{"id":"https://openalex.org/W7124528574","doi":"https://doi.org/10.1007/s13042-025-02963-9","title":"An offline actor-critic policy improvement algorithm with historical state-action pairs","display_name":"An offline actor-critic policy improvement algorithm with historical state-action pairs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124528574","doi":"https://doi.org/10.1007/s13042-025-02963-9"},"language":"en","primary_location":{"id":"doi:10.1007/s13042-025-02963-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13042-025-02963-9","pdf_url":null,"source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Machine Learning and Cybernetics","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/A5101688281","display_name":"Huaqing Zhang","orcid":"https://orcid.org/0000-0001-8791-1672"},"institutions":[{"id":"https://openalex.org/I4210110997","display_name":"Ministry of Education","ror":"https://ror.org/01xexqx38","country_code":"ME","type":"government","lineage":["https://openalex.org/I4210110997"]}],"countries":["ME"],"is_corresponding":true,"raw_author_name":"Huaqing Zhang","raw_affiliation_strings":["National Key Laboratory of Complex System Control and Intelligent Agent Cooperation, Beijing, 100074, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Complex System Control and Intelligent Agent Cooperation, Beijing, 100074, China","institution_ids":["https://openalex.org/I4210110997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447059","display_name":"Xiaofei Zhang","orcid":"https://orcid.org/0000-0003-4796-1688"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Zhang","raw_affiliation_strings":["Beijing Institute of Computer Technology and Applications, Beijing, 100854, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Computer Technology and Applications, Beijing, 100854, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102620212","display_name":"Jixiang Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110997","display_name":"Ministry of Education","ror":"https://ror.org/01xexqx38","country_code":"ME","type":"government","lineage":["https://openalex.org/I4210110997"]}],"countries":["ME"],"is_corresponding":false,"raw_author_name":"Jixiang Jiang","raw_affiliation_strings":["National Key Laboratory of Complex System Control and Intelligent Agent Cooperation, Beijing, 100074, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Complex System Control and Intelligent Agent Cooperation, Beijing, 100074, China","institution_ids":["https://openalex.org/I4210110997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123272340","display_name":"Mingrui Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110997","display_name":"Ministry of Education","ror":"https://ror.org/01xexqx38","country_code":"ME","type":"government","lineage":["https://openalex.org/I4210110997"]}],"countries":["ME"],"is_corresponding":false,"raw_author_name":"Mingrui Hao","raw_affiliation_strings":["National Key Laboratory of Complex System Control and Intelligent Agent Cooperation, Beijing, 100074, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Complex System Control and Intelligent Agent Cooperation, Beijing, 100074, China","institution_ids":["https://openalex.org/I4210110997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123277958","display_name":"Hongbin Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbin Ma","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, 100081, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123264122","display_name":"Ning Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Zhang","raw_affiliation_strings":["Beijing Institute of Computer Technology and Applications, Beijing, 100854, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Computer Technology and Applications, Beijing, 100854, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101688281"],"corresponding_institution_ids":["https://openalex.org/I4210110997"],"apc_list":{"value":2790,"currency":"EUR","value_usd":3590},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07145546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.638700008392334,"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":0.638700008392334,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.06920000165700912,"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":0.03240000084042549,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8240000009536743},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.6642000079154968},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5812000036239624},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.5295000076293945},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.5087000131607056},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.4480000138282776},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.42989999055862427}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8240000009536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893999814987183},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5812000036239624},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.5295000076293945},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.5087000131607056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5052000284194946},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4754999876022339},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4481000006198883},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4401000142097473},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.42989999055862427},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s13042-025-02963-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13042-025-02963-9","pdf_url":null,"source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Machine Learning and Cybernetics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7205694317817688,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2646844173","display_name":null,"funder_award_id":"62076028","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2036945521","https://openalex.org/W3014101816","https://openalex.org/W3100789280","https://openalex.org/W3123538634","https://openalex.org/W3178225342","https://openalex.org/W4226257065","https://openalex.org/W4241811150","https://openalex.org/W4292338032","https://openalex.org/W4297792190","https://openalex.org/W4306958143","https://openalex.org/W4308080451","https://openalex.org/W4323363125","https://openalex.org/W4360584316","https://openalex.org/W4376868870","https://openalex.org/W4382202881","https://openalex.org/W4384937907","https://openalex.org/W4385764347","https://openalex.org/W4393164544","https://openalex.org/W4415796419"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-01-19T04:05:37.678316","created_date":"2026-01-19T00:00:00"}