{"id":"https://openalex.org/W3097268408","doi":"https://doi.org/10.1109/tcds.2020.3034452","title":"Off-Policy Deep Reinforcement Learning Based on Steffensen Value Iteration","display_name":"Off-Policy Deep Reinforcement Learning Based on Steffensen Value Iteration","publication_year":2020,"publication_date":"2020-10-28","ids":{"openalex":"https://openalex.org/W3097268408","doi":"https://doi.org/10.1109/tcds.2020.3034452","mag":"3097268408"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2020.3034452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2020.3034452","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental 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/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":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou Key Laboratory of Artificial Intelligence and Big Data, Xuzhou, China","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":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou Key Laboratory of Artificial Intelligence and Big Data, Xuzhou, China","institution_ids":[]},{"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/A5100746873","display_name":"Lin Chen","orcid":"https://orcid.org/0009-0002-0639-2191"},"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":"Lin Chen","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou Key Laboratory of Artificial Intelligence and Big Data, Xuzhou, China","School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou Key Laboratory of Artificial Intelligence and Big Data, Xuzhou, China","institution_ids":[]},{"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/A5100643265","display_name":"C. L. Philip Chen","orcid":"https://orcid.org/0000-0001-5451-7230"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"C. L. Philip Chen","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0001-5451-7230","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","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":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou Key Laboratory of Artificial Intelligence and Big Data, Xuzhou, China","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":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou Key Laboratory of Artificial Intelligence and Big Data, Xuzhou, China","institution_ids":[]},{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1734,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.83934803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"13","issue":"4","first_page":"1023","last_page":"1032"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9656000137329102,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8713860511779785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7567148208618164},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.694225549697876},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.48911529779434204},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4337036609649658},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4184994101524353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4164561629295349},{"id":"https://openalex.org/keywords/fixed-point","display_name":"Fixed point","score":0.4153582453727722},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37071293592453003},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3354009985923767},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2636112570762634},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14539456367492676}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8713860511779785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7567148208618164},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.694225549697876},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.48911529779434204},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4337036609649658},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4184994101524353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4164561629295349},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.4153582453727722},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37071293592453003},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3354009985923767},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2636112570762634},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14539456367492676},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2020.3034452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2020.3034452","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5750115239","display_name":null,"funder_award_id":"U1813203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G653700208","display_name":null,"funder_award_id":"61751202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6792490895","display_name":null,"funder_award_id":"61976215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1646707810","https://openalex.org/W1771410628","https://openalex.org/W2050581641","https://openalex.org/W2068089288","https://openalex.org/W2077559824","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155968351","https://openalex.org/W2158782408","https://openalex.org/W2159662096","https://openalex.org/W2160815625","https://openalex.org/W2201581102","https://openalex.org/W2553303224","https://openalex.org/W2569132502","https://openalex.org/W2595700172","https://openalex.org/W2614497824","https://openalex.org/W2634239194","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2787938642","https://openalex.org/W2792645523","https://openalex.org/W2798705390","https://openalex.org/W2896457183","https://openalex.org/W2951799221","https://openalex.org/W2963864421","https://openalex.org/W2964268978","https://openalex.org/W2966349401","https://openalex.org/W3007000110","https://openalex.org/W3121933628","https://openalex.org/W4245296547","https://openalex.org/W4288348722","https://openalex.org/W4297797010","https://openalex.org/W4298876402","https://openalex.org/W4300799055","https://openalex.org/W6638018090","https://openalex.org/W6683300800","https://openalex.org/W6685444567","https://openalex.org/W6727862155","https://openalex.org/W6740801417","https://openalex.org/W6748638692","https://openalex.org/W6748839928","https://openalex.org/W6774087990"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2386410636","https://openalex.org/W2025663273","https://openalex.org/W3038962357","https://openalex.org/W4313679781","https://openalex.org/W3099153698"],"abstract_inverted_index":{"As":[0],"an":[1],"important":[2],"machine":[3],"learning":[4,8,41,45],"method,":[5],"deep":[6,51],"reinforcement":[7,44],"(DRL)":[9],"has":[10,18,132],"been":[11],"rapidly":[12],"developed":[13],"in":[14,22,190],"recent":[15],"years":[16],"and":[17,32,46,63,119,158,163,169,176],"achieved":[19],"breakthrough":[20],"results":[21],"many":[23],"fields,":[24],"such":[25],"as":[26],"video":[27],"games,":[28],"natural":[29],"language":[30],"processing,":[31],"robot":[33],"control.":[34],"However,":[35],"due":[36],"to":[37,75,96,116],"the":[38,47,55,66,77,93,97,105,173,195],"inherit":[39],"trial-and-error":[40],"mechanism":[42],"of":[43,50,58,69,80,101,107],"time-consuming":[48],"training":[49],"neural":[52],"network":[53],"itself,":[54],"convergence":[56,78,123],"speed":[57,79,124],"DRL":[59,103],"is":[60,113],"very":[61],"slow":[62],"consequently":[64],"limits":[65],"real":[67],"applications":[68],"DRL.":[70],"In":[71,144],"this":[72,145],"article,":[73,146],"aiming":[74],"improve":[76],"DRL,":[81],"we":[82,147],"proposed":[83,111,130,148,182],"a":[84,121,191],"novel":[85],"Steffensen":[86,94],"value":[87,98,127],"iteration":[88,95,100],"(SVI)":[89],"method":[90],"by":[91,153],"applying":[92],"function":[99],"off-policy":[102,141,151],"from":[104,172],"perspective":[106],"fixed-point":[108],"iteration.":[109,128],"The":[110,129],"SVI":[112,131,155],"theoretically":[114],"proved":[115],"be":[117,136],"convergent":[118],"have":[120],"faster":[122],"than":[125,194],"Bellman":[126],"versatility,":[133],"which":[134],"can":[135,185],"easily":[137],"combined":[138],"with":[139,156],"existing":[140],"RL":[142],"algorithms.":[143],"two":[149],"speedy":[150],"DRLs":[152,184],"combining":[154],"DDQN":[157],"TD3,":[159],"respectively,":[160],"namely,":[161],"SVI-DDQN":[162],"SVI-TD3.":[164],"Experiments":[165],"on":[166],"several":[167],"discrete-action":[168],"continuous-action":[170],"tasks":[171],"Atari":[174],"2600":[175],"MuJoCo":[177],"platforms":[178],"demonstrated":[179],"that":[180],"our":[181],"SVI-based":[183],"achieve":[186],"higher":[187],"average":[188],"reward":[189],"shorter":[192],"time":[193],"comparative":[196],"algorithm.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}