<?xml version="1.0" encoding="UTF-8"?>
<mods xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://www.loc.gov/mods/v3" version="3.1" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-1.xsd">
  <titleInfo>
    <title>Reinforcement Learning, Fast and Slow</title>
  </titleInfo>
  <name type="personal">
    <namePart>Matthew Botvinick</namePart>
    <role>
      <roleTerm authority="marcrelator" type="text">creator</roleTerm>
    </role>
    <role>
      <roleTerm type="text">author.</roleTerm>
    </role>
  </name>
  <name type="personal">
    <namePart>Sam Ritter</namePart>
    <role>
      <roleTerm type="text">author.</roleTerm>
    </role>
  </name>
  <name type="personal">
    <namePart>Jane X. Wang</namePart>
    <role>
      <roleTerm type="text">author.</roleTerm>
    </role>
  </name>
  <name type="personal">
    <namePart>Zeb Kurth-Nelson</namePart>
    <role>
      <roleTerm type="text">author.</roleTerm>
    </role>
  </name>
  <name type="personal">
    <namePart>Charles Blundell</namePart>
    <role>
      <roleTerm type="text">author.</roleTerm>
    </role>
  </name>
  <name type="personal">
    <namePart>Demis Hassabis</namePart>
    <role>
      <roleTerm type="text">author.</roleTerm>
    </role>
  </name>
  <typeOfResource>text</typeOfResource>
  <genre authority="">Review articles.</genre>
  <originInfo>
    <place>
      <placeTerm type="code" authority="marccountry">xx</placeTerm>
    </place>
    <dateIssued encoding="marc">2019</dateIssued>
    <issuance>monographic</issuance>
  </originInfo>
  <language>
    <languageTerm authority="iso639-2b" type="code">eng</languageTerm>
  </language>
  <physicalDescription>
    <extent>1 online resource (1 article).</extent>
  </physicalDescription>
  <abstract>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.</abstract>
  <note type="statement of responsibility">Matthew Botvinick; Sam Ritter; Jane X. Wang [and others].</note>
  <note>Publication type: Review article.</note>
  <note>Linked open-access copy: published version.</note>
  <note>Open access; no subscription required for the linked open-access version. Unrestricted online access star</note>
  <note xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="https://openalex.org/W2938321354">Creative Commons Attribution (licence family recorded by the source; version not supplied in metadata). https://openalex.org/W2938321354</note>
  <note>In English.</note>
  <subject>
    <topic>deep reinforcement learning</topic>
  </subject>
  <subject>
    <topic>sample efficiency</topic>
  </subject>
  <subject>
    <topic>human learning</topic>
  </subject>
  <subject>
    <topic>fast learning</topic>
  </subject>
  <subject>
    <topic>incremental learning</topic>
  </subject>
  <subject>
    <topic>learning speed</topic>
  </subject>
  <subject>
    <topic>B. Sc. Artificial Intelligence</topic>
  </subject>
  <subject>
    <topic>UMUN open access collection</topic>
  </subject>
  <subject>
    <topic>reinforcement learning</topic>
  </subject>
  <relatedItem type="host">
    <titleInfo>
      <title>Trends in Cognitive Sciences</title>
    </titleInfo>
    <identifier type="issn">1364-6613</identifier>
    <part>
      <text>Vol. 23, no. 5, (2019), pages/article 408-422</text>
    </part>
  </relatedItem>
  <identifier type="uri">http://www.cell.com/article/S1364661319300610/pdf</identifier>
  <location>
    <url displayLabel="Read open-access publication">http://www.cell.com/article/S1364661319300610/pdf</url>
  </location>
  <accessCondition type="restrictionOnAccess">Open access; no subscription required for the linked open-access version.</accessCondition>
  <accessCondition type="useAndReproduction">Creative Commons Attribution (licence family recorded by the source; version not supplied in metadata).</accessCondition>
  <recordInfo>
    <recordContentSource authority="marcorg">local</recordContentSource>
    <recordCreationDate encoding="marc">261005</recordCreationDate>
    <recordChangeDate encoding="iso8601">20261005174825.0</recordChangeDate>
    <recordIdentifier source="local">UMUN-OA-20261005-AI-038</recordIdentifier>
    <languageOfCataloging>
      <languageTerm authority="iso639-2b" type="code">eng</languageTerm>
    </languageOfCataloging>
  </recordInfo>
</mods>
