{"id":"https://openalex.org/W2099658286","doi":"https://doi.org/10.1142/s021952591350015x","title":"COMBINING CORRELATION-BASED AND REWARD-BASED LEARNING IN NEURAL CONTROL FOR POLICY IMPROVEMENT","display_name":"COMBINING CORRELATION-BASED AND REWARD-BASED LEARNING IN NEURAL CONTROL FOR POLICY IMPROVEMENT","publication_year":2013,"publication_date":"2013-04-29","ids":{"openalex":"https://openalex.org/W2099658286","doi":"https://doi.org/10.1142/s021952591350015x","mag":"2099658286"},"language":"en","primary_location":{"id":"doi:10.1142/s021952591350015x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021952591350015x","pdf_url":null,"source":{"id":"https://openalex.org/S107361000","display_name":"Advances in Complex Systems","issn_l":"0219-5259","issn":["0219-5259","1793-6802","1793-9615","1793-9623"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Complex Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034246691","display_name":"Poramate Manoonpong","orcid":"https://orcid.org/0000-0002-4806-7576"},"institutions":[{"id":"https://openalex.org/I4210087171","display_name":"Bernstein Center for Computational Neuroscience G\u00f6ttingen","ror":"https://ror.org/003g6b432","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210087171","https://openalex.org/I4210092532"]},{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"PORAMATE MANOONPONG","raw_affiliation_strings":["ATR Computational Neuroscience Laboratories, 2-2-2 Hikaridai Seika-cho, Soraku-gun, Kyoto 619-0288, Japan","Bernstein Center for Computational Neuroscience, The Third Institute of Physics, University of G\u00f6ttingen, G\u00f6ttingen 37077, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Computational Neuroscience Laboratories, 2-2-2 Hikaridai Seika-cho, Soraku-gun, Kyoto 619-0288, Japan","institution_ids":[]},{"raw_affiliation_string":"Bernstein Center for Computational Neuroscience, The Third Institute of Physics, University of G\u00f6ttingen, G\u00f6ttingen 37077, Germany","institution_ids":["https://openalex.org/I4210087171","https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111954344","display_name":"Christoph Kolodziejski","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087171","display_name":"Bernstein Center for Computational Neuroscience G\u00f6ttingen","ror":"https://ror.org/003g6b432","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210087171","https://openalex.org/I4210092532"]},{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"CHRISTOPH KOLODZIEJSKI","raw_affiliation_strings":["Bernstein Center for Computational Neuroscience, The Third Institute of Physics, University of G\u00f6ttingen, G\u00f6ttingen 37077, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bernstein Center for Computational Neuroscience, The Third Institute of Physics, University of G\u00f6ttingen, G\u00f6ttingen 37077, Germany","institution_ids":["https://openalex.org/I4210087171","https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023811677","display_name":"Florentin W\u00f6rg\u00f6tter","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087171","display_name":"Bernstein Center for Computational Neuroscience G\u00f6ttingen","ror":"https://ror.org/003g6b432","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210087171","https://openalex.org/I4210092532"]},{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"FLORENTIN W\u00d6RG\u00d6TTER","raw_affiliation_strings":["Bernstein Center for Computational Neuroscience, The Third Institute of Physics, University of G\u00f6ttingen, G\u00f6ttingen 37077, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bernstein Center for Computational Neuroscience, The Third Institute of Physics, University of G\u00f6ttingen, G\u00f6ttingen 37077, Germany","institution_ids":["https://openalex.org/I4210087171","https://openalex.org/I74656192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025458882","display_name":"Jun Morimoto","orcid":"https://orcid.org/0000-0002-4115-1919"},"institutions":[{"id":"https://openalex.org/I4210087171","display_name":"Bernstein Center for Computational Neuroscience G\u00f6ttingen","ror":"https://ror.org/003g6b432","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210087171","https://openalex.org/I4210092532"]},{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"JUN MORIMOTO","raw_affiliation_strings":["ATR Computational Neuroscience Laboratories, 2-2-2 Hikaridai Seika-cho, Soraku-gun, Kyoto 619-0288, Japan","Bernstein Center for Computational Neuroscience, The Third Institute of Physics, University of G\u00f6ttingen, G\u00f6ttingen 37077, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Computational Neuroscience Laboratories, 2-2-2 Hikaridai Seika-cho, Soraku-gun, Kyoto 619-0288, Japan","institution_ids":[]},{"raw_affiliation_string":"Bernstein Center for Computational Neuroscience, The Third Institute of Physics, University of G\u00f6ttingen, G\u00f6ttingen 37077, Germany","institution_ids":["https://openalex.org/I4210087171","https://openalex.org/I74656192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4338,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90471152,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"16","issue":"02n03","first_page":"1350015","last_page":"1350015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9707000255584717,"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":0.8300584554672241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6641647815704346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6003695726394653},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5324194431304932},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46296003460884094},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.44225209951400757},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.42683714628219604},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4128496050834656},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4125761389732361},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38917648792266846},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2989668846130371},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.1508539915084839},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1334514617919922}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8300584554672241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6641647815704346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6003695726394653},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5324194431304932},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46296003460884094},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.44225209951400757},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.42683714628219604},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4128496050834656},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4125761389732361},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38917648792266846},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2989668846130371},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.1508539915084839},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1334514617919922},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1142/s021952591350015x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021952591350015x","pdf_url":null,"source":{"id":"https://openalex.org/S107361000","display_name":"Advances in Complex Systems","issn_l":"0219-5259","issn":["0219-5259","1793-6802","1793-9615","1793-9623"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Complex Systems","raw_type":"journal-article"},{"id":"pmh:oai:sdu.dk:openaire_cris_publications/15b81a55-efa6-4af9-9265-2124b2a00bb2","is_oa":false,"landing_page_url":"https://portal.findresearcher.sdu.dk/da/publications/15b81a55-efa6-4af9-9265-2124b2a00bb2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400423","display_name":"University of Southern Denmark Research Portal (University of Southern Denmark)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177969490","host_organization_name":"University of Southern Denmark","host_organization_lineage":["https://openalex.org/I177969490"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Manoonpong, P, Kolodziejski, C, W\u00f6rg\u00f6tter, F & Morimoto, J 2013, 'Combining Correlation-Based and Reward-Based Learning in Neural Control for Policy Improvement', Advances in Complex Systems, vol. 16, no. 2-3, 1350015. https://doi.org/10.1142/S021952591350015X","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:RePEc:wsi:acsxxx:v:16:y:2013:i:02:p:1350015-1-1350015-38","is_oa":false,"landing_page_url":"http://www.worldscinet.com/cgi-bin/details.cgi?type=html&id=pii:S021952591350015X","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:RePEc:wsi:acsxxx:v:16:y:2013:i:02n03:n:s021952591350015x","is_oa":false,"landing_page_url":"http://www.worldscientific.com/doi/abs/10.1142/S021952591350015X","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W160989634","https://openalex.org/W1484952941","https://openalex.org/W1497531449","https://openalex.org/W1536038439","https://openalex.org/W1568049844","https://openalex.org/W1568416023","https://openalex.org/W1578521162","https://openalex.org/W1592847719","https://openalex.org/W1597980240","https://openalex.org/W1599882658","https://openalex.org/W1604966734","https://openalex.org/W1777239053","https://openalex.org/W1821288245","https://openalex.org/W1966795887","https://openalex.org/W1970302770","https://openalex.org/W1979908112","https://openalex.org/W1996847178","https://openalex.org/W2001004911","https://openalex.org/W2005967666","https://openalex.org/W2009988656","https://openalex.org/W2017910024","https://openalex.org/W2039148875","https://openalex.org/W2040657708","https://openalex.org/W2043615441","https://openalex.org/W2044391780","https://openalex.org/W2050090126","https://openalex.org/W2051620263","https://openalex.org/W2056655352","https://openalex.org/W2057303784","https://openalex.org/W2060066549","https://openalex.org/W2065220180","https://openalex.org/W2066947576","https://openalex.org/W2070340706","https://openalex.org/W2080759927","https://openalex.org/W2091565802","https://openalex.org/W2095564494","https://openalex.org/W2097113539","https://openalex.org/W2098607794","https://openalex.org/W2105780862","https://openalex.org/W2111768113","https://openalex.org/W2113077545","https://openalex.org/W2113122939","https://openalex.org/W2113501460","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2126211886","https://openalex.org/W2136074593","https://openalex.org/W2136621137","https://openalex.org/W2141184901","https://openalex.org/W2143245633","https://openalex.org/W2144366468","https://openalex.org/W2148067905","https://openalex.org/W2159600763","https://openalex.org/W2160877908","https://openalex.org/W2162617871","https://openalex.org/W2167390657","https://openalex.org/W2167489871","https://openalex.org/W2167647761","https://openalex.org/W2167779676","https://openalex.org/W2170274374","https://openalex.org/W2176864480","https://openalex.org/W2292999476","https://openalex.org/W2573977285","https://openalex.org/W3011120880","https://openalex.org/W3035034888","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4301831348"],"related_works":["https://openalex.org/W3148138296","https://openalex.org/W4294873804","https://openalex.org/W3153786280","https://openalex.org/W2808546214","https://openalex.org/W3127551068","https://openalex.org/W2152445738","https://openalex.org/W2171128163","https://openalex.org/W225045806","https://openalex.org/W1502839564","https://openalex.org/W1987864653"],"abstract_inverted_index":{"Classical":[0],"conditioning":[1,9],"(conventionally":[2,10],"modeled":[3,11],"as":[4,12,76,92,103],"correlation-based":[5,57],"learning)":[6,17,64],"and":[7,65,98,194],"operant":[8],"reinforcement":[13,71],"learning":[14,32,44,58,62,67,72,147,189],"or":[15],"reward-based":[16,66],"have":[18],"been":[19],"found":[20],"in":[21,131],"biological":[22,38],"systems.":[23,53],"Evidence":[24],"shows":[25],"that":[26,111],"these":[27,37],"two":[28,187],"mechanisms":[29,190],"strongly":[30,115],"involve":[31],"about":[33],"associations.":[34],"Based":[35],"on":[36],"findings,":[39],"we":[40],"propose":[41],"a":[42,77,89,93,99,104,145,154,169],"new":[43],"model":[45,55,82,113,150],"to":[46,126,139,167,173],"achieve":[47],"successful":[48,155],"control":[49,96,107,119,156],"policies":[50],"for":[51,158,198],"artificial":[52],"This":[54,149],"combines":[56],"using":[59,68,144],"input":[60],"correlation":[61],"(ICO":[63],"continuous":[69],"actor\u2013critic":[70],"(RL),":[73],"thereby":[74],"working":[75],"dual":[78],"learner":[79],"system.":[80],"The":[81],"performance":[83],"is":[84],"evaluated":[85],"by":[86],"simulations":[87],"of":[88,135,185],"cart-pole":[90],"system":[91,102],"dynamic":[94],"motion":[95],"problem":[97],"mobile":[100],"robot":[101,163],"goal-directed":[105,159],"behavior":[106],"problem.":[108],"Results":[109],"show":[110],"the":[112,124,129,132,140,162,178],"can":[114,151,164,191],"improve":[116],"pole":[117,130],"balancing":[118],"policy,":[120],"i.e.,":[121,161],"it":[122],"allows":[123],"controller":[125],"learn":[127,166],"stabilizing":[128],"largest":[133],"domain":[134],"initial":[136],"conditions":[137],"compared":[138,172],"results":[141],"obtained":[142],"when":[143],"single":[146],"mechanism.":[148],"also":[152],"find":[153],"policy":[157],"behavior,":[160],"effectively":[165],"approach":[168],"given":[170],"goal":[171],"its":[174],"individual":[175],"components.":[176],"Thus,":[177],"study":[179],"pursued":[180],"here":[181],"sharpens":[182],"our":[183],"understanding":[184],"how":[186],"different":[188],"be":[192],"combined":[193],"complement":[195],"each":[196],"other":[197],"solving":[199],"complex":[200],"tasks.":[201]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}