<?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-01629654</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="2026-05-24T17:19:08+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Bridging the Gap Between Imitation Learning and Inverse Reinforcement Learning</title>
            <author role="aut">
              <persName>
                <forename type="first">Bilal</forename>
                <surname>Piot</surname>
              </persName>
              <idno type="halauthorid">638076-0</idno>
              <affiliation ref="#struct-242819"/>
              <affiliation ref="#struct-432036"/>
            </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-411575"/>
              <affiliation ref="#struct-237201"/>
            </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-432036"/>
              <affiliation ref="#struct-242819"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Matthieu</forename>
                <surname>GEIST</surname>
              </persName>
              <email type="md5">c025140e3cc06ac39e7de0f0db2a4b70</email>
              <email type="domain">univ-lorraine.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2017-11-06 16:15:54</date>
              <date type="whenModified">2026-03-26 08:18:01</date>
              <date type="whenReleased">2017-11-07 14:56:59</date>
              <date type="whenProduced">2017-08</date>
              <date type="whenEndEmbargoed">2017-11-06</date>
              <ref type="file" target="https://hal.science/hal-01629654v1/document">
                <date notBefore="2017-11-06"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01629654v1/file/TNNLS_2016_BPMGOP.pdf" id="file-1629654-1675012">
                <date notBefore="2017-11-06"/>
              </ref>
              <ref type="externalLink" target="https://hal.archives-ouvertes.fr/hal-01629654/file/TNNLS_2016_BPMGOP.pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="330688">
                <persName>
                  <forename>Matthieu</forename>
                  <surname>GEIST</surname>
                </persName>
                <email type="md5">c025140e3cc06ac39e7de0f0db2a4b70</email>
                <email type="domain">univ-lorraine.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01629654</idno>
            <idno type="halUri">https://hal.science/hal-01629654</idno>
            <idno type="halBibtex">piot:hal-01629654</idno>
            <idno type="halRefHtml">&lt;i&gt;IEEE Transactions on Neural Networks and Learning Systems&lt;/i&gt;, 2017, 28 (8), pp.1814 - 1826. &lt;a target="_blank" href="https://dx.doi.org/10.1109/TNNLS.2016.2543000"&gt;&amp;#x27E8;10.1109/TNNLS.2016.2543000&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">IEEE Transactions on Neural Networks and Learning Systems, 2017, 28 (8), pp.1814 - 1826. &amp;#x27E8;10.1109/TNNLS.2016.2543000&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1629654-1675012"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="INSU">INSU - Institut National des Sciences de l'Univers</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="INRIA-LILLE">INRIA Lille - Nord Europe</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="MALIS" corresp="UMI-GTL">Equipe : MAchine Learning and Interactive Systems</idno>
            <idno type="stamp" n="UMI-GTL">IRL2958-GT-CNRS</idno>
            <idno type="stamp" n="UMI-COMPUTERSCIENCE">UMI 2958 - Axe de recherche : Computer Science</idno>
            <idno type="stamp" n="CRISTAL">Centre de Recherche en Informatique, Signal et Automatique de Lille (CRISTAL)</idno>
            <idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="CRISTAL-SEQUEL" corresp="CRISTAL">CRISTAL-SEQUEL</idno>
            <idno type="stamp" n="LIEC-UL">LIEC</idno>
            <idno type="stamp" n="OTELO-UL">Pôle scientifique Observatoire Terre et Environnement de Lorraine de l'Université de Lorraine</idno>
            <idno type="stamp" n="CENTRALESUPELEC-SACLAY" corresp="UNIV-PARIS-SACLAY">CENTRALESUPELEC-SACLAY</idno>
            <idno type="stamp" n="INRIA2017">INRIA2017</idno>
            <idno type="stamp" n="UNIV-LILLE">Université de Lille</idno>
            <idno type="stamp" n="TEST-HALCNRS">Collection test HAL CNRS</idno>
            <idno type="stamp" n="INRIAARTDOI">INRIAARTDOI</idno>
            <idno type="stamp" n="TEST4-HALCNRS">collection test</idno>
            <idno type="stamp" n="INRIA-ROYAUMEUNI">INRIA-ROYAUMEUNI</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">Bridging the Gap Between Imitation Learning and Inverse Reinforcement Learning</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Bilal</forename>
                    <surname>Piot</surname>
                  </persName>
                  <idno type="halauthorid">638076-0</idno>
                  <affiliation ref="#struct-242819"/>
                  <affiliation ref="#struct-432036"/>
                </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-411575"/>
                  <affiliation ref="#struct-237201"/>
                </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-432036"/>
                  <affiliation ref="#struct-242819"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">81027</idno>
                <idno type="issn">2162-237X</idno>
                <title level="j">IEEE Transactions on Neural Networks and Learning Systems</title>
                <imprint>
                  <publisher>IEEE</publisher>
                  <biblScope unit="volume">28</biblScope>
                  <biblScope unit="issue">8</biblScope>
                  <biblScope unit="pp">1814 - 1826</biblScope>
                  <date type="datePub">2017-08</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/TNNLS.2016.2543000</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Learning from Demonstrations</term>
                <term xml:lang="en">Inverse Reinforcement Learning</term>
                <term xml:lang="en">Imitation Learning</term>
              </keywords>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</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>—Learning from Demonstrations (LfD) is a paradigm by which an apprentice agent learns a control policy for a dynamic environment by observing demonstrations delivered by an expert agent. It is usually implemented as either Imitation Learning (IL) or Inverse Reinforcement Learning (IRL) in the literature. On the one hand, IRL is a paradigm relying on Markov Decision Processes (MDPs), where the goal of the apprentice agent is to find a reward function from the expert demonstrations that could explain the expert behavior. On the other hand, IL consists in directly generalizing the expert strategy, observed in the demonstrations, to unvisited states (and it is therefore close to classification, when there is a finite set of possible decisions). While these two visions are often considered as opposite to each other, the purpose of this paper is to exhibit a formal link between these approaches from which new algorithms can be derived. We show that IL and IRL can be redefined in a way that they are equivalent, in the sense that there exists an explicit bijective operator (namely the inverse optimal Bellman operator) between their respective spaces of solutions. To do so, we introduce the set-policy framework which creates a clear link between IL and IRL. As a result, IL and IRL solutions making the best of both worlds are obtained. In addition, it is a unifying framework from which existing IL and IRL algorithms can be derived and which opens the way for IL methods able to deal with the environment's dynamics. Finally, the IRL algorithms derived from the set-policy framework are compared to algorithms belonging to the more common trajectory-matching family. Experiments demonstrate that the set-policy-based algorithms outperform both standard IRL and IL ones and result in more robust solutions.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-242819" status="VALID">
          <orgName>DeepMind [London]</orgName>
          <desc>
            <address>
              <country key="GB"/>
            </address>
            <ref type="url">https://deepmind.com/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-358168" type="direct"/>
          </listRelation>
        </org>
        <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="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="laboratory" xml:id="struct-237201" status="VALID">
          <idno type="IdRef">174161565</idno>
          <idno type="ISNI">0000000417588250</idno>
          <idno type="RNSR">201320576N</idno>
          <idno type="IdUnivLorraine">[UL]RRI--</idno>
          <idno type="ROR">https://ror.org/05je79696</idno>
          <orgName>Laboratoire Interdisciplinaire des Environnements Continentaux</orgName>
          <orgName type="acronym">LIEC</orgName>
          <date type="start">2013-01-01</date>
          <desc>
            <address>
              <addrLine>Site Charmois : 15 Avenue du Charmois, F-54500 VANDOEUVRE-LES-NANCY ; Site Aiguillettes : Faculté des Sciences et Technologies, F-54506 VANDOEUVRE-LES-NANCY ; Site Bridoux : Campus Bridoux - Rue du Général Delestraint, F-57070 METZ ; Site Thionville : IUT de Thionville-Yutz - Espace Cormontaigne, F-57970 THIONVILLE-YUTZ</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://liec.univ-lorraine.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR7360" active="#struct-300045" type="direct"/>
            <relation active="#struct-413289" type="direct"/>
            <relation name="UMR7360" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-358168" status="VALID">
          <orgName>DeepMind Technologies</orgName>
          <desc>
            <address>
              <country key="GB"/>
            </address>
            <ref type="url">https://deepmind.com/</ref>
          </desc>
        </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="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="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>
        <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="institution" xml:id="struct-300045" status="VALID">
          <idno type="IdRef">029349265</idno>
          <idno type="ISNI">0000 0001 2154 1736</idno>
          <idno type="ROR">https://ror.org/04kdfz702</idno>
          <idno type="Wikidata">Q3152437</idno>
          <orgName>Institut national des sciences de l'Univers</orgName>
          <orgName type="acronym">INSU - CNRS</orgName>
          <date type="start">2007-04-19</date>
          <desc>
            <address>
              <addrLine>INSU-CNRS3 rue Michel-Ange, 75794 Paris Cedex 16</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.insu.cnrs.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>
      </listOrg>
    </back>
  </text>
</TEI>