Associative search network: A reinforcement learning associative memory

Associative search network: A reinforcement learning associative memory

An associative memory system is presented which does not require a "teacher" to provide the desired associations. For each input key it conducts a search for the output pattern which optimizes an external payoff or reinforcement signal. The associative search network (ASN) combines pattern...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Biological cybernetics 1981-05, Vol.40 (3), p.201-211
Hauptverfasser: Barto, Andrew G., Sutton, Richard S., Brouwer, Peter S.
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 211
container_issue 3
container_start_page 201
container_title Biological cybernetics
container_volume 40
creator Barto, Andrew G.
Sutton, Richard S.
Brouwer, Peter S.
description An associative memory system is presented which does not require a "teacher" to provide the desired associations. For each input key it conducts a search for the output pattern which optimizes an external payoff or reinforcement signal. The associative search network (ASN) combines pattern recognition and function optimization capabilities in a simple and effective way. The authors define the associative search problem, discuss conditions under which the associative search network is capable of solving it, and present results from computer simulations. The synthesis of sensory-motor control surfaces is discussed as an example of the associative search problem.
doi_str_mv 10.1007/BF00453370
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_15339716</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>15339716</sourcerecordid><originalsourceid>FETCH-LOGICAL-c326t-bb76074637557f07713be5032c91edcbc6d545ea7f4ab3f41b162a7aa979e063</originalsourceid><addsrcrecordid>eNpNUDtPwzAYtBBIhMLCL_DEgBT4HL9ktlLRglSJpbvluF8gkNjFTkH9901VJJhuuIfujpBrBncMQN8_zgGE5FzDCSmY4FUJWsMpKYALKFkFcE4ucv4AAFNJU5DFNOfoWze030gzuuTfacDhJ6bPBzqlCdvQxOSxxzDQbuRDG96o-2fqsY9pd0nOGtdlvPrFCVnNn1az53L5uniZTZel55UayrrWCrRQXEupm7Eb4zVK4JU3DNe-9mothUSnG-Fq3ghWM1U57ZzRBkHxCbk5xm5S_NpiHmzfZo9d5wLGbbZs3G40Owhvj0KfYs4JG7tJbe_SzjKwh6vs31V8D_NVW3c</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>15339716</pqid></control><display><type>article</type><title>Associative search network: A reinforcement learning associative memory</title><source>SpringerLink Journals - AutoHoldings</source><creator>Barto, Andrew G. ; Sutton, Richard S. ; Brouwer, Peter S.</creator><creatorcontrib>Barto, Andrew G. ; Sutton, Richard S. ; Brouwer, Peter S.</creatorcontrib><description>An associative memory system is presented which does not require a "teacher" to provide the desired associations. For each input key it conducts a search for the output pattern which optimizes an external payoff or reinforcement signal. The associative search network (ASN) combines pattern recognition and function optimization capabilities in a simple and effective way. The authors define the associative search problem, discuss conditions under which the associative search network is capable of solving it, and present results from computer simulations. The synthesis of sensory-motor control surfaces is discussed as an example of the associative search problem.</description><identifier>ISSN: 0340-1200</identifier><identifier>EISSN: 1432-0770</identifier><identifier>DOI: 10.1007/BF00453370</identifier><language>eng</language><ispartof>Biological cybernetics, 1981-05, Vol.40 (3), p.201-211</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c326t-bb76074637557f07713be5032c91edcbc6d545ea7f4ab3f41b162a7aa979e063</citedby><cites>FETCH-LOGICAL-c326t-bb76074637557f07713be5032c91edcbc6d545ea7f4ab3f41b162a7aa979e063</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Barto, Andrew G.</creatorcontrib><creatorcontrib>Sutton, Richard S.</creatorcontrib><creatorcontrib>Brouwer, Peter S.</creatorcontrib><title>Associative search network: A reinforcement learning associative memory</title><title>Biological cybernetics</title><description>An associative memory system is presented which does not require a "teacher" to provide the desired associations. For each input key it conducts a search for the output pattern which optimizes an external payoff or reinforcement signal. The associative search network (ASN) combines pattern recognition and function optimization capabilities in a simple and effective way. The authors define the associative search problem, discuss conditions under which the associative search network is capable of solving it, and present results from computer simulations. The synthesis of sensory-motor control surfaces is discussed as an example of the associative search problem.</description><issn>0340-1200</issn><issn>1432-0770</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1981</creationdate><recordtype>article</recordtype><recordid>eNpNUDtPwzAYtBBIhMLCL_DEgBT4HL9ktlLRglSJpbvluF8gkNjFTkH9901VJJhuuIfujpBrBncMQN8_zgGE5FzDCSmY4FUJWsMpKYALKFkFcE4ucv4AAFNJU5DFNOfoWze030gzuuTfacDhJ6bPBzqlCdvQxOSxxzDQbuRDG96o-2fqsY9pd0nOGtdlvPrFCVnNn1az53L5uniZTZel55UayrrWCrRQXEupm7Eb4zVK4JU3DNe-9mothUSnG-Fq3ghWM1U57ZzRBkHxCbk5xm5S_NpiHmzfZo9d5wLGbbZs3G40Owhvj0KfYs4JG7tJbe_SzjKwh6vs31V8D_NVW3c</recordid><startdate>19810501</startdate><enddate>19810501</enddate><creator>Barto, Andrew G.</creator><creator>Sutton, Richard S.</creator><creator>Brouwer, Peter S.</creator><scope>AAYXX</scope><scope>CITATION</scope><scope>7QG</scope></search><sort><creationdate>19810501</creationdate><title>Associative search network: A reinforcement learning associative memory</title><author>Barto, Andrew G. ; Sutton, Richard S. ; Brouwer, Peter S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c326t-bb76074637557f07713be5032c91edcbc6d545ea7f4ab3f41b162a7aa979e063</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1981</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Barto, Andrew G.</creatorcontrib><creatorcontrib>Sutton, Richard S.</creatorcontrib><creatorcontrib>Brouwer, Peter S.</creatorcontrib><collection>CrossRef</collection><collection>Animal Behavior Abstracts</collection><jtitle>Biological cybernetics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Barto, Andrew G.</au><au>Sutton, Richard S.</au><au>Brouwer, Peter S.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Associative search network: A reinforcement learning associative memory</atitle><jtitle>Biological cybernetics</jtitle><date>1981-05-01</date><risdate>1981</risdate><volume>40</volume><issue>3</issue><spage>201</spage><epage>211</epage><pages>201-211</pages><issn>0340-1200</issn><eissn>1432-0770</eissn><abstract>An associative memory system is presented which does not require a "teacher" to provide the desired associations. For each input key it conducts a search for the output pattern which optimizes an external payoff or reinforcement signal. The associative search network (ASN) combines pattern recognition and function optimization capabilities in a simple and effective way. The authors define the associative search problem, discuss conditions under which the associative search network is capable of solving it, and present results from computer simulations. The synthesis of sensory-motor control surfaces is discussed as an example of the associative search problem.</abstract><doi>10.1007/BF00453370</doi><tpages>11</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0340-1200
ispartof Biological cybernetics, 1981-05, Vol.40 (3), p.201-211
issn 0340-1200
1432-0770
language eng
recordid cdi_proquest_miscellaneous_15339716
source SpringerLink Journals - AutoHoldings
title Associative search network: A reinforcement learning associative memory
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T00%3A08%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Associative%20search%20network:%20A%20reinforcement%20learning%20associative%20memory&rft.jtitle=Biological%20cybernetics&rft.au=Barto,%20Andrew%20G.&rft.date=1981-05-01&rft.volume=40&rft.issue=3&rft.spage=201&rft.epage=211&rft.pages=201-211&rft.issn=0340-1200&rft.eissn=1432-0770&rft_id=info:doi/10.1007/BF00453370&rft_dat=%3Cproquest_cross%3E15339716%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=15339716&rft_id=info:pmid/&rfr_iscdi=true