              <affiliation ref="#struct-160692"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Matthieu</forename>
                <surname>Geist</surname>
              </persName>
              <email type="md5">c025140e3cc06ac39e7de0f0db2a4b70</email>
              <email type="domain">univ-lorraine.fr</email>
              <idno type="idhal" notation="string">matthieu-geist</idno>
              <idno type="idhal" notation="numeric">6945</idno>
              <idno type="halauthorid" notation="string">7492-6945</idno>
              <affiliation ref="#struct-160692"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Senthilkumar</forename>
                <surname>Chandramohan</surname>
              </persName>
              <email type="md5">9908f23fc9be8f7c0db06a5e45d7fe93</email>
              <email type="domain">supelec.fr</email>
              <idno type="idhal" notation="numeric">888330</idno>
              <idno type="halauthorid" notation="string">522223-888330</idno>
              <affiliation ref="#struct-160692"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Olivier</forename>
                <surname>Pietquin</surname>
              </persName>
              <email type="md5">d7ca8400327f875d5b916c43fee3b2c5</email>
              <email type="domain">univ-lille1.fr</email>
              <idno type="idhal" notation="string">olivier-pietquin</idno>
              <idno type="idhal" notation="numeric">4024</idno>
              <idno type="halauthorid" notation="string">23089-4024</idno>
              <idno type="IDREF">https://www.idref.fr/142821861</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-5386-465X</idno>
              <affiliation ref="#struct-160692"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Sébastien</forename>
                <surname>Van Luchene</surname>
              </persName>
              <email type="md5">983556412cb0e7fb6d6508a01ac9cf46</email>
              <email type="domain">supelec.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2013-01-09 10:19:58</date>
              <date type="whenModified">2025-11-04 12:05:09</date>
              <date type="whenReleased">2013-01-09 13:56:06</date>
              <date type="whenProduced">2012-12</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="123540">
                <persName>
                  <forename>Sébastien</forename>
                  <surname>Van Luchene</surname>
                </persName>
                <email type="md5">983556412cb0e7fb6d6508a01ac9cf46</email>
                <email type="domain">supelec.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00771646</idno>
            <idno type="halUri">https://centralesupelec.hal.science/hal-00771646</idno>
            <idno type="halBibtex">daubigney:hal-00771646</idno>
            <idno type="halRefHtml">&lt;i&gt;IEEE Journal of Selected Topics in Signal Processing&lt;/i&gt;, 2012, 6 (8), pp.891-902. &lt;a target="_blank" href="https://dx.doi.org/10.1109/JSTSP.2012.2229257"&gt;&amp;#x27E8;10.1109/JSTSP.2012.2229257&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">IEEE Journal of Selected Topics in Signal Processing, 2012, 6 (8), pp.891-902. &amp;#x27E8;10.1109/JSTSP.2012.2229257&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SUPELEC">SUPELEC</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="SUP_IMS" corresp="SUPELEC">IMS - Equipe Information, Multimodalité et Signal</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="LORIA2">Publications du LORIA</idno>
            <idno type="stamp" n="INRIA-NANCY-GRAND-EST">INRIA Nancy - Grand Est</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="LORIA">Laboratoire Lorrain de Recherche en Informatique et ses Applications</idno>
            <idno type="stamp" n="LORIA-AIS" corresp="LORIA">Department of Complex Systems, Artificial Intelligence  &amp; Robotics</idno>
            <idno type="stamp" n="AM2I-UL">Pôle scientifique Automatique, Mathématiques, Informatique et leurs Intéractions de l'Université de Lorraine</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">A Comprehensive Reinforcement Learning Framework for Dialogue Management Optimisation</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Lucie</forename>
                    <surname>Daubigney</surname>
                  </persName>
                  <email type="md5">4e18289de1a5214cb7462274758c1d67</email>
                  <email type="domain">supelec.fr</email>
                  <idno type="idhal" notation="numeric">908990</idno>
                  <idno type="halauthorid" notation="string">580624-908990</idno>
                  <affiliation ref="#struct-205124"/>
                  <affiliation ref="#struct-160692"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Matthieu</forename>
                    <surname>Geist</surname>
                  </persName>
                  <email type="md5">c025140e3cc06ac39e7de0f0db2a4b70</email>
                  <email type="domain">univ-lorraine.fr</email>
                  <idno type="idhal" notation="string">matthieu-geist</idno>
                  <idno type="idhal" notation="numeric">6945</idno>
                  <idno type="halauthorid" notation="string">7492-6945</idno>
                  <affiliation ref="#struct-160692"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Senthilkumar</forename>
                    <surname>Chandramohan</surname>
                  </persName>
                  <email type="md5">9908f23fc9be8f7c0db06a5e45d7fe93</email>
                  <email type="domain">supelec.fr</email>
                  <idno type="idhal" notation="numeric">888330</idno>
                  <idno type="halauthorid" notation="string">522223-888330</idno>
                  <affiliation ref="#struct-160692"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Olivier</forename>
                    <surname>Pietquin</surname>
                  </persName>
                  <email type="md5">d7ca8400327f875d5b916c43fee3b2c5</email>
                  <email type="domain">univ-lille1.fr</email>
                  <idno type="idhal" notation="string">olivier-pietquin</idno>
                  <idno type="idhal" notation="numeric">4024</idno>
                  <idno type="halauthorid" notation="string">23089-4024</idno>
                  <idno type="IDREF">https://www.idref.fr/142821861</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-5386-465X</idno>
                  <affiliation ref="#struct-160692"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">104366</idno>
                <idno type="issn">1932-4553</idno>
                <title level="j">IEEE Journal of Selected Topics in Signal Processing</title>
                <imprint>
                  <publisher>IEEE</publisher>
                  <biblScope unit="volume">6</biblScope>
                  <biblScope unit="issue">8</biblScope>
                  <biblScope unit="pp">891-902</biblScope>
                  <date type="datePub">2012-12</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/JSTSP.2012.2229257</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Reinforcement learning is now an acknowledged approach for optimising the interaction strategy of spoken dialogue systems. If the first considered algorithms were quite basic (like SARSA), recent works concentrated on more sophisticated methods. More attention has been paid to off-policy learning, dealing with the exploration-exploitation dilemma, sample efficiency or handling non-stationarity. New algorithms have been proposed to address these issues and have been applied to dialogue management. However, each algorithm often solves a single issue at a time, while dialogue systems exhibit all the problems at once. In this paper, we propose to apply the Kalman Temporal Differences (KTD) framework to the problem of dialogue strategy optimisation so as to address all these issues in a comprehensive manner with a single framework. Our claims are illustrated by experiments led on two real-world goal-oriented dialogue management frameworks, DIPPER and HIS.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-205124" status="OLD">
          <idno type="RNSR">200218290B</idno>
          <orgName>Autonomous intelligent machine</orgName>
          <orgName type="acronym">MAIA</orgName>
          <date type="end">2014-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/maia</ref>
          </desc>
          <listRelation>
            <relation active="#struct-129671" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-423090" type="direct"/>
            <relation active="#struct-206040" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-160692" status="OLD">
          <orgName>IMS : Information, Multimodalité &amp; Signal</orgName>
          <desc>
            <address>
              <addrLine>2 rue Edouard Belin - - 57070 METZ</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-26305" type="direct"/>
            <relation active="#struct-303397" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-129671" status="VALID">
          <idno type="RNSR">198618246Y</idno>
          <idno type="ROR">https://ror.org/03fcjvn64</idno>
          <orgName>Centre Inria de l'Université de Lorraine</orgName>
          <desc>
            <address>
              <addrLine>615 rue du Jardin Botanique 54600 Villers-lès-Nancy</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/nancy</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="department" xml:id="struct-423090" status="VALID">
          <orgName>Department of Complex Systems, Artificial Intelligence &amp; Robotics</orgName>
          <orgName type="acronym">LORIA - AIS</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr/en/research/departments/complex-systems-artificial-intelligence-and-robotics/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-206040" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-206040" status="VALID">
          <idno type="IdRef">067077927</idno>
          <idno type="ISNI">0000000121795429</idno>
          <idno type="RNSR">198912571S</idno>
          <idno type="IdUnivLorraine">[UL]RSI--</idno>
          <idno type="ROR">https://ror.org/02vnf0c38</idno>
          <orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
          <orgName type="acronym">LORIA</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-413289" type="direct"/>
            <relation name="UMR7503" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-413289" status="VALID">
          <idno type="IdRef">157040569</idno>
          <idno type="IdUnivLorraine">[UL]100--</idno>
          <idno type="ROR">https://ror.org/04vfs2w97</idno>
          <orgName>Université de Lorraine</orgName>
          <orgName type="acronym">UL</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lorraine.fr/</ref>
          </desc>
        </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-26305" status="OLD">
          <orgName>SUPELEC-Campus Metz</orgName>
          <date type="start">1985-01-01</date>
          <date type="end">2014-12-31</date>
          <desc>
            <address>
              <addrLine>2 rue Edouard Belin 57070 Metz</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.metz.supelec.fr/metz/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-303397" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-303397" status="VALID">
          <orgName>Ecole Supérieure d'Electricité - SUPELEC (FRANCE)</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>