{"id":"https://openalex.org/W4312614522","doi":"https://doi.org/10.1109/tai.2022.3225251","title":"Offline\u2013Online Actor\u2013Critic","display_name":"Offline\u2013Online Actor\u2013Critic","publication_year":2022,"publication_date":"2022-11-28","ids":{"openalex":"https://openalex.org/W4312614522","doi":"https://doi.org/10.1109/tai.2022.3225251"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2022.3225251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2022.3225251","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","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/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 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 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/A5078775234","display_name":"Diyuan Hou","orcid":"https://orcid.org/0009-0002-9427-1532"},"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":"Diyuan Hou","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education and School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-9427-1532","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education and 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/A5085372626","display_name":"Longyang Huang","orcid":"https://orcid.org/0000-0001-5123-5043"},"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":"Longyang Huang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education and School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-5043","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education and 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 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 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":0.2624,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62411405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"5","issue":"1","first_page":"61","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9922999739646912,"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":0.9922999739646912,"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/T11197","display_name":"Digital Games and Media","score":0.9782000184059143,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9775000214576721,"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":0.4626603424549103},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.3244360387325287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4626603424549103},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.3244360387325287}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2022.3225251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2022.3225251","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6499999761581421}],"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/G6792490895","display_name":null,"funder_award_id":"61976215","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":34,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2963561234","https://openalex.org/W2991355586","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3048493514","https://openalex.org/W3127561923","https://openalex.org/W3128395826","https://openalex.org/W3184846191","https://openalex.org/W3194724567","https://openalex.org/W3200856852","https://openalex.org/W4287756699","https://openalex.org/W6638018090","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6771270455","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6779656125","https://openalex.org/W6779963924","https://openalex.org/W6796589144","https://openalex.org/W6797702751","https://openalex.org/W6802251749","https://openalex.org/W6803572779"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W4395014643","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"Offline\u2013online":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"can":[4],"effectively":[5],"address":[6,93],"the":[7,22,27,49,88,94,107,110,120],"problem":[8],"of":[9,24,29,51,109],"missing":[10],"data":[11],"(commonly":[12],"known":[13],"as":[14],"transition)":[15],"in":[16,58,62,97,103],"offline":[17,38,98],"RL.":[18,60],"However,":[19],"due":[20],"to":[21,39,64,92],"effect":[23],"distribution":[25,52,95],"shift,":[26],"performance":[28,56,122],"policy":[30,55,89,121],"may":[31],"degrade":[32],"when":[33],"an":[34],"agent":[35],"moves":[36],"from":[37],"online":[40,104],"training":[41,99,105],"phases.":[42],"In":[43,78,101],"this":[44],"article,":[45],"we":[46,68],"first":[47],"analyze":[48],"problems":[50],"shift":[53,96],"and":[54],"degradation":[57],"offline\u2013online":[59,74,130],"Then,":[61],"order":[63],"alleviate":[65],"these":[66],"problems,":[67],"propose":[69],"a":[70,80],"novel":[71],"RL":[72,131],"algorithm":[73],"actor\u2013critic":[75],"(O2AC)":[76],"algorithm.":[77],"O2AC,":[79],"behavior":[81,111],"clone":[82,112],"constraint":[83,113],"term":[84,114],"is":[85,115],"introduced":[86],"into":[87],"objective":[90],"function":[91],"phase.":[100],"addition,":[102],"phase,":[106],"influence":[108],"gradually":[116],"reduced,":[117],"which":[118],"alleviates":[119],"degradation.":[123],"Experiments":[124],"show":[125],"that":[126],"O2AC":[127],"outperforms":[128],"existing":[129],"algorithms.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}