<?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-02987427</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="2026-05-03T17:50:24+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Transfer learning for direct policy search: a reward shaping approach</title>
            <author role="aut">
              <persName>
                <forename type="first">Stéphane</forename>
                <surname>Doncieux</surname>
              </persName>
              <email type="md5">b937d1286db3da7e0877aa203468bd7d</email>
              <email type="domain">sorbonne-universite.fr</email>
              <idno type="idhal" notation="string">stephane-doncieux</idno>
              <idno type="idhal" notation="numeric">3909</idno>
              <idno type="halauthorid" notation="string">413189-3909</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1541-054X</idno>
              <idno type="IDREF">https://www.idref.fr/089428617</idno>
              <idno type="ISNI">http://isni.org/isni/000000010267981X</idno>
              <idno type="VIAF">https://viaf.org/viaf/153201463</idno>
              <affiliation ref="#struct-96164"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Stephane</forename>
                <surname>Doncieux</surname>
              </persName>
              <email type="md5">b937d1286db3da7e0877aa203468bd7d</email>
              <email type="domain">sorbonne-universite.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-11-03 20:49:11</date>
              <date type="whenModified">2023-03-24 14:53:19</date>
              <date type="whenReleased">2020-11-06 09:42:00</date>
              <date type="whenProduced">2013</date>
              <date type="whenEndEmbargoed">2013-01-01</date>
              <ref type="file" target="https://hal.science/hal-02987427v1/document">
                <date notBefore="2013-01-01"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-02987427v1/file/2013ACTI2858.pdf" id="file-2987427-2634563">
                <date notBefore="2013-01-01"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="138268">
                <persName>
                  <forename>Stephane</forename>
                  <surname>Doncieux</surname>
                </persName>
                <email type="md5">b937d1286db3da7e0877aa203468bd7d</email>
                <email type="domain">sorbonne-universite.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02987427</idno>
            <idno type="halUri">https://hal.science/hal-02987427</idno>
            <idno type="halBibtex">doncieux:hal-02987427</idno>
            <idno type="halRefHtml">&lt;i&gt;Proceedings of ICDL-EpiRob conference&lt;/i&gt;, 2013, Osaka, Japan. pp.1-6</idno>
            <idno type="halRef">Proceedings of ICDL-EpiRob conference, 2013, Osaka, Japan. pp.1-6</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2987427-2634563"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UPMC" corresp="SORBONNE-UNIVERSITE">Université Pierre et Marie Curie</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="ISIR" corresp="SORBONNE-UNIVERSITE">Institut des Systèmes Intelligents et de Robotique</idno>
            <idno type="stamp" n="UPMC_POLE_1" corresp="UPMC">UPMC Pôle 1</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SU-SCIENCES" corresp="SORBONNE-UNIVERSITE">Faculté des Sciences de Sorbonne Université</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="ISIR_AMAC" corresp="ISIR">Architectures et Modèles de l'Adaptation et de la Cognition</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</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="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Transfer learning for direct policy search: a reward shaping approach</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Stéphane</forename>
                    <surname>Doncieux</surname>
                  </persName>
                  <email type="md5">b937d1286db3da7e0877aa203468bd7d</email>
                  <email type="domain">sorbonne-universite.fr</email>
                  <idno type="idhal" notation="string">stephane-doncieux</idno>
                  <idno type="idhal" notation="numeric">3909</idno>
                  <idno type="halauthorid" notation="string">413189-3909</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1541-054X</idno>
                  <idno type="IDREF">https://www.idref.fr/089428617</idno>
                  <idno type="ISNI">http://isni.org/isni/000000010267981X</idno>
                  <idno type="VIAF">https://viaf.org/viaf/153201463</idno>
                  <affiliation ref="#struct-96164"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Proceedings of ICDL-EpiRob conference</title>
                <meeting>
                  <title>Proceedings of ICDL-EpiRob conference</title>
                  <date type="start">2013</date>
                  <settlement>Osaka</settlement>
                  <country key="JP">Japan</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">1-6</biblScope>
                  <date type="datePub">2013</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-rb">Computer Science [cs]/Robotics [cs.RO]</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>In  the  perspective  of  life  long  learning,  a  robotmay  face  different,  but  related  situations.  Being  able  to  exploitthe  knowledge  acquired  during  a  first  learning  phase  may  becritical in order to solve more complex tasks. This is the transferlearning problem. This problem is addressed here in the case ofdirect  policy  search  algorithms.  No  discrete  states,  nor  actionsare   defined   a   priori.   A   policy   is   described   by   a   controllerthat  computes  orders  to  be  sent  to  the  motors  out  of  sensorvalues.  Both  motor  and  sensor  values  can  be  continuous.  Theproposed approach relies on population based direct policy searchalgorithms, i.e. evolutionary algorithms. It exploits the numerousbehaviors  that  are  generated  during  the  search.  When  learningon  the  source  task,  a  knowledge  base  is  built.  The  knowledgebase aims at identifying the most salient behaviors segments withregards  to  the  considered  task.  Afterwards,  the  knowledge  baseis  exploited  on  a  target  task,  with  a  reward  shaping  approach : besides its reward on the task, a policy is credited with a rewardcomputed  from  the  knowledge  base.  The  rationale  behind  thisapproach  is  to  automatically  detect  the  stepping  stones,  i.e.  thebehavior segments that have lead to a reward in the source taskbefore the policy is efficient enough to get the reward on the targettask. The approach is tested in simulation with a neuroevolutionapproach  and  on  ball  collecting  tasks</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-96164" status="OLD">
          <idno type="RNSR">200918463J</idno>
          <orgName>Institut des Systèmes Intelligents et de Robotique</orgName>
          <orgName type="acronym">ISIR</orgName>
          <date type="start">2002-01-01</date>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>Université Pierre et Marie Curie - Paris VI Boite courrier 173 4 Place JUSSIEU 75252 Paris cedex 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.isir.upmc.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-93591" type="direct"/>
            <relation name="UMR7222 / FRE2507" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-93591" status="OLD">
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Université Pierre et Marie Curie - Paris 6</orgName>
          <orgName type="acronym">UPMC</orgName>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>4 place Jussieu - 75005 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.upmc.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>
      </listOrg>
    </back>
  </text>
</TEI>