{"id":"https://openalex.org/W2978041660","doi":"https://doi.org/10.1109/ijcnn.2019.8851690","title":"Deep Reinforcement Learning with Dual Targeting Algorithm","display_name":"Deep Reinforcement Learning with Dual Targeting Algorithm","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2978041660","doi":"https://doi.org/10.1109/ijcnn.2019.8851690","mag":"2978041660"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851690","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5071120983","display_name":"Naoki Kodama","orcid":"https://orcid.org/0000-0003-3412-8558"},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoki Kodama","raw_affiliation_strings":["Department of Industrial Administration, Tokyo University of Science, Chiba, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Administration, Tokyo University of Science, Chiba, Japan","institution_ids":["https://openalex.org/I161296585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029835691","display_name":"Taku Harada","orcid":"https://orcid.org/0000-0001-5410-7514"},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taku Harada","raw_affiliation_strings":["Department of Industrial Administration, Tokyo University of Science, Chiba, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Administration, Tokyo University of Science, Chiba, Japan","institution_ids":["https://openalex.org/I161296585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062124983","display_name":"Kazuteru Miyazaki","orcid":"https://orcid.org/0000-0001-8175-213X"},"institutions":[{"id":"https://openalex.org/I4210100966","display_name":"National Institution for Academic Degrees and Quality Enhancement of Higher Education","ror":"https://ror.org/01cdnw320","country_code":"JP","type":"other","lineage":["https://openalex.org/I4210100966"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuteru Miyazaki","raw_affiliation_strings":["Research Department, National Institution for Academic Degrees and Quality Enhancement of Higher Education, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Research Department, National Institution for Academic Degrees and Quality Enhancement of Higher Education, Tokyo, Japan","institution_ids":["https://openalex.org/I4210100966"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.198,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.35677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":74,"max":77},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9996,"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":0.9996,"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":0.9932,"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/T14011","display_name":"Elevator Systems and Control","score":0.9853,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8457496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.70467424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5525673},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.538495},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35443854},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34418356},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851690","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1557517019","https://openalex.org/W1600437712","https://openalex.org/W1995663008","https://openalex.org/W2091565802","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2290354866","https://openalex.org/W2746553466","https://openalex.org/W2755611982","https://openalex.org/W2761873684","https://openalex.org/W2909521941","https://openalex.org/W2950471160","https://openalex.org/W2951799221","https://openalex.org/W2963423916","https://openalex.org/W2963477884","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W3103780890","https://openalex.org/W32403112","https://openalex.org/W4214717370","https://openalex.org/W4298876402"],"related_works":["https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4306674287","https://openalex.org/W4283697347","https://openalex.org/W4210805261","https://openalex.org/W3170094116","https://openalex.org/W3107602296","https://openalex.org/W3046775127","https://openalex.org/W2961085424"],"abstract_inverted_index":{"Recently,":[0],"deep":[1],"reinforcement":[2],"learning":[3,20,46],"using":[4,25,51],"the":[5,31,40,52,56,91,120,132,135,155,159,171,179,182,187,191,197],"Deep":[6],"Q-networks":[7],"(DQN)":[8],"algorithm":[9,144],"has":[10],"attracted":[11],"attention,":[12],"and":[13,95,164,213,216],"extended":[14,32],"methods":[15,64],"continue":[16],"to":[17,35,60,90,107,127,131,154,175,200],"improve":[18],"its":[19,218],"performance.":[21],"A":[22,74],"multi-step":[23,214],"DQN":[24,76,80,212],"an":[26],"n-step":[27,41],"TD":[28,42],"method":[29,33,106,173,199],"in":[30,39,45,113,158,178],"contributes":[34],"faster":[36,78],"learning.":[37],"However,":[38],"methods,":[43],"improvement":[44],"speed":[47],"is":[48,174],"better":[49],"when":[50],"intermediate":[53],"prediction":[54,70,110],"over":[55],"long-term":[57,69,109],"prediction.":[58],"Therefore,":[59],"further":[61],"accelerate":[62],"learning,":[63],"that":[65,105,145],"can":[66],"use":[67,108,121],"a":[68,82,141,147,201],"effectively":[71],"are":[72,116],"required.":[73],"learning-accelerated":[75],"learns":[77],"than":[79],"through":[81],"training":[83],"neural":[84,136,183],"network":[85,184],"with":[86,129,150,211],"bootstrap":[87,97,151,166],"targets":[88,152],"up":[89,153],"next":[92,160],"positive":[93,162],"reward":[94,157,163],"1-step":[96,165],"targets.":[98,167],"It":[99],"is,":[100],"however,":[101],"not":[102],"possible":[103],"for":[104,111],"tasks":[112],"which":[114],"rewards":[115],"continuously":[117],"observed.":[118],"Furthermore,":[119],"of":[122,134,170,181],"two":[123],"independent":[124],"updates":[125],"leads":[126],"instability":[128,177],"respect":[130],"convergence":[133,180],"network.":[137],"We":[138,195],"therefore":[139],"propose":[140],"dual":[142,188],"targeting":[143],"uses":[146],"single":[148],"update":[149],"last":[156],"consecutive":[161],"The":[168],"aim":[169],"proposed":[172,198],"reduce":[176],"by":[185],"calculating":[186],"target":[189],"from":[190],"same":[192],"sampled":[193],"experience.":[194],"apply":[196],"few":[202],"classic":[203],"control":[204],"problems":[205],"involving":[206],"OpenAI":[207],"Gym,":[208],"compare":[209],"it":[210],"DQN,":[215],"verify":[217],"effectiveness.":[219]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2978041660","counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-01-18T00:04:05.476485","created_date":"2019-10-10"}