<?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>03851naa a22005177i 4500</leader>
  <controlfield tag="001">UMUN-OA-20261005-AI-022</controlfield>
  <controlfield tag="003">local</controlfield>
  <controlfield tag="005">20261005174824.0</controlfield>
  <controlfield tag="006">m     o  d        </controlfield>
  <controlfield tag="007">cr||||||||||||</controlfield>
  <controlfield tag="008">261005s2021    xx      o    u000 0 eng d</controlfield>
  <datafield tag="024" ind1="7" ind2=" ">
    <subfield code="a">10.1080/00207543.2021.1973138</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="035" ind1=" " ind2=" ">
    <subfield code="a">(local)OpenAlex:W3201000358</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">Marcel Panzer</subfield>
    <subfield code="e">author.</subfield>
  </datafield>
  <datafield tag="245" ind1="1" ind2="0">
    <subfield code="a">Deep reinforcement learning in production systems: a systematic literature review /</subfield>
    <subfield code="c">Marcel Panzer; Benedict Bender.</subfield>
  </datafield>
  <datafield tag="264" ind1=" " ind2="1">
    <subfield code="a">[Place of publication not identified] :</subfield>
    <subfield code="b">Taylor &amp; Francis,</subfield>
    <subfield code="c">2021.</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: Review 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">Shortening product development cycles and fully customisable products pose major challenges for production systems. These not only have to cope with an increased product diversity but also enable high throughputs and provide a high adaptability and robustness to process variations and unforeseen incidents. To overcome these challenges, deep Reinforcement Learning (RL) has been increasingly applied for the optimisation of production systems. Unlike other machine learning methods, deep RL operates on recently collected sensor-data in direct interaction with its environment and enables real-time responses to system changes. Although deep RL is already being deployed in production systems, a systematic review of the results has not yet been established. The main contribution of this paper is to provide researchers and practitioners an overview of applications and to motivate further implementations and research of deep RL supported production systems. Findings reveal that deep RL is applied in a variety of production domains, contributing to data-driven and flexible processes. In most applications, conventional methods were outperformed and implementation efforts or dependence on human experience were reduced. Nevertheless, future research must focus more on transferring the findings to real-world systems to analyse safety aspects and demonstrate reliability under prevailing conditions.</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="a">Creative Commons Attribution-NonCommercial-NoDerivatives (licence family recorded by the source; version not supplied in metadata).</subfield>
    <subfield code="u">https://openalex.org/W3201000358</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">deep reinforcement learning</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">production systems</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">production optimization</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">product development cycle</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">process variation</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">real-time control</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">Review articles.</subfield>
  </datafield>
  <datafield tag="700" ind1="0" ind2=" ">
    <subfield code="a">Benedict Bender</subfield>
    <subfield code="e">author.</subfield>
  </datafield>
  <datafield tag="773" ind1="0" ind2=" ">
    <subfield code="t">International Journal of Production Research</subfield>
    <subfield code="g">Vol. 60, no. 13, (2021), pages/article 4316-4341</subfield>
    <subfield code="x">0020-7543</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2="0">
    <subfield code="u">https://www.tandfonline.com/doi/pdf/10.1080/00207543.2021.1973138?needAccess=true</subfield>
    <subfield code="y">Read open-access publication</subfield>
    <subfield code="z">Open access. Access and licence reported by the source; this host could not be independently checked by automation.</subfield>
    <subfield code="7">0</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/W3201000358</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">579</subfield>
    <subfield code="d">579</subfield>
  </datafield>
</record>
