<?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-03479324</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="2026-05-22T12:02:13+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection</title>
            <author role="aut">
              <persName>
                <forename type="first">Matteo</forename>
                <surname>Papini</surname>
              </persName>
              <email type="md5">c9f7b871e93a15779ec4aba7e92a9c75</email>
              <email type="domain">upf.edu</email>
              <idno type="idhal" notation="numeric">1120314</idno>
              <idno type="halauthorid" notation="string">1273200-1120314</idno>
              <affiliation ref="#struct-490042"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Andrea</forename>
                <surname>Tirinzoni</surname>
              </persName>
              <email type="md5">70492e42b9ba249ca8b4a9b353e3e7aa</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="numeric">1115339</idno>
              <idno type="halauthorid" notation="string">1470990-1115339</idno>
              <affiliation ref="#struct-1042631"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Aldo</forename>
                <surname>Pacchiano</surname>
              </persName>
              <email type="md5">33d660f272be35df6de19785deaa873b</email>
              <email type="domain">microsoft.com</email>
              <idno type="idhal" notation="numeric">1118669</idno>
              <idno type="halauthorid" notation="string">2355349-1118669</idno>
              <affiliation ref="#struct-365620"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Marcello</forename>
                <surname>Restilli</surname>
              </persName>
              <email type="md5">4cd1e422477f5e0e425f27f33bacb42e</email>
              <email type="domain">polimi.it</email>
              <idno type="idhal" notation="numeric">1120315</idno>
              <idno type="halauthorid" notation="string">2368897-1120315</idno>
              <affiliation ref="#struct-490042"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Alessandro</forename>
                <surname>Lazaric</surname>
              </persName>
              <email type="md5">b86b90c8f78fc3c7fbc1cc70fc4ebad3</email>
              <email type="domain">fb.com</email>
              <idno type="idhal" notation="numeric">1105515</idno>
              <idno type="halauthorid" notation="string">18261-1105515</idno>
              <affiliation ref="#struct-267305"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Matteo</forename>
                <surname>Pirotta</surname>
              </persName>
              <email type="md5">647f5d9c2f18816b5173fed9dce524fa</email>
              <email type="domain">fb.com</email>
              <idno type="idhal" notation="numeric">1105514</idno>
              <idno type="halauthorid" notation="string">1270799-1105514</idno>
              <affiliation ref="#struct-267305"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Andrea</forename>
                <surname>Tirinzoni</surname>
              </persName>
              <email type="md5">70492e42b9ba249ca8b4a9b353e3e7aa</email>
              <email type="domain">inria.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-12-14 11:45:10</date>
              <date type="whenModified">2026-05-06 09:34:02</date>
              <date type="whenReleased">2021-12-14 13:53:16</date>
              <date type="whenProduced">2021-12-06</date>
              <date type="whenEndEmbargoed">2021-12-14</date>
              <ref type="file" target="https://inria.hal.science/hal-03479324v1/document">
                <date notBefore="2021-12-14"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-03479324v1/file/unisoft.pdf" id="file-3479324-3051416">
                <date notBefore="2021-12-14"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1111696">
                <persName>
                  <forename>Andrea</forename>
                  <surname>Tirinzoni</surname>
                </persName>
                <email type="md5">70492e42b9ba249ca8b4a9b353e3e7aa</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03479324</idno>
            <idno type="halUri">https://inria.hal.science/hal-03479324</idno>
            <idno type="halBibtex">papini:hal-03479324</idno>
            <idno type="halRefHtml">&lt;i&gt;Thirty-Fifth Conference on Neural Information Processing Systems&lt;/i&gt;, Dec 2021, Virtual, France</idno>
            <idno type="halRef">Thirty-Fifth Conference on Neural Information Processing Systems, Dec 2021, Virtual, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3479324-3051416"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <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="CRISTAL">Centre de Recherche en Informatique, Signal et Automatique de Lille (CRISTAL)</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</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="CRISTAL-SCOOL" corresp="CRISTAL">SCOOL</idno>
            <idno type="stamp" n="INRIA-ETATSUNIS">Copublications Inria-Etats-Unis</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">Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Matteo</forename>
                    <surname>Papini</surname>
                  </persName>
                  <email type="md5">c9f7b871e93a15779ec4aba7e92a9c75</email>
                  <email type="domain">upf.edu</email>
                  <idno type="idhal" notation="numeric">1120314</idno>
                  <idno type="halauthorid" notation="string">1273200-1120314</idno>
                  <affiliation ref="#struct-490042"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Andrea</forename>
                    <surname>Tirinzoni</surname>
                  </persName>
                  <email type="md5">70492e42b9ba249ca8b4a9b353e3e7aa</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="numeric">1115339</idno>
                  <idno type="halauthorid" notation="string">1470990-1115339</idno>
                  <affiliation ref="#struct-1042631"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Aldo</forename>
                    <surname>Pacchiano</surname>
                  </persName>
                  <email type="md5">33d660f272be35df6de19785deaa873b</email>
                  <email type="domain">microsoft.com</email>
                  <idno type="idhal" notation="numeric">1118669</idno>
                  <idno type="halauthorid" notation="string">2355349-1118669</idno>
                  <affiliation ref="#struct-365620"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Marcello</forename>
                    <surname>Restilli</surname>
                  </persName>
                  <email type="md5">4cd1e422477f5e0e425f27f33bacb42e</email>
                  <email type="domain">polimi.it</email>
                  <idno type="idhal" notation="numeric">1120315</idno>
                  <idno type="halauthorid" notation="string">2368897-1120315</idno>
                  <affiliation ref="#struct-490042"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Alessandro</forename>
                    <surname>Lazaric</surname>
                  </persName>
                  <email type="md5">b86b90c8f78fc3c7fbc1cc70fc4ebad3</email>
                  <email type="domain">fb.com</email>
                  <idno type="idhal" notation="numeric">1105515</idno>
                  <idno type="halauthorid" notation="string">18261-1105515</idno>
                  <affiliation ref="#struct-267305"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Matteo</forename>
                    <surname>Pirotta</surname>
                  </persName>
                  <email type="md5">647f5d9c2f18816b5173fed9dce524fa</email>
                  <email type="domain">fb.com</email>
                  <idno type="idhal" notation="numeric">1105514</idno>
                  <idno type="halauthorid" notation="string">1270799-1105514</idno>
                  <affiliation ref="#struct-267305"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Thirty-Fifth Conference on Neural Information Processing Systems</title>
                  <date type="start">2021-12-06</date>
                  <settlement>Virtual</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint/>
              </monogr>
            </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="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>We study the role of the representation of state-action value functions in regret minimization in finite-horizon Markov Decision Processes (MDPs) with linear structure. We first derive a necessary condition on the representation, called universally spanning optimal features (UNISOFT), to achieve constant regret in any MDP with linear reward function. This result encompasses the well-known settings of low-rank MDPs and, more generally, zero inherent Bellman error (also known as the Bellman closure assumption). We then demonstrate that this condition is also sufficient for these classes of problems by deriving a constant regret bound for two optimistic algorithms (LSVI-UCB and ELEANOR). Finally, we propose an algorithm for representation selection and we prove that it achieves constant regret when one of the given representations, or a suitable combination of them, satisfies the UNISOFT condition.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="department" xml:id="struct-490042" status="VALID">
          <orgName>Department of Electronics, Information, and Bioengineering [Milano]</orgName>
          <orgName type="acronym">DEIB</orgName>
          <date type="start">2017-04-03</date>
          <desc>
            <address>
              <country key="IT"/>
            </address>
            <ref type="url">http://www.deib.polimi.it/ita/home</ref>
          </desc>
          <listRelation>
            <relation active="#struct-125443" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1042631" status="VALID">
          <idno type="RNSR">202023603Y</idno>
          <idno type="ROR">https://ror.org/025wa0q37</idno>
          <orgName>Prise de décision séquentielle dans l’incertain</orgName>
          <orgName type="acronym">Scool</orgName>
          <date type="start">2020-07-01</date>
          <date type="end">2027-12-31</date>
          <desc>
            <address>
              <addrLine>Sequential decision making under uncertainty problemParc Scientifique de la Haute Borne 40, avenue Halley Bât.A, Park Plaza 59650 Villeneuve d'Ascq</addrLine>
              <country key="FR"/>
            </address>
          </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-365620" status="VALID">
          <orgName>Microsoft Research</orgName>
          <desc>
            <address>
              <country key="US"/>
            </address>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-267305" status="VALID">
          <orgName>Facebook AI Research [Paris]</orgName>
          <orgName type="acronym">FAIR</orgName>
          <desc>
            <address>
              <addrLine>Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://research.facebook.com/ai</ref>
          </desc>
          <listRelation>
            <relation active="#struct-332252" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-125443" status="VALID">
          <idno type="ISNI">0000 0004 1937 0327</idno>
          <idno type="ROR">https://ror.org/01nffqt88</idno>
          <orgName>Politecnico di Milano [Milan]</orgName>
          <orgName type="acronym">POLIMI</orgName>
          <desc>
            <address>
              <addrLine>Piazza Leonardo da Vinci, 32 20133 Milano</addrLine>
              <country key="IT"/>
            </address>
            <ref type="url">https://www.polimi.it/</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-332252" status="VALID">
          <orgName>Facebook</orgName>
          <desc>
            <address>
              <country key="US"/>
            </address>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>