<?xml version="1.0" encoding="UTF-8"?>
<record
    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://www.loc.gov/MARC21/slim http://www.loc.gov/standards/marcxml/schema/MARC21slim.xsd"
    xmlns="http://www.loc.gov/MARC21/slim">

  <leader>03886naa a22004937i 4500</leader>
  <controlfield tag="001">UMUN-OA-20261005-AI-046</controlfield>
  <controlfield tag="003">local</controlfield>
  <controlfield tag="005">20261005174826.0</controlfield>
  <controlfield tag="006">m     o  d        </controlfield>
  <controlfield tag="007">cr||||||||||||</controlfield>
  <controlfield tag="008">261005s2023    xx      o    u000 0 eng d</controlfield>
  <datafield tag="024" ind1="7" ind2=" ">
    <subfield code="a">10.1109/tnnls.2023.3250269</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="035" ind1=" " ind2=" ">
    <subfield code="a">(local)OpenAlex:W4360584316</subfield>
  </datafield>
  <datafield tag="040" ind1=" " ind2=" ">
    <subfield code="a">local</subfield>
    <subfield code="b">eng</subfield>
    <subfield code="c">local</subfield>
  </datafield>
  <datafield tag="041" ind1="0" ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="100" ind1="0" ind2=" ">
    <subfield code="a">Rafael Figueiredo Prudencio</subfield>
    <subfield code="e">author.</subfield>
  </datafield>
  <datafield tag="245" ind1="1" ind2="2">
    <subfield code="a">A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems /</subfield>
    <subfield code="c">Rafael Figueiredo Prudencio; Marcos R. O. A. Maximo; Esther Luna Colombini.</subfield>
  </datafield>
  <datafield tag="264" ind1=" " ind2="1">
    <subfield code="a">[Place of publication not identified] :</subfield>
    <subfield code="b">Institute of Electrical and Electronics Engineers,</subfield>
    <subfield code="c">2023.</subfield>
  </datafield>
  <datafield tag="300" ind1=" " ind2=" ">
    <subfield code="a">1 online resource (1 article).</subfield>
  </datafield>
  <datafield tag="336" ind1=" " ind2=" ">
    <subfield code="a">text</subfield>
    <subfield code="b">txt</subfield>
    <subfield code="2">rdacontent</subfield>
  </datafield>
  <datafield tag="337" ind1=" " ind2=" ">
    <subfield code="a">computer</subfield>
    <subfield code="b">c</subfield>
    <subfield code="2">rdamedia</subfield>
  </datafield>
  <datafield tag="338" ind1=" " ind2=" ">
    <subfield code="a">online resource</subfield>
    <subfield code="b">cr</subfield>
    <subfield code="2">rdacarrier</subfield>
  </datafield>
  <datafield tag="500" ind1=" " ind2=" ">
    <subfield code="a">Publication type: Journal article.</subfield>
  </datafield>
  <datafield tag="500" ind1=" " ind2=" ">
    <subfield code="a">Linked open-access copy: published version.</subfield>
  </datafield>
  <datafield tag="506" ind1="0" ind2=" ">
    <subfield code="a">Open access; no subscription required for the linked open-access version.</subfield>
    <subfield code="f">Unrestricted online access</subfield>
    <subfield code="2">star</subfield>
  </datafield>
  <datafield tag="520" ind1="3" ind2=" ">
    <subfield code="a">With the widespread adoption of deep learning, reinforcement learning (RL) has experienced a dramatic increase in popularity, scaling to previously intractable problems, such as playing complex games from pixel observations, sustaining conversations with humans, and controlling robotic agents. However, there is still a wide range of domains inaccessible to RL due to the high cost and danger of interacting with the environment. Offline RL is a paradigm that learns exclusively from static datasets of previously collected interactions, making it feasible to extract policies from large and diverse training datasets. Effective offline RL algorithms have a much wider range of applications than online RL, being particularly appealing for real-world applications, such as education, healthcare, and robotics. In this work, we contribute with a unifying taxonomy to classify offline RL methods. Furthermore, we provide a comprehensive review of the latest algorithmic breakthroughs in the field using a unified notation as well as a review of existing benchmarks' properties and shortcomings. Additionally, we provide a figure that summarizes the performance of each method and class of methods on different dataset properties, equipping researchers with the tools to decide which type of algorithm is best suited for the problem at hand and identify which classes of algorithms look the most promising. Finally, we provide our perspective on open problems and propose future research directions for this rapidly growing field.</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="a">Creative Commons Attribution (licence family recorded by the source; version not supplied in metadata).</subfield>
    <subfield code="u">https://openalex.org/W4360584316</subfield>
  </datafield>
  <datafield tag="546" ind1=" " ind2=" ">
    <subfield code="a">In English.</subfield>
  </datafield>
  <datafield tag="588" ind1="0" ind2=" ">
    <subfield code="a">Description generated from OpenAlex bibliographic metadata retrieved on 5 October 2026; full text linked from the source.</subfield>
  </datafield>
  <datafield tag="590" ind1=" " ind2=" ">
    <subfield code="a">Course allocation: B. Sc. Artificial Intelligence.</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">offline reinforcement learning</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">benchmark dataset</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">algorithm comparison</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">B. Sc. Artificial Intelligence</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">UMUN open access collection</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">reinforcement learning</subfield>
  </datafield>
  <datafield tag="655" ind1=" " ind2="4">
    <subfield code="a">Journal articles.</subfield>
  </datafield>
  <datafield tag="700" ind1="0" ind2=" ">
    <subfield code="a">Marcos R. O. A. Maximo</subfield>
    <subfield code="e">author.</subfield>
  </datafield>
  <datafield tag="700" ind1="0" ind2=" ">
    <subfield code="a">Esther Luna Colombini</subfield>
    <subfield code="e">author.</subfield>
  </datafield>
  <datafield tag="773" ind1="0" ind2=" ">
    <subfield code="t">IEEE Transactions on Neural Networks and Learning Systems</subfield>
    <subfield code="g">Vol. 35, no. 8, (2023), pages/article 10237-10257</subfield>
    <subfield code="x">2162-237X</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2="0">
    <subfield code="u">https://ieeexplore.ieee.org/ielx7/5962385/6104215/10078377.pdf</subfield>
    <subfield code="y">Read open-access publication</subfield>
    <subfield code="z">Open access.</subfield>
    <subfield code="7">0</subfield>
    <subfield code="q">application/pdf</subfield>
  </datafield>
  <datafield tag="884" ind1=" " ind2=" ">
    <subfield code="a">Course selection and automated MARC21 enrichment from OpenAlex metadata.</subfield>
    <subfield code="g">20261005</subfield>
    <subfield code="k">https://openalex.org/W4360584316</subfield>
    <subfield code="q">local</subfield>
  </datafield>
  <datafield tag="942" ind1=" " ind2=" ">
    <subfield code="n">0</subfield>
  </datafield>
  <datafield tag="999" ind1=" " ind2=" ">
    <subfield code="c">603</subfield>
    <subfield code="d">603</subfield>
  </datafield>
</record>
