{"id":"https://openalex.org/W4396542660","doi":"https://doi.org/10.1109/tsmc.2024.3388007","title":"Dual Behavior Regularized Offline Deterministic Actor\u2013Critic","display_name":"Dual Behavior Regularized Offline Deterministic Actor\u2013Critic","publication_year":2024,"publication_date":"2024-05-01","ids":{"openalex":"https://openalex.org/W4396542660","doi":"https://doi.org/10.1109/tsmc.2024.3388007"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2024.3388007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3388007","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: 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/A5004354148","display_name":"Shuo Cao","orcid":"https://orcid.org/0000-0003-3998-461X"},"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":"Shuo Cao","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3998-461X","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the 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":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the 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, and the 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/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, and the 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, and the School of Information and Control Engineering, 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":null,"apc_paid":null,"fwci":1.6808,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85430653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"54","issue":"8","first_page":"4841","last_page":"4852"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9577999711036682,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9545999765396118,"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/dual","display_name":"Dual (grammatical number)","score":0.5889228582382202},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5321428179740906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37101513147354126},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.17669862508773804}],"concepts":[{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5889228582382202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5321428179740906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37101513147354126},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.17669862508773804},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2024.3388007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3388007","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4756161396","display_name":null,"funder_award_id":"62176259","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4823360002","display_name":null,"funder_award_id":"62373364","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":58,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W2154291838","https://openalex.org/W2158782408","https://openalex.org/W2970999977","https://openalex.org/W2978455699","https://openalex.org/W2989958156","https://openalex.org/W2991355586","https://openalex.org/W2991391803","https://openalex.org/W3004840042","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3168236455","https://openalex.org/W3176234924","https://openalex.org/W3187550742","https://openalex.org/W3188220908","https://openalex.org/W3205794883","https://openalex.org/W4210294974","https://openalex.org/W4214717370","https://openalex.org/W4283835015","https://openalex.org/W4285600796","https://openalex.org/W4287266180","https://openalex.org/W4307230233","https://openalex.org/W4309210950","https://openalex.org/W4311897500","https://openalex.org/W4313914531","https://openalex.org/W4318823674","https://openalex.org/W4321012295","https://openalex.org/W4322759939","https://openalex.org/W4360584316","https://openalex.org/W4375929017","https://openalex.org/W4378805020","https://openalex.org/W4382318909","https://openalex.org/W4391759535","https://openalex.org/W4395680426","https://openalex.org/W6679100793","https://openalex.org/W6684205842","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6751661917","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6771270455","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6780159193","https://openalex.org/W6785559887","https://openalex.org/W6791377749","https://openalex.org/W6792049622","https://openalex.org/W6792413377","https://openalex.org/W6796589144","https://openalex.org/W6802659552","https://openalex.org/W6811051195","https://openalex.org/W6838356327","https://openalex.org/W6846529360","https://openalex.org/W6848738909","https://openalex.org/W6849435238","https://openalex.org/W6850361595"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"To":[0],"mitigate":[1],"the":[2,43,53,58,61,64,73,81,90,96,99,114,126,135,145],"extrapolation":[3],"error":[4],"arising":[5],"from":[6],"offline":[7,33,156,165],"reinforcement":[8],"learning":[9],"(RL)":[10],"paradigm,":[11],"existing":[12],"methods":[13],"typically":[14],"make":[15],"learned":[16,93,131],"Q-functions":[17],"over-conservative":[18],"or":[19],"enforce":[20],"global":[21],"policy":[22,45,49,54,105],"constraints.":[23],"In":[24,57,95],"this":[25],"article,":[26],"we":[27],"propose":[28],"a":[29],"dual":[30],"behavior":[31,40,67,75,104,120],"regularized":[32],"deterministic":[34],"Actor-Critic":[35],"(DBRAC)":[36],"by":[37],"simultaneously":[38],"performing":[39],"regularization":[41,77,122],"on":[42,134],"coupling-iterative":[44],"evaluation":[46],"(PE)":[47],"and":[48,66,116],"improvement":[50,128],"(PI)":[51],"in":[52,106,154],"iteration":[55],"process.":[56],"PE":[59],"phase,":[60,98],"difference":[62],"between":[63],"Q-function":[65,82],"value":[68,76],"is":[69],"first":[70],"taken":[71],"as":[72],"anti-exploration":[74],"term":[78],"to":[79],"drive":[80],"toward":[83],"its":[84],"true":[85],"Q-value,":[86],"which":[87,124],"significantly":[88,162],"reduces":[89],"conservatism":[91],"of":[92,103,118,130],"Q-function.":[94],"PI":[97],"estimated":[100],"action":[101],"variances":[102],"different":[107,159],"states":[108],"are":[109],"then":[110],"utilized":[111],"for":[112,138],"designing":[113],"weight":[115],"threshold":[117],"mild-local":[119],"cloning":[121],"term,":[123],"standardizes":[125],"local":[127],"potential":[129],"policy.":[132],"Experiments":[133],"well-known":[136],"datasets":[137],"deep":[139],"data-driven":[140],"RL":[141,166],"(D4RL)":[142],"demonstrate":[143],"that":[144],"DBRAC":[146],"can":[147],"quickly":[148],"learn":[149],"more":[150],"competitive":[151],"task-solving":[152],"policies":[153],"various":[155],"situations":[157],"with":[158],"data":[160],"qualities,":[161],"outperforming":[163],"state-of-the-art":[164],"baselines.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}