<?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>03433naa a22005657i 4500</leader>
  <controlfield tag="001">UMUN-OA-20261005-AI-038</controlfield>
  <controlfield tag="003">local</controlfield>
  <controlfield tag="005">20261005174825.0</controlfield>
  <controlfield tag="006">m     o  d        </controlfield>
  <controlfield tag="007">cr||||||||||||</controlfield>
  <controlfield tag="008">261005s2019    xx      o    u000 0 eng d</controlfield>
  <datafield tag="024" ind1="7" ind2=" ">
    <subfield code="a">10.1016/j.tics.2019.02.006</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="035" ind1=" " ind2=" ">
    <subfield code="a">(local)OpenAlex:W2938321354</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">Matthew Botvinick</subfield>
    <subfield code="e">author.</subfield>
  </datafield>
  <datafield tag="245" ind1="1" ind2="0">
    <subfield code="a">Reinforcement Learning, Fast and Slow /</subfield>
    <subfield code="c">Matthew Botvinick; Sam Ritter; Jane X. Wang [and others].</subfield>
  </datafield>
  <datafield tag="264" ind1=" " ind2="1">
    <subfield code="a">[Place of publication not identified] :</subfield>
    <subfield code="b">Elsevier BV,</subfield>
    <subfield code="c">2019.</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">Deep reinforcement learning (RL) methods have driven impressive advances in artificial intelligence in recent years, exceeding human performance in domains ranging from Atari to Go to no-limit poker. This progress has drawn the attention of cognitive scientists interested in understanding human learning. However, the concern has been raised that deep RL may be too sample-inefficient - that is, it may simply be too slow - to provide a plausible model of how humans learn. In the present review, we counter this critique by describing recently developed techniques that allow deep RL to operate more nimbly, solving problems much more quickly than previous methods. Although these techniques were developed in an AI context, we propose that they may have rich implications for psychology and neuroscience. A key insight, arising from these AI methods, concerns the fundamental connection between fast RL and slower, more incremental forms of learning.</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/W2938321354</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">sample efficiency</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">human learning</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">fast learning</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">incremental learning</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">learning speed</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">Sam Ritter</subfield>
    <subfield code="e">author.</subfield>
  </datafield>
  <datafield tag="700" ind1="0" ind2=" ">
    <subfield code="a">Jane X. Wang</subfield>
    <subfield code="e">author.</subfield>
  </datafield>
  <datafield tag="700" ind1="0" ind2=" ">
    <subfield code="a">Zeb Kurth-Nelson</subfield>
    <subfield code="e">author.</subfield>
  </datafield>
  <datafield tag="700" ind1="0" ind2=" ">
    <subfield code="a">Charles Blundell</subfield>
    <subfield code="e">author.</subfield>
  </datafield>
  <datafield tag="700" ind1="0" ind2=" ">
    <subfield code="a">Demis Hassabis</subfield>
    <subfield code="e">author.</subfield>
  </datafield>
  <datafield tag="773" ind1="0" ind2=" ">
    <subfield code="t">Trends in Cognitive Sciences</subfield>
    <subfield code="g">Vol. 23, no. 5, (2019), pages/article 408-422</subfield>
    <subfield code="x">1364-6613</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2="0">
    <subfield code="u">http://www.cell.com/article/S1364661319300610/pdf</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/W2938321354</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">595</subfield>
    <subfield code="d">595</subfield>
  </datafield>
</record>
