<?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-04574316</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="2026-05-11T13:19:31+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learning</title>
            <author role="aut">
              <persName>
                <forename type="first">Paul</forename>
                <surname>Daoudi</surname>
              </persName>
              <email type="md5">e2e4527f0e5352f03161e2d16979f98d</email>
              <email type="domain">huawei.com</email>
              <idno type="idhal" notation="numeric">1243056</idno>
              <idno type="halauthorid" notation="string">2772399-1243056</idno>
              <idno type="IDREF">https://www.idref.fr/280769776</idno>
              <affiliation ref="#struct-569607"/>
            </author>
            <author role="crp">
              <persName>
                <forename type="first">Bogdan</forename>
                <surname>Robu</surname>
              </persName>
              <email type="md5">9b5c55d5ec683232ea9ae231e5db9313</email>
              <email type="domain">gipsa-lab.grenoble-inp.fr</email>
              <idno type="idhal" notation="string">bogdan-robu</idno>
              <idno type="idhal" notation="numeric">747277</idno>
              <idno type="halauthorid" notation="string">15017-747277</idno>
              <idno type="IDREF">https://www.idref.fr/156193779</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-7568-007X</idno>
              <idno type="VIAF">https://viaf.org/viaf/289754907</idno>
              <idno type="ISNI">http://isni.org/isni/0000000395125131</idno>
              <affiliation ref="#struct-1043346"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Christophe</forename>
                <surname>Prieur</surname>
              </persName>
              <email type="md5">e7a39b5305d865d22e7e7fbe5635c265</email>
              <email type="domain">gipsa-lab.grenoble-inp.fr</email>
              <idno type="idhal" notation="string">christophe-prieur</idno>
              <idno type="idhal" notation="numeric">1109</idno>
              <idno type="halauthorid" notation="string">23551-1109</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4456-2019</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?hl=en&amp;user=uqZI680AAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/060559497</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=uqZI680AAAAJ</idno>
              <affiliation ref="#struct-1043347"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Merwan</forename>
                <surname>Barlier</surname>
              </persName>
              <email type="md5">b0a748bb19da32d2139ac66e338ecd51</email>
              <email type="domain">huawei.com</email>
              <idno type="idhal" notation="numeric">1243058</idno>
              <idno type="halauthorid" notation="string">964374-1243058</idno>
              <affiliation ref="#struct-569607"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ludovic</forename>
                <surname>Dos Santos</surname>
              </persName>
              <idno type="halauthorid">2586316-0</idno>
              <affiliation ref="#struct-1001229"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Bogdan</forename>
                <surname>Robu</surname>
              </persName>
              <email type="md5">53e2d95a3c7a7b9cab96bed6220dc7a8</email>
              <email type="domain">gipsa-lab.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-08-28 11:40:01</date>
              <date type="whenModified">2026-01-08 10:48:24</date>
              <date type="whenReleased">2024-08-28 13:52:40</date>
              <date type="whenProduced">2024-08-03</date>
              <date type="whenEndEmbargoed">2024-08-28</date>
              <ref type="file" target="https://hal.science/hal-04574316v1/document">
                <date notBefore="2024-08-28"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04574316v1/file/main.pdf" id="file-4679890-4067086">
                <date notBefore="2024-08-28"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="160757">
                <persName>
                  <forename>Bogdan</forename>
                  <surname>Robu</surname>
                </persName>
                <email type="md5">53e2d95a3c7a7b9cab96bed6220dc7a8</email>
                <email type="domain">gipsa-lab.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04574316</idno>
            <idno type="halUri">https://hal.science/hal-04574316</idno>
            <idno type="halBibtex">daoudi:hal-04574316</idno>
            <idno type="halRefHtml">&lt;i&gt;IJCAI 2024 - International Joint Conference on Artificial Intelligence&lt;/i&gt;, Aug 2024, Jeju Island, South Korea</idno>
            <idno type="halRef">IJCAI 2024 - International Joint Conference on Artificial Intelligence, Aug 2024, Jeju Island, South Korea</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4679890-4067086"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UGA">HAL Grenoble Alpes</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INPG">Institut polytechnique de Grenoble</idno>
            <idno type="stamp" n="GIPSA">Grenoble Images Parole Signal Automatique</idno>
            <idno type="stamp" n="GIPSA-PAD" corresp="GIPSA">Pôle Automatique et Diagnostic</idno>
            <idno type="stamp" n="GIPSA-INFINITY">Infinite Dimensional Dynamics</idno>
            <idno type="stamp" n="GIPSA-MODUS">Modelling and Optinal Decision for Uncertain Systems</idno>
            <idno type="stamp" n="UGA-EPE">Université Grenoble Alpes [2020-*]</idno>
            <idno type="stamp" n="TEST-UGA">TEST-UGA</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="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learning</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Paul</forename>
                    <surname>Daoudi</surname>
                  </persName>
                  <email type="md5">e2e4527f0e5352f03161e2d16979f98d</email>
                  <email type="domain">huawei.com</email>
                  <idno type="idhal" notation="numeric">1243056</idno>
                  <idno type="halauthorid" notation="string">2772399-1243056</idno>
                  <idno type="IDREF">https://www.idref.fr/280769776</idno>
                  <affiliation ref="#struct-569607"/>
                </author>
                <author role="crp">
                  <persName>
                    <forename type="first">Bogdan</forename>
                    <surname>Robu</surname>
                  </persName>
                  <email type="md5">9b5c55d5ec683232ea9ae231e5db9313</email>
                  <email type="domain">gipsa-lab.grenoble-inp.fr</email>
                  <idno type="idhal" notation="string">bogdan-robu</idno>
                  <idno type="idhal" notation="numeric">747277</idno>
                  <idno type="halauthorid" notation="string">15017-747277</idno>
                  <idno type="IDREF">https://www.idref.fr/156193779</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-7568-007X</idno>
                  <idno type="VIAF">https://viaf.org/viaf/289754907</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000395125131</idno>
                  <affiliation ref="#struct-1043346"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Christophe</forename>
                    <surname>Prieur</surname>
                  </persName>
                  <email type="md5">e7a39b5305d865d22e7e7fbe5635c265</email>
                  <email type="domain">gipsa-lab.grenoble-inp.fr</email>
                  <idno type="idhal" notation="string">christophe-prieur</idno>
                  <idno type="idhal" notation="numeric">1109</idno>
                  <idno type="halauthorid" notation="string">23551-1109</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4456-2019</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?hl=en&amp;user=uqZI680AAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/060559497</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=uqZI680AAAAJ</idno>
                  <affiliation ref="#struct-1043347"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Merwan</forename>
                    <surname>Barlier</surname>
                  </persName>
                  <email type="md5">b0a748bb19da32d2139ac66e338ecd51</email>
                  <email type="domain">huawei.com</email>
                  <idno type="idhal" notation="numeric">1243058</idno>
                  <idno type="halauthorid" notation="string">964374-1243058</idno>
                  <affiliation ref="#struct-569607"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ludovic</forename>
                    <surname>Dos Santos</surname>
                  </persName>
                  <idno type="halauthorid">2586316-0</idno>
                  <affiliation ref="#struct-1001229"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>IJCAI 2024 - International Joint Conference on Artificial  Intelligence</title>
                  <date type="start">2024-08-03</date>
                  <date type="end">2024-08-09</date>
                  <settlement>Jeju Island</settlement>
                  <country key="KR">South Korea</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Real-world application</term>
                <term xml:lang="en">Transfer learning</term>
                <term xml:lang="en">Off-dynamics Reinforcement Learning</term>
                <term xml:lang="en">Dynamic systems</term>
              </keywords>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halDomain" n="info.info-au">Computer Science [cs]/Automatic Control Engineering</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>Off-dynamics Reinforcement Learning (ODRL) seeks to transfer a policy from a source environment to a target environment characterized by distinct yet similar dynamics. In this context, traditional RL agents depend excessively on the dynamics of the source environment, resulting in the discovery of policies that excel in this environment but fail to provide reasonable performance in the target one. In the few-shot framework, a limited number of transitions from the target environment are introduced to facilitate a more effective transfer. Addressing this challenge, we propose an innovative approach inspired by recent advancements in Imitation Learning and Conservative RL algorithms. This method introduces a penalty to regulate the trajectories generated by the source-trained policy. We evaluate our method across various environments representing diverse off-dynamics conditions, where access to the target environment is extremely limited. These experiments include high-dimensional systems relevant to real-world applications. Across most tested scenarios, our proposed method demonstrates performance improvements compared to existing baselines.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-569607" status="VALID">
          <orgName>Huawei Technologies France</orgName>
          <date type="start">2014-04-01</date>
          <desc>
            <address>
              <addrLine>790 avenue Dr Maurice DonatMarco Polo A06250 Mougins</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.huawei.com/fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-431513" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1043346" status="OLD">
          <orgName>GIPSA - Modelling and Optimal Decision for Uncertain Systems</orgName>
          <orgName type="acronym">GIPSA-MODUS</orgName>
          <date type="start">2020-01-01</date>
          <date type="end">2025-12-31</date>
          <desc>
            <address>
              <addrLine>GIPSA-lab, 11 rue des Mathématiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-1043344" type="direct"/>
            <relation active="#struct-1043333" type="indirect"/>
            <relation name="UMR5216" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1042703" type="indirect"/>
            <relation active="#struct-1043329" type="indirect"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1043347" status="OLD">
          <orgName>GIPSA - Infinite Dimensional Dynamics</orgName>
          <orgName type="acronym">GIPSA-INFINITY</orgName>
          <date type="start">2020-01-01</date>
          <date type="end">2025-12-31</date>
          <desc>
            <address>
              <addrLine>GIPSA-lab, 11 rue des Mathématiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-1043344" type="direct"/>
            <relation active="#struct-1043333" type="indirect"/>
            <relation name="UMR5216" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1042703" type="indirect"/>
            <relation active="#struct-1043329" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1001229" status="VALID">
          <orgName>Criteo AI Lab</orgName>
          <desc>
            <address>
              <addrLine>Paris</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-458139" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-431513" status="VALID">
          <idno type="ROR">https://ror.org/02rbzf697</idno>
          <orgName>Huawei Technologies France [Boulogne-Billancourt]</orgName>
          <desc>
            <address>
              <addrLine>Arcs de Seine18 quai du Point du JourCS 7000392100 Boulogne Billancourt</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="department" xml:id="struct-1043344" status="VALID">
          <orgName>GIPSA Pôle Automatique et Diagnostic</orgName>
          <orgName type="acronym">GIPSA-PAD</orgName>
          <date type="start">2020-01-01</date>
          <date type="end">2025-12-31</date>
          <desc>
            <address>
              <addrLine>GIPSA-lab, 11 rue des Mathématiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-1043333" type="direct"/>
            <relation name="UMR5216" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1042703" type="indirect"/>
            <relation active="#struct-1043329" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1043333" status="VALID">
          <idno type="IdRef">137251122</idno>
          <idno type="ISNI">0000000118823396</idno>
          <idno type="RNSR">200711885T</idno>
          <idno type="ROR">https://ror.org/02wrme198</idno>
          <orgName>Grenoble Images Parole Signal Automatique</orgName>
          <orgName type="acronym">GIPSA-lab</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>GIPSA-lab 11 rue des Mathématiques, Grenoble Campus BP46F-38402 SAINT MARTIN D'HERES CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.gipsa-lab.inpg.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR5216" active="#struct-441569" type="direct"/>
            <relation active="#struct-1042703" type="direct"/>
            <relation active="#struct-1043329" type="direct"/>
          </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="regroupinstitution" xml:id="struct-1042703" status="VALID">
          <idno type="IdRef">240648315</idno>
          <idno type="ROR">https://ror.org/02rx3b187</idno>
          <orgName>Université Grenoble Alpes</orgName>
          <orgName type="acronym">UGA</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Adresse CS 40700 - 38058 Grenoble cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-grenoble-alpes.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1043329" status="VALID">
          <idno type="IdRef">026388804</idno>
          <idno type="ROR">https://ror.org/05sbt2524</idno>
          <orgName>Institut polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
          <orgName type="acronym">Grenoble INP</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>46 avenue Félix Viallet 38031 Grenoble Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.grenoble-inp.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1042703" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-458139" status="VALID">
          <orgName>Criteo [Paris]</orgName>
          <desc>
            <address>
              <addrLine>32 rue Blanche 75 009 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.criteo.com/fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>