{"id":"https://openalex.org/W2950211955","doi":"https://doi.org/10.1109/access.2019.2922706","title":"Stochastic Double Deep Q-Network","display_name":"Stochastic Double Deep Q-Network","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2950211955","doi":"https://doi.org/10.1109/access.2019.2922706","mag":"2950211955"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2922706","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2922706","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08736298.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08736298.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038888043","display_name":"Pingli Lv","orcid":null},"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":"Pingli Lv","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/A5009645879","display_name":"Ziming Duan","orcid":null},"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":"Ziming Duan","raw_affiliation_strings":["School of Mathematics, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.7407,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.88022445,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"7","issue":null,"first_page":"79446","last_page":"79454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9972000122070312,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9951000213623047,"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/estimator","display_name":"Estimator","score":0.8147972822189331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7052595615386963},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5879955291748047},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.47524094581604004},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4271320700645447},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.421917200088501},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.41990578174591064},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4194566011428833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.333227276802063},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24149933457374573},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23423981666564941},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.10654416680335999}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.8147972822189331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7052595615386963},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5879955291748047},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.47524094581604004},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4271320700645447},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.421917200088501},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.41990578174591064},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4194566011428833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.333227276802063},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24149933457374573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23423981666564941},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.10654416680335999},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2922706","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2922706","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08736298.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:913e8e57aeaf4ff4b13066c47cd43dc2","is_oa":true,"landing_page_url":"https://doaj.org/article/913e8e57aeaf4ff4b13066c47cd43dc2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 79446-79454 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2922706","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2922706","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08736298.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7031480287","display_name":"\u57fa\u4e8e\u5c5e\u6027\u5b66\u4e60\u7684\u96f6\u6837\u672c\u56fe\u50cf\u5206\u7c7b\u7814\u7a76","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950211955.pdf","grobid_xml":"https://content.openalex.org/works/W2950211955.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1613249581","https://openalex.org/W1952243512","https://openalex.org/W2121092017","https://openalex.org/W2121615981","https://openalex.org/W2143612262","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2168405694","https://openalex.org/W2179488730","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2345097924","https://openalex.org/W2469051754","https://openalex.org/W2548277951","https://openalex.org/W2574978968","https://openalex.org/W2746553466","https://openalex.org/W2766447205","https://openalex.org/W2767696060","https://openalex.org/W2771966232","https://openalex.org/W2802164917","https://openalex.org/W2802633170","https://openalex.org/W2886620426","https://openalex.org/W2893381601","https://openalex.org/W2951799221","https://openalex.org/W2953364219","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W4297669414","https://openalex.org/W4298857966","https://openalex.org/W6636456564","https://openalex.org/W6637967152","https://openalex.org/W6640955601","https://openalex.org/W6677067356","https://openalex.org/W6677939520","https://openalex.org/W6678317597","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6692055482","https://openalex.org/W6692846177","https://openalex.org/W6735506055","https://openalex.org/W6746549794","https://openalex.org/W6775686901","https://openalex.org/W6948057359","https://openalex.org/W7000276917"],"related_works":["https://openalex.org/W4287880334","https://openalex.org/W4306904969","https://openalex.org/W4366700029","https://openalex.org/W2138720691","https://openalex.org/W2949597507","https://openalex.org/W2156326090","https://openalex.org/W2150901859","https://openalex.org/W84146095","https://openalex.org/W2119298659","https://openalex.org/W2963001040"],"abstract_inverted_index":{"Estimation":[0],"bias":[1,147],"seriously":[2],"affects":[3],"the":[4,18,28,52,71,78,90,94,145],"performance":[5],"of":[6,54,60],"reinforcement":[7],"learning":[8],"algorithms.":[9],"The":[10,110,129],"maximum":[11,91],"operation":[12,21,92,97],"may":[13],"result":[14],"in":[15,37],"overestimation,":[16],"while":[17],"double":[19,43,67,79,95],"estimator":[20,80,96],"often":[22],"leads":[23],"to":[24,87],"underestimation.":[25],"To":[26],"eliminate":[27],"estimation":[29,146],"bias,":[30],"these":[31],"two":[32],"operations":[33],"are":[34,75],"combined":[35],"together":[36],"our":[38,140],"proposed":[39,141],"algorithm":[40],"named":[41,65],"stochastic":[42,66],"deep":[44],"Q-learning":[45,68],"network":[46],"(SDDQN),":[47],"which":[48,102],"is":[49,62,103],"based":[50,76],"on":[51,77,131],"idea":[53],"random":[55,107,120],"selection.":[56],"A":[57],"tabular":[58],"version":[59],"SDDQN":[61,72,125],"also":[63],"given,":[64],"(SDQ).":[69],"Both":[70],"and":[73,126,134,149],"SDQ":[74,127],"framework.":[81],"At":[82],"each":[83],"step,":[84],"we":[85],"choose":[86],"use":[88],"either":[89],"or":[93],"with":[98],"a":[99,106,118],"certain":[100],"probability,":[101],"determined":[104],"by":[105],"selection":[108,121],"parameter.":[109],"theoretical":[111],"analysis":[112],"shows":[113],"that":[114,123,139],"there":[115],"indeed":[116],"exists":[117],"proper":[119],"parameter":[122],"makes":[124],"unbiased.":[128],"experiments":[130],"Grid":[132],"World":[133],"Atari":[135],"2600":[136],"games":[137],"illustrate":[138],"algorithms":[142],"can":[143],"balance":[144],"effectively":[148],"improve":[150],"performance.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}