{"id":"https://openalex.org/W3019982035","doi":"https://doi.org/10.1109/tii.2020.2986501","title":"Cognitive Optimal-Setting Control of AIoT Industrial Applications With Deep Reinforcement Learning","display_name":"Cognitive Optimal-Setting Control of AIoT Industrial Applications With Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3019982035","doi":"https://doi.org/10.1109/tii.2020.2986501","mag":"3019982035"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2020.2986501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2020.2986501","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Informatics","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/A5046825475","display_name":"Ying-Hsun Lai","orcid":"https://orcid.org/0000-0003-0458-6435"},"institutions":[{"id":"https://openalex.org/I178613991","display_name":"National Taitung University","ror":"https://ror.org/05j9d8v51","country_code":"TW","type":"education","lineage":["https://openalex.org/I178613991"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ying-Hsun Lai","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taitung University, Taitung, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taitung University, Taitung, Taiwan","institution_ids":["https://openalex.org/I178613991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081261484","display_name":"Tung-Cheng Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tung-Cheng Wu","raw_affiliation_strings":["Department of Engineering Science, National Cheng Kung University, Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering Science, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103237662","display_name":"Chin\u2010Feng Lai","orcid":"https://orcid.org/0000-0001-7138-0272"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chin-Feng Lai","raw_affiliation_strings":["Department of Engineering Science, National Cheng Kung University, Tainan, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-7138-0272","affiliations":[{"raw_affiliation_string":"Department of Engineering Science, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049154222","display_name":"Laurence T. Yang","orcid":"https://orcid.org/0000-0002-7986-4244"},"institutions":[{"id":"https://openalex.org/I197191942","display_name":"St. Francis Xavier University","ror":"https://ror.org/01wcaxs37","country_code":"CA","type":"education","lineage":["https://openalex.org/I197191942"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Laurence Tianruo Yang","raw_affiliation_strings":["Department of Computer Science, St. Francis Xavier University, Antigonish, NS, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7986-4244","affiliations":[{"raw_affiliation_string":"Department of Computer Science, St. Francis Xavier University, Antigonish, NS, Canada","institution_ids":["https://openalex.org/I197191942"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055675863","display_name":"Xiaokang Zhou","orcid":"https://orcid.org/0000-0003-3488-4679"},"institutions":[{"id":"https://openalex.org/I171494771","display_name":"Shiga University","ror":"https://ror.org/01vvhy971","country_code":"JP","type":"education","lineage":["https://openalex.org/I171494771"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaokang Zhou","raw_affiliation_strings":["Faculty of Data Science, Shiga University, Hikone, Japan","RIKEN Center for Advanced Intelligence Project, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3488-4679","affiliations":[{"raw_affiliation_string":"Faculty of Data Science, Shiga University, Hikone, Japan","institution_ids":["https://openalex.org/I171494771"]},{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6505,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94226344,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"17","issue":"3","first_page":"2116","last_page":"2123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973000288009644,"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":0.9973000288009644,"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":0.9722999930381775,"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/T12676","display_name":"Machine Learning and ELM","score":0.9679999947547913,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.8376606702804565},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.798550009727478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6971607208251953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6687607169151306},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5818405747413635},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5574437379837036},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49782466888427734},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4545648396015167}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8376606702804565},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.798550009727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6971607208251953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6687607169151306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5818405747413635},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5574437379837036},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49782466888427734},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4545648396015167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2020.2986501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2020.2986501","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Informatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1515851193","https://openalex.org/W1522301498","https://openalex.org/W1985658808","https://openalex.org/W2008776027","https://openalex.org/W2034365297","https://openalex.org/W2115211925","https://openalex.org/W2132083787","https://openalex.org/W2145339207","https://openalex.org/W2146502635","https://openalex.org/W2150459019","https://openalex.org/W2155968351","https://openalex.org/W2167489871","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2746553466","https://openalex.org/W2752108245","https://openalex.org/W2785523195","https://openalex.org/W2786928559","https://openalex.org/W2806964477","https://openalex.org/W2810443361","https://openalex.org/W2912348842","https://openalex.org/W2962847657","https://openalex.org/W2963296584","https://openalex.org/W2963433607","https://openalex.org/W2963477884","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W2984291819","https://openalex.org/W4239610380","https://openalex.org/W6600284362","https://openalex.org/W6631190155","https://openalex.org/W6677067356","https://openalex.org/W6681435938","https://openalex.org/W6682142764","https://openalex.org/W6687681856","https://openalex.org/W6687688904","https://openalex.org/W6692846177","https://openalex.org/W6743845034","https://openalex.org/W6747620207","https://openalex.org/W6748554570"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4226420367","https://openalex.org/W3170224572","https://openalex.org/W3099765033","https://openalex.org/W4323060069"],"abstract_inverted_index":{"For":[0],"industrial":[1,92,229],"applications":[2],"of":[3,7,43,63,86,99,142,184,199,208,228],"the":[4,13,27,37,41,61,83,95,100,105,109,113,123,130,137,140,143,163,166,178,181,185,196,204,209,219,224],"artificial":[5],"intelligence":[6],"things,":[8],"mechanical":[9,33],"control":[10,34,58,227],"usually":[11],"affects":[12],"overall":[14],"product":[15],"output":[16],"and":[17,22,59,151,173],"production":[18],"schedule.":[19],"Recently,":[20],"more":[21,23],"engineers":[24],"have":[25],"applied":[26],"deep":[28,44,88],"reinforcement":[29,45,89],"learning":[30,46,77,90,149,155,189,213],"method":[31,78,126,156,190,214],"to":[32,35,67],"improve":[36],"company's":[38],"profit.":[39],"However,":[40],"problem":[42],"training":[47],"stage":[48],"is":[49,79,191],"that":[50,122,203],"overfitting":[51,132],"often":[52],"occurs,":[53],"which":[54],"results":[55],"in":[56,71,133,159,195],"accidental":[57],"increases":[60],"risk":[62],"overcontrol.":[64],"In":[65,136],"order":[66],"address":[68],"this":[69,72],"problem,":[70],"article,":[73],"an":[74],"expected":[75,153,187,211],"advantage":[76,148,154,188,212],"proposed":[80,124,186,210],"for":[81,91,223],"moderating":[82],"maximum":[84],"value":[85,131],"expectation-based":[87,125],"applications.":[93,230],"With":[94],"tanh":[96,110],"softmax":[97,101,114],"policy":[98],"function,":[102],"we":[103],"replace":[104],"sigmod":[106],"function":[107,111,115],"with":[108,162,177],"as":[112],"activation":[116],"value.":[117],"It":[118],"makes":[119],"it":[120],"so":[121],"can":[127],"successfully":[128],"decrease":[129],"cognitive":[134],"computing.":[135],"experimental":[138],"results,":[139],"performance":[141,217],"Deep":[144],"Q":[145],"Network":[146],"algorithm,":[147,150,180],"propose":[152],"were":[157],"evaluated":[158],"every":[160],"episodes":[161],"four":[164],"criteria:":[165],"total":[167,169,182],"score,":[168,172],"step,":[170],"average":[171],"highest":[174],"score.":[175],"Comparing":[176],"AL":[179],"score":[183],"increased":[192],"by":[193],"6%":[194],"same":[197],"number":[198],"trainings.":[200],"This":[201],"shows":[202],"action":[205],"probability":[206],"distribution":[207],"has":[215],"better":[216],"than":[218],"traditional":[220],"soft-max":[221],"strategy":[222],"optimal":[225],"setting":[226]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}