<?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-02272091</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="2026-05-03T20:07:15+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="fr">Étude de la motivation intrinsèque en apprentissage par renforcement</title>
            <author role="aut">
              <persName>
                <forename type="first">Arthur</forename>
                <surname>Aubret</surname>
              </persName>
              <email type="md5">9af073ec1733a4d2004b4d1f8d2302b6</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">arthur-aubret</idno>
              <idno type="idhal" notation="numeric">176995</idno>
              <idno type="halauthorid" notation="string">45987-176995</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3495-4323</idno>
              <affiliation ref="#struct-413093"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Laëtitia</forename>
                <surname>Matignon</surname>
              </persName>
              <email type="md5">b2ec0964ba70e29b4bcac9a851898487</email>
              <email type="domain">univ-lyon1.fr</email>
              <idno type="idhal" notation="string">laetitia-matignon</idno>
              <idno type="idhal" notation="numeric">3290</idno>
              <idno type="halauthorid" notation="string">4775-3290</idno>
              <idno type="IDREF">https://www.idref.fr/134644239</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-7126-8715</idno>
              <affiliation ref="#struct-413093"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Salima</forename>
                <surname>Hassas</surname>
              </persName>
              <email type="md5">ffda4d31412239ad727a9705e4560215</email>
              <email type="domain">univ-lyon1.fr</email>
              <idno type="idhal" notation="string">salima-hassas</idno>
              <idno type="idhal" notation="numeric">3291</idno>
              <idno type="halauthorid" notation="string">10006-3291</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1387-2866</idno>
              <idno type="IDREF">https://www.idref.fr/083298398</idno>
              <affiliation ref="#struct-413093"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Arthur</forename>
                <surname>Aubret</surname>
              </persName>
              <email type="md5">a19df095bd43f4b2b69a2646ec7a1f2b</email>
              <email type="domain">univ-lyon1.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2019-08-28 13:59:45</date>
              <date type="whenModified">2025-09-03 10:48:33</date>
              <date type="whenReleased">2019-08-28 14:01:35</date>
              <date type="whenProduced">2019-07-01</date>
              <date type="whenEndEmbargoed">2019-08-27</date>
              <ref type="file" target="https://hal.science/hal-02272091v1/document">
                <date notBefore="2019-08-27"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-02272091v1/file/JFPDA2019_2.pdf" id="file-2272091-2195541">
                <date notBefore="2019-08-27"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="775625">
                <persName>
                  <forename>Arthur</forename>
                  <surname>Aubret</surname>
                </persName>
                <email type="md5">a19df095bd43f4b2b69a2646ec7a1f2b</email>
                <email type="domain">univ-lyon1.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02272091</idno>
            <idno type="halUri">https://hal.science/hal-02272091</idno>
            <idno type="halBibtex">aubret:hal-02272091</idno>
            <idno type="halRefHtml">&lt;i&gt;Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes&lt;/i&gt;, Jul 2019, Toulouse, France</idno>
            <idno type="halRef">Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes, Jul 2019, Toulouse, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2272091-2195541"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-LYON1">Université Claude Bernard - Lyon I</idno>
            <idno type="stamp" n="UNIV-LYON2">Université Lumière Lyon 2</idno>
            <idno type="stamp" n="INSA-LYON">Institut National des Sciences Appliquées de Lyon</idno>
            <idno type="stamp" n="EC-LYON">Ecole Centrale de Lyon</idno>
            <idno type="stamp" n="LIRIS" corresp="UNIV-LYON1">Laboratoire d'InfoRmatique en Image et Systèmes d'information</idno>
            <idno type="stamp" n="LYON2">Université Lyon2</idno>
            <idno type="stamp" n="INSA-GROUPE">Groupe INSA</idno>
            <idno type="stamp" n="UDL">UDL</idno>
            <idno type="stamp" n="UNIV-LYON">Université de Lyon</idno>
            <idno type="stamp" n="HAL-LYON-2-NOUVELLE-VERSION">Nouvelle version portail </idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="3">National</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="fr">Étude de la motivation intrinsèque en apprentissage par renforcement</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Arthur</forename>
                    <surname>Aubret</surname>
                  </persName>
                  <email type="md5">9af073ec1733a4d2004b4d1f8d2302b6</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">arthur-aubret</idno>
                  <idno type="idhal" notation="numeric">176995</idno>
                  <idno type="halauthorid" notation="string">45987-176995</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3495-4323</idno>
                  <affiliation ref="#struct-413093"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Laëtitia</forename>
                    <surname>Matignon</surname>
                  </persName>
                  <email type="md5">b2ec0964ba70e29b4bcac9a851898487</email>
                  <email type="domain">univ-lyon1.fr</email>
                  <idno type="idhal" notation="string">laetitia-matignon</idno>
                  <idno type="idhal" notation="numeric">3290</idno>
                  <idno type="halauthorid" notation="string">4775-3290</idno>
                  <idno type="IDREF">https://www.idref.fr/134644239</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-7126-8715</idno>
                  <affiliation ref="#struct-413093"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Salima</forename>
                    <surname>Hassas</surname>
                  </persName>
                  <email type="md5">ffda4d31412239ad727a9705e4560215</email>
                  <email type="domain">univ-lyon1.fr</email>
                  <idno type="idhal" notation="string">salima-hassas</idno>
                  <idno type="idhal" notation="numeric">3291</idno>
                  <idno type="halauthorid" notation="string">10006-3291</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1387-2866</idno>
                  <idno type="IDREF">https://www.idref.fr/083298398</idno>
                  <affiliation ref="#struct-413093"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes</title>
                  <date type="start">2019-07-01</date>
                  <date type="end">2019-07-05</date>
                  <settlement>Toulouse</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <date type="datePub">2019-06-01</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="fr">French</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Reinforcement learning</term>
                <term xml:lang="en">intrinsic motivation</term>
                <term xml:lang="en">curiosity</term>
                <term xml:lang="en">meta-reward</term>
                <term xml:lang="en">generation of objectives</term>
                <term xml:lang="en">options</term>
                <term xml:lang="en">knowledge acquisition</term>
                <term xml:lang="fr">curiosité</term>
                <term xml:lang="fr">Apprentissage par renforcement</term>
                <term xml:lang="fr">motivation intrinsèque</term>
                <term xml:lang="fr">génération d'objectifs</term>
                <term xml:lang="fr">options</term>
                <term xml:lang="fr">empowerment</term>
                <term xml:lang="fr">acquisition de connaissances</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Despite many existing works in reinforcement learning (RL) and the recent successes obtained by combining it with deep learning, RL is facing many challenges. Some of them, like the ability to abstract the action or the difficulty to conceive a reward function without expert knowledge, can be addressed by the use of intrinsic motivation. In this article, we provide a survey on the role of intrinsic motivation in RL and its different usages by detailing interests and limits of existing approaches. Our analysis suggests that mutual information is central to most of the work using intrinsic motivation in RL. The combination of deep RL and intrinsic motivation enables to learn more complicated and more generalisable behaviours than what enables standard RL.</p>
            </abstract>
            <abstract xml:lang="fr">
              <p>Malgré les nombreux travaux existants en apprentissage par renforcement (AR) et les récents succès obtenus notamment en le combinant avec l'apprentissage profond, l'AR fait encore aujourd'hui face à de nombreux défis. Certains d'entre eux, comme la problématique de l'abstraction temporelle des actions ou la difficulté de concevoir une fonction de récompense sans connaissances ex-pertes, peuvent être adressées par l'utilisation de récompenses intrinsèques. Dans cet article, nous proposons une étude du rôle de la motivation intrinsèque en AR et de ses différents usages, en détaillant les intérêts et les limites des approches existantes. Notre analyse suggère que la notion d'information mutuelle est centrale à la plupart des travaux utilisant la motivation intrinsèque en AR. Celle-ci, combinée aux algorithmes d'AR profond, permet d'apprendre des comportements plus complexes et plus généralisables que ce que permet l'AR traditionnel.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-413093" status="VALID">
          <orgName>Systèmes Cognitifs et Systèmes Multi-Agents</orgName>
          <orgName type="acronym">SyCoSMA</orgName>
          <date type="start">2015-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-2003" type="direct"/>
            <relation active="#struct-33804" type="indirect"/>
            <relation active="#struct-126765" type="indirect"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-194495" type="indirect"/>
            <relation active="#struct-219748" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation name="UMR5205" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-2003" status="VALID">
          <idno type="IdRef">149705271</idno>
          <idno type="ISNI">0000000122577669</idno>
          <idno type="RNSR">200511875R</idno>
          <idno type="ROR">https://ror.org/04dv4he91</idno>
          <orgName>Laboratoire d'InfoRmatique en Image et Systèmes d'information</orgName>
          <orgName type="acronym">LIRIS</orgName>
          <date type="start">2003-01-01</date>
          <desc>
            <address>
              <addrLine>Bâtiment Blaise Pascal - 20, avenue Albert Einstein - 69621 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://liris.cnrs.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-33804" type="direct"/>
            <relation active="#struct-126765" type="direct"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-194495" type="direct"/>
            <relation active="#struct-219748" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation name="UMR5205" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-33804" status="VALID">
          <idno type="IdRef">02640334X</idno>
          <idno type="ISNI">0000 0001 2188 0906</idno>
          <idno type="ROR">https://ror.org/03rth4p18</idno>
          <idno type="Wikidata">Q4041</idno>
          <orgName>Université Lumière - Lyon 2</orgName>
          <orgName type="acronym">UL2</orgName>
          <desc>
            <address>
              <addrLine>86, rue Pasteur - 69007 Lyon</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon2.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-126765" status="VALID">
          <idno type="ROR">https://ror.org/05s6rge65</idno>
          <orgName>École Centrale de Lyon</orgName>
          <orgName type="acronym">ECL</orgName>
          <desc>
            <address>
              <addrLine>36 avenue Guy de Collongue - 69134 Ecully cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ec-lyon.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301088" status="VALID">
          <idno type="ROR">https://ror.org/01rk35k63</idno>
          <orgName>Université de Lyon</orgName>
          <desc>
            <address>
              <addrLine>92 rue Pasteur - CS 30122, 69361 Lyon Cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-lyon.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-194495" status="VALID">
          <idno type="IdRef">026402823</idno>
          <idno type="ISNI">0000000121686185</idno>
          <idno type="ROR">https://ror.org/029brtt94</idno>
          <orgName>Université Claude Bernard Lyon 1</orgName>
          <orgName type="acronym">UCBL</orgName>
          <desc>
            <address>
              <addrLine>43, boulevard du 11 novembre 1918, 69622 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon1.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-219748" status="VALID">
          <idno type="IdRef">052444724</idno>
          <idno type="ISNI">0000 0001 2292 0228</idno>
          <orgName>Institut National des Sciences Appliquées de Lyon</orgName>
          <orgName type="acronym">INSA Lyon</orgName>
          <date type="start">1957-03-18</date>
          <desc>
            <address>
              <addrLine>20 Avenue Albert Einstein, 69621 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-lyon.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
            <relation active="#struct-301232" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301232" status="VALID">
          <idno type="IdRef">162105150</idno>
          <orgName>Institut National des Sciences Appliquées</orgName>
          <orgName type="acronym">INSA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </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>
      </listOrg>
    </back>
  </text>
</TEI>