{"id":"https://openalex.org/W2792645523","doi":"https://doi.org/10.1109/tnnls.2018.2806087","title":"Multisource Transfer Double DQN Based on Actor Learning","display_name":"Multisource Transfer Double DQN Based on Actor Learning","publication_year":2018,"publication_date":"2018-03-09","ids":{"openalex":"https://openalex.org/W2792645523","doi":"https://doi.org/10.1109/tnnls.2018.2806087","mag":"2792645523","pmid":"https://pubmed.ncbi.nlm.nih.gov/29771674"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2018.2806087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2806087","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5064538645","display_name":"Jie Pan","orcid":"https://orcid.org/0000-0002-4993-298X"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Pan","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108064895","display_name":"Xuesong Wang","orcid":"https://orcid.org/0000-0002-5327-1088"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Wang","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5327-1088","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091364297","display_name":"Yuhu Cheng","orcid":"https://orcid.org/0000-0003-2022-9999"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhu Cheng","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2022-9999","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003557943","display_name":"Qiang Yu","orcid":"https://orcid.org/0000-0002-8454-0500"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Yu","raw_affiliation_strings":["School of Electrical and Power Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Power Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064538645"],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":5.4152,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.96462158,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"29","issue":"6","first_page":"2227","last_page":"2238"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9664000272750854,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9614999890327454,"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/computer-science","display_name":"Computer science","score":0.742397665977478},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7315463423728943},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6940572261810303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.663658082485199},{"id":"https://openalex.org/keywords/negative-transfer","display_name":"Negative transfer","score":0.6268483400344849},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.578453779220581},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5133551955223083},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4533686637878418},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.416833758354187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742397665977478},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7315463423728943},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6940572261810303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.663658082485199},{"id":"https://openalex.org/C2779178101","wikidata":"https://www.wikidata.org/wiki/Q6987274","display_name":"Negative transfer","level":3,"score":0.6268483400344849},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.578453779220581},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5133551955223083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4533686637878418},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.416833758354187},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014163","descriptor_name":"Transfer, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014163","descriptor_name":"Transfer, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014163","descriptor_name":"Transfer, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2018.2806087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2806087","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:29771674","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29771674","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":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4779677174","display_name":null,"funder_award_id":"51607180","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5171279565","display_name":null,"funder_award_id":"BK20150203","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G6386838018","display_name":null,"funder_award_id":"61472424","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7031480287","display_name":null,"funder_award_id":"61772532","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W110451278","https://openalex.org/W166862392","https://openalex.org/W232085181","https://openalex.org/W1191599655","https://openalex.org/W1457482454","https://openalex.org/W1490954610","https://openalex.org/W1573267348","https://openalex.org/W1890963104","https://openalex.org/W1934909785","https://openalex.org/W2004030284","https://openalex.org/W2018629084","https://openalex.org/W2024162902","https://openalex.org/W2052688942","https://openalex.org/W2094387729","https://openalex.org/W2123178778","https://openalex.org/W2128905965","https://openalex.org/W2145339207","https://openalex.org/W2151210636","https://openalex.org/W2155968351","https://openalex.org/W2164077610","https://openalex.org/W2183137222","https://openalex.org/W2294065713","https://openalex.org/W2344415132","https://openalex.org/W2344786740","https://openalex.org/W2347074400","https://openalex.org/W2405379562","https://openalex.org/W2418667810","https://openalex.org/W2460299708","https://openalex.org/W2475089067","https://openalex.org/W2498017881","https://openalex.org/W2509783950","https://openalex.org/W2536385907","https://openalex.org/W2575472443","https://openalex.org/W2582616844","https://openalex.org/W2606378794","https://openalex.org/W2746553466","https://openalex.org/W2951115206","https://openalex.org/W2951799221","https://openalex.org/W2964043796","https://openalex.org/W2964179661","https://openalex.org/W4293138483","https://openalex.org/W4294535763","https://openalex.org/W6604483558","https://openalex.org/W6628598448","https://openalex.org/W6629554151","https://openalex.org/W6679426499","https://openalex.org/W6682314434","https://openalex.org/W6684391863","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6721101288","https://openalex.org/W6725861512","https://openalex.org/W6732325040"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2398668521","https://openalex.org/W2619137770","https://openalex.org/W2952841984"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,77,91,96,185,197,230,237],"(RL)":[3],"comprehensively":[4],"uses":[5],"the":[6,38,57,66,105,121,133,141,148,159,195,202,235],"psychological":[7],"mechanisms":[8],"of":[9,40,123,137,206],"\"trial":[10],"and":[11,13,15,25,43,110,117,179,204,218,239],"error\"":[12],"\"reward":[14],"punishment\"":[16],"in":[17,28,37,75,130],"RL":[18,48,102,106],"as":[19,21,216],"well":[20],"powerful":[22],"feature":[23,118],"expression":[24],"nonlinear":[26],"mapping":[27],"deep":[29,58,101],"learning.":[30,45],"Currently,":[31],"it":[32,210],"plays":[33],"an":[34,47],"essential":[35],"role":[36],"fields":[39],"artificial":[41],"intelligence":[42],"machine":[44],"Since":[46],"agent":[49,107],"needs":[50],"to":[51,68,103,120,140,157,168,173,200],"constantly":[52],"interact":[53],"with":[54,65,100,211],"its":[55],"surroundings,":[56],"Q":[59,143],"network":[60,71,150],"(DQN)":[61],"is":[62,92,98,145,151,187,192],"inevitably":[63],"faced":[64],"need":[67],"learn":[69],"numerous":[70],"parameters,":[72],"which":[73],"results":[74],"low":[76],"efficiency.":[78],"In":[79,166],"this":[80],"paper,":[81],"a":[82,182],"multisource":[83,183],"transfer":[84,95,111,149,184,231],"double":[85,155,219],"DQN":[86,156,217],"(MTDDQN)":[87],"based":[88],"on":[89,194,242],"actor":[90,229],"proposed.":[93],"The":[94,189],"technique":[97],"integrated":[99],"make":[104],"collect,":[108],"summarize,":[109],"action":[112,128,138,164],"knowledge,":[113],"including":[114],"policy":[115],"mimic":[116],"regression,":[119],"training":[122],"related":[124],"tasks.":[125],"There":[126],"exists":[127],"overestimation":[129],"DQN,":[131],"i.e.,":[132,172],"lower":[134],"probability":[135],"limit":[136],"corresponding":[139],"maximum":[142],"value":[144],"nonzero.":[146],"Therefore,":[147],"trained":[152],"by":[153,163,208],"using":[154],"eliminate":[158],"error":[160],"accumulation":[161],"caused":[162],"overestimation.":[165],"addition,":[167],"avoid":[169],"negative":[170],"transfer,":[171],"ensure":[174],"strong":[175],"correlations":[176],"between":[177],"source":[178],"target":[180,243],"tasks,":[181],"mechanism":[186],"applied.":[188],"Atari2600":[190],"game":[191],"tested":[193],"arcade":[196],"environment":[198],"platform":[199],"evaluate":[201],"feasibility":[203],"performance":[205],"MTDDQN":[207,224],"comparing":[209],"some":[212],"mainstream":[213],"approaches,":[214],"such":[215],"DQN.":[220],"Experiments":[221],"prove":[222],"that":[223],"achieves":[225],"not":[226],"only":[227],"human-like":[228],"capability,":[232],"but":[233],"also":[234],"desired":[236],"efficiency":[238],"testing":[240],"accuracy":[241],"task.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
