{"id":"https://openalex.org/W1621787170","doi":"https://doi.org/10.1109/ijcnn.2015.7280636","title":"Continuous-time on-policy neural Reinforcement Learning of working memory tasks","display_name":"Continuous-time on-policy neural Reinforcement Learning of working memory tasks","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W1621787170","doi":"https://doi.org/10.1109/ijcnn.2015.7280636","mag":"1621787170"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2015.7280636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2015.7280636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ir.cwi.nl/pub/23907/23907B.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071457735","display_name":"Davide Zambrano","orcid":"https://orcid.org/0000-0003-3977-4647"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832","https://openalex.org/I4405262988"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Davide Zambrano","raw_affiliation_strings":["CWI Amsterdam, The Netherlands","CWI, Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CWI Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]},{"raw_affiliation_string":"CWI, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008620732","display_name":"Pieter R. Roelfsema","orcid":"https://orcid.org/0000-0002-1625-0034"},"institutions":[{"id":"https://openalex.org/I1295801184","display_name":"Netherlands Institute for Neuroscience","ror":"https://ror.org/05csn2x06","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1295801184","https://openalex.org/I1322597698"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Pieter R. Roelfsema","raw_affiliation_strings":["Department of Vision & Cognition Netherlands, Institute for Neuroscience (KNAW) Amsterdam, The Netherlands","Department of Vision and Cognition, Netherlands Institute for Neuroscience (KNAW), Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Vision & Cognition Netherlands, Institute for Neuroscience (KNAW) Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I1295801184"]},{"raw_affiliation_string":"Department of Vision and Cognition, Netherlands Institute for Neuroscience (KNAW), Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I1295801184"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005914878","display_name":"Sander M. Boht\u00e9","orcid":"https://orcid.org/0000-0002-7866-278X"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832","https://openalex.org/I4405262988"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Sander M. Bohte","raw_affiliation_strings":["CWI Amsterdam, The Netherlands","CWI, Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CWI Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]},{"raw_affiliation_string":"CWI, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2344,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80802955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"482","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7808924913406372},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7724325656890869},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6479368209838867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6246667504310608},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.6026984453201294},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5791077613830566},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5710047483444214},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5692057013511658},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.561184287071228},{"id":"https://openalex.org/keywords/working-memory","display_name":"Working memory","score":0.5581485033035278},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5471148490905762},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5089011192321777},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.49357593059539795},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.45806318521499634},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.4572131633758545},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42619192600250244},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4255807399749756},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41162675619125366},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.32737866044044495},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.1434665024280548}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7808924913406372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7724325656890869},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6479368209838867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6246667504310608},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.6026984453201294},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5791077613830566},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5710047483444214},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5692057013511658},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.561184287071228},{"id":"https://openalex.org/C21963081","wikidata":"https://www.wikidata.org/wiki/Q11337567","display_name":"Working memory","level":3,"score":0.5581485033035278},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5471148490905762},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5089011192321777},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.49357593059539795},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.45806318521499634},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.4572131633758545},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42619192600250244},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4255807399749756},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41162675619125366},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.32737866044044495},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.1434665024280548},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn.2015.7280636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2015.7280636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:cwi.nl:23907","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/23907","pdf_url":"https://ir.cwi.nl/pub/23907/23907B.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:cwi.nl:23907","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/23907","pdf_url":"https://ir.cwi.nl/pub/23907/23907B.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320885","display_name":"European Research Consortium for Informatics and Mathematics","ror":"https://ror.org/055zrhj18"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1621787170.pdf","grobid_xml":"https://content.openalex.org/works/W1621787170.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1536673555","https://openalex.org/W1978947708","https://openalex.org/W1994016657","https://openalex.org/W2011882079","https://openalex.org/W2020539709","https://openalex.org/W2020925019","https://openalex.org/W2031658574","https://openalex.org/W2037697248","https://openalex.org/W2038605385","https://openalex.org/W2053694398","https://openalex.org/W2064675550","https://openalex.org/W2096533821","https://openalex.org/W2106505783","https://openalex.org/W2113501460","https://openalex.org/W2120632836","https://openalex.org/W2139283936","https://openalex.org/W2145339207","https://openalex.org/W2153947321","https://openalex.org/W2165061373","https://openalex.org/W2295984314","https://openalex.org/W2912185451","https://openalex.org/W3139377883","https://openalex.org/W4241521318","https://openalex.org/W6632244493","https://openalex.org/W6645118935","https://openalex.org/W6674304311","https://openalex.org/W6676027264","https://openalex.org/W6680275833","https://openalex.org/W6682802936","https://openalex.org/W6696949133","https://openalex.org/W6792155000"],"related_works":["https://openalex.org/W2379153735","https://openalex.org/W2046172023","https://openalex.org/W2972896947","https://openalex.org/W2170146914","https://openalex.org/W2355105570","https://openalex.org/W2083974823","https://openalex.org/W2072751097","https://openalex.org/W2597948870","https://openalex.org/W2428505524","https://openalex.org/W2962722950"],"abstract_inverted_index":{"As":[0],"living":[1],"organisms,":[2],"one":[3],"of":[4,34,126,156,191,229,240],"our":[5,176],"primary":[6],"characteristics":[7],"is":[8,64,71,81,179],"the":[9,59,62,90,100,116,173,182,186,206,210,227,238,241,244],"ability":[10],"to":[11,16,27,38,53,65,67,76,84,88,96,103,113,131,136,142,224,226],"rapidly":[12,54],"process":[13],"and":[14,18,36,55,73],"react":[15,225],"unknown":[17],"unexpected":[19],"events.":[20],"To":[21,92],"this":[22],"end,":[23],"we":[24,151,200],"are":[25,50,194],"able":[26,52],"recognize":[28,68],"an":[29,215],"event":[30],"or":[31,135,243],"a":[32,110,119,123,137,153,160,167,230],"sequence":[33],"events":[35,228,242],"learn":[37,66,89,97,132,143],"respond":[39,57,93],"properly.":[40],"Despite":[41],"advances":[42],"in":[43,58,159,185,209],"machine":[44],"learning,":[45],"current":[46],"cognitive":[47],"robotic":[48],"systems":[49],"not":[51],"efficiently":[56],"real":[60,187],"world:":[61],"challenge":[63],"both":[69],"what":[70,174],"important,":[72],"also":[74],"when":[75,98,177],"act.":[77],"Reinforcement":[78],"Learning":[79],"(RL)":[80],"typically":[82],"used":[83],"solve":[85],"complex":[86],"tasks:":[87],"how.":[91],"quickly":[94],"-":[95,99],"environment":[101],"has":[102,112],"be":[104],"sampled":[105],"often":[106],"enough.":[107],"For":[108],"\u201cenough\u201d,":[109],"programmer":[111],"decide":[114],"on":[115,181],"step-size":[117],"as":[118],"time-representation,":[120],"choosing":[121],"between":[122,246],"fine-grained":[124],"representation":[125],"time":[127],"(many":[128],"state-transitions;":[129],"difficult":[130],"with":[133,144],"RL)":[134],"coarse":[138],"temporal":[139],"resolution":[140],"(easier":[141],"RL":[145,212],"but":[146],"lacking":[147],"precise":[148],"timing).":[149],"Here,":[150],"derive":[152],"continuous-time":[154,231],"version":[155],"on-policy":[157],"SARSA-learning":[158],"working-memory":[161],"neural":[162,168,211],"network":[163,171],"model,":[164],"AuGMEnT.":[165],"Using":[166],"working":[169],"memory":[170],"resolves":[172],"problem,":[175],"solution":[178],"built":[180],"notion":[183],"that":[184],"world,":[188],"instantaneous":[189],"actions":[190],"duration":[192,204,239],"dt":[193],"actually":[195],"impossible.":[196],"We":[197],"demonstrate":[198],"how":[199],"can":[201],"decouple":[202],"action":[203,216],"from":[205],"internal":[207],"time-steps":[208],"model":[213],"using":[214],"selection":[217],"system.":[218],"The":[219],"resultant":[220],"CT-AuGMEnT":[221],"successfully":[222],"learns":[223],"task,":[232],"without":[233],"any":[234],"pre-imposed":[235],"specifications":[236],"about":[237],"delays":[245],"them.":[247]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
