{"id":"https://openalex.org/W2981707302","doi":"https://doi.org/10.1016/j.neunet.2019.10.011","title":"A complementary learning systems approach to temporal difference learning","display_name":"A complementary learning systems approach to temporal difference learning","publication_year":2019,"publication_date":"2019-10-26","ids":{"openalex":"https://openalex.org/W2981707302","doi":"https://doi.org/10.1016/j.neunet.2019.10.011","mag":"2981707302","pmid":"https://pubmed.ncbi.nlm.nih.gov/31689680","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/6964152"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2019.10.011","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neunet.2019.10.011","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065665155","display_name":"Sam Blakeman","orcid":"https://orcid.org/0000-0002-5023-7933"},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sam Blakeman","raw_affiliation_strings":["Centre for Brain and Cognitive Development, Department of Psychological Sciences, Birkbeck, University of London, Malet Street, WC1E 7HX, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Centre for Brain and Cognitive Development, Department of Psychological Sciences, Birkbeck, University of London, Malet Street, WC1E 7HX, United Kingdom","institution_ids":["https://openalex.org/I98259816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073001689","display_name":"Denis Mareschal","orcid":"https://orcid.org/0000-0002-9828-9548"},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Denis Mareschal","raw_affiliation_strings":["Centre for Brain and Cognitive Development, Department of Psychological Sciences, Birkbeck, University of London, Malet Street, WC1E 7HX, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Centre for Brain and Cognitive Development, Department of Psychological Sciences, Birkbeck, University of London, Malet Street, WC1E 7HX, United Kingdom","institution_ids":["https://openalex.org/I98259816"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065665155"],"corresponding_institution_ids":["https://openalex.org/I98259816"],"apc_list":{"value":3350,"currency":"USD","value_usd":3350,"provenance":"doaj"},"apc_paid":{"value":3350,"currency":"USD","value_usd":3350,"provenance":"doaj"},"fwci":2.174,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":33,"citation_normalized_percentile":{"value":0.791058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":"122","issue":null,"first_page":"218","last_page":"230"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10448","display_name":"Memory and Neural Mechanisms","score":0.9996,"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"}},"topics":[{"id":"https://openalex.org/T10448","display_name":"Memory and Neural Mechanisms","score":0.9996,"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"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9994,"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"}},{"id":"https://openalex.org/T11685","display_name":"Zebrafish Biomedical Research Applications","score":0.994,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6857697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76062584},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6857697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.66531545},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.567153},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.55841213},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5225358},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43924344},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43541196},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38728586},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.104436725},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006624","descriptor_name":"Hippocampus","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013597","descriptor_name":"Systems Analysis","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013598","descriptor_name":"Systems Theory","qualifier_ui":"","qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2019.10.011","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://europepmc.org/articles/pmc6964152","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":["European Bioinformatics Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6964152","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://eprints.bbk.ac.uk/id/eprint/29596/8/29596a.pdf","pdf_url":"https://eprints.bbk.ac.uk/id/eprint/29596/8/29596a.pdf","source":{"id":"https://openalex.org/S4306400465","display_name":"BIROn (Birkbeck, University of London)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98259816","host_organization_name":"Birkbeck, University of London","host_organization_lineage":["https://openalex.org/I98259816"],"host_organization_lineage_names":["Birkbeck, University of London"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1905.02636","pdf_url":"https://arxiv.org/pdf/1905.02636","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31689680","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2019.10.011","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council","award_id":null}],"datasets":[],"versions":[],"referenced_works_count":41,"referenced_works":["https://openalex.org/W125252782","https://openalex.org/W1970006557","https://openalex.org/W1998436798","https://openalex.org/W2006760951","https://openalex.org/W2007414406","https://openalex.org/W2047057213","https://openalex.org/W2066605983","https://openalex.org/W2068084351","https://openalex.org/W2081030963","https://openalex.org/W2100983013","https://openalex.org/W2104148727","https://openalex.org/W2109059823","https://openalex.org/W2109152498","https://openalex.org/W2117726420","https://openalex.org/W2121863487","https://openalex.org/W2134368213","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2157088567","https://openalex.org/W2346736747","https://openalex.org/W2362143032","https://openalex.org/W2419438565","https://openalex.org/W2424347275","https://openalex.org/W2436711315","https://openalex.org/W2594466397","https://openalex.org/W2621551027","https://openalex.org/W2783761400","https://openalex.org/W2938321354","https://openalex.org/W2949633842","https://openalex.org/W2950347959","https://openalex.org/W2951066214","https://openalex.org/W2952504784","https://openalex.org/W2963305465","https://openalex.org/W2963871073","https://openalex.org/W2964043796","https://openalex.org/W3037207827","https://openalex.org/W3100366369","https://openalex.org/W3103780890","https://openalex.org/W4214717370","https://openalex.org/W4297732320"],"related_works":["https://openalex.org/W4321463377","https://openalex.org/W4308828368","https://openalex.org/W3038962357","https://openalex.org/W2768629321","https://openalex.org/W2341346307","https://openalex.org/W2189613824","https://openalex.org/W2154399718","https://openalex.org/W2145363145","https://openalex.org/W2130711276","https://openalex.org/W1528400370"],"abstract_inverted_index":{"Complementary":[0,134],"Learning":[1,69,137],"Systems":[2],"(CLS)":[3],"theory":[4,110],"suggests":[5,111],"that":[6,27,101,112,227,244],"the":[7,28,39,55,64,113,124,150,165,177,205,215,222,228,239],"brain":[8],"uses":[9],"a":[10,13,59,78,116,129,141,144,154,157,174,180,233],"'neocortical'":[11,29,79,155],"and":[12,106,156,176,182,195,200,242,251,254],"'hippocampal'":[14,40,117,158],"learning":[15,34,45,219],"system":[16,30,41,80,118],"to":[17,54,148,172,184,248],"achieve":[18],"complex":[19],"behaviour.":[20],"These":[21,211],"two":[22,240],"systems":[23,52,220,241],"are":[24,103],"complementary":[25,218],"in":[26,63,89],"relies":[31,42],"on":[32,43,191],"slow":[33],"of":[35,46,50,67,97,115,152,162,167,179,217,224,236],"distributed":[36,85],"representations":[37,86],"while":[38],"fast":[44],"pattern-separated":[47],"representations.":[48],"Both":[49],"these":[51,121],"project":[53],"striatum,":[56],"which":[57,139],"is":[58,100,232],"key":[60],"neural":[61],"structure":[62],"brain's":[65],"implementation":[66],"Reinforcement":[68],"(RL).":[70],"Current":[71],"deep":[72],"RL":[73],"approaches":[74,99],"share":[75],"similarities":[76],"with":[77,143],"because":[81],"they":[82,102],"slowly":[83],"learn":[84],"through":[87],"backpropagation":[88],"Deep":[90,207],"Neural":[91],"Networks":[92],"(DNNs).":[93],"An":[94],"ongoing":[95],"criticism":[96],"such":[98],"data":[104],"inefficient":[105],"lack":[107],"flexibility.":[108],"CLS":[109],"addition":[114],"could":[119],"address":[120],"criticisms.":[122],"In":[123],"present":[125],"study":[126],"we":[127],"propose":[128],"novel":[130],"algorithm":[131],"known":[132],"as":[133],"Temporal":[135,168],"Difference":[136,169],"(CTDL),":[138],"combines":[140],"DNN":[142,183],"Self-Organizing":[145],"Map":[146],"(SOM)":[147],"obtain":[149],"benefits":[151,203],"both":[153,249],"system.":[159],"Key":[160],"features":[161],"CTDL":[163,190],"include":[164],"use":[166],"(TD)":[170],"error":[171,230],"update":[173],"SOM":[175,181],"combination":[178],"calculate":[185],"action":[186,255],"values.":[187],"We":[188],"evaluate":[189],"Grid":[192],"World,":[193],"Cart-Pole":[194],"Continuous":[196],"Mountain":[197],"Car":[198],"tasks":[199],"show":[201],"several":[202],"over":[204],"classic":[206],"Q-Network":[208],"(DQN)":[209],"approach.":[210],"results":[212],"demonstrate":[213],"(1)":[214],"utility":[216],"for":[221],"evaluation":[223],"actions,":[225],"(2)":[226],"TD":[229],"signal":[231],"useful":[234],"form":[235],"communication":[237],"between":[238],"(3)":[243],"our":[245],"approach":[246],"extends":[247],"discrete":[250],"continuous":[252],"state":[253],"spaces.":[256]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2981707302","counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4}],"updated_date":"2025-01-07T17:46:48.054147","created_date":"2019-11-01"}