{"id":"https://openalex.org/W4404810339","doi":"https://doi.org/10.1109/tnnls.2024.3497667","title":"ACL-QL: Adaptive Conservative Level in <i>Q</i>-Learning for Offline Reinforcement Learning","display_name":"ACL-QL: Adaptive Conservative Level in <i>Q</i>-Learning for Offline Reinforcement Learning","publication_year":2024,"publication_date":"2024-11-28","ids":{"openalex":"https://openalex.org/W4404810339","doi":"https://doi.org/10.1109/tnnls.2024.3497667","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030344"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3497667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3497667","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.16848","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116592777","display_name":"Kun Wu","orcid":"https://orcid.org/0000-0003-2095-2140"},"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"]},{"id":"https://openalex.org/I4210091156","display_name":"SAIC-GM (China)","ror":"https://ror.org/00h64t852","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091156"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Kun Wu","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USA","Shanghai201700, China","with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","Beijing Institute of Technology, Beijing 100811, China","Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USA","institution_ids":["https://openalex.org/I70983195"]},{"raw_affiliation_string":"Shanghai201700, China","institution_ids":["https://openalex.org/I4210091156"]},{"raw_affiliation_string":"with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Beijing Institute of Technology, Beijing 100811, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067665057","display_name":"Yinuo Zhao","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"]},{"id":"https://openalex.org/I4210091156","display_name":"SAIC-GM (China)","ror":"https://ror.org/00h64t852","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091156"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yinuo Zhao","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China","Beijing Institute of Technology, Beijing 100811, China","with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","Shanghai201700, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Beijing Institute of Technology, Beijing 100811, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","institution_ids":["https://openalex.org/I70983195"]},{"raw_affiliation_string":"Shanghai201700, China","institution_ids":["https://openalex.org/I4210091156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047324704","display_name":"Zhiyuan Xu","orcid":"https://orcid.org/0000-0003-2879-3244"},"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"]},{"id":"https://openalex.org/I4210091156","display_name":"SAIC-GM (China)","ror":"https://ror.org/00h64t852","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091156"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhiyuan Xu","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics, Beijing, China","Shanghai201700, China","Beijing Institute of Technology, Beijing 100811, China","with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244"],"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Shanghai201700, China","institution_ids":["https://openalex.org/I4210091156"]},{"raw_affiliation_string":"Beijing Institute of Technology, Beijing 100811, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079044416","display_name":"Zhengping Che","orcid":"https://orcid.org/0000-0001-6818-1125"},"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"]},{"id":"https://openalex.org/I4210091156","display_name":"SAIC-GM (China)","ror":"https://ror.org/00h64t852","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091156"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhengping Che","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics, Beijing, China","Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","Shanghai201700, China","with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","Beijing Institute of Technology, Beijing 100811, China"],"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","institution_ids":["https://openalex.org/I70983195"]},{"raw_affiliation_string":"Shanghai201700, China","institution_ids":["https://openalex.org/I4210091156"]},{"raw_affiliation_string":"with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Beijing Institute of Technology, Beijing 100811, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031741238","display_name":"Chengxiang Yin","orcid":"https://orcid.org/0000-0002-3238-960X"},"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"]},{"id":"https://openalex.org/I4210091156","display_name":"SAIC-GM (China)","ror":"https://ror.org/00h64t852","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091156"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Chengxiang Yin","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USA","Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","Beijing Institute of Technology, Beijing 100811, China","Shanghai201700, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USA","institution_ids":["https://openalex.org/I70983195"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","institution_ids":["https://openalex.org/I70983195"]},{"raw_affiliation_string":"with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Beijing Institute of Technology, Beijing 100811, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Shanghai201700, China","institution_ids":["https://openalex.org/I4210091156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102923184","display_name":"Chi Harold Liu","orcid":"https://orcid.org/0000-0002-0252-329X"},"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"]},{"id":"https://openalex.org/I4210091156","display_name":"SAIC-GM (China)","ror":"https://ror.org/00h64t852","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091156"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Chi Harold Liu","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China","Shanghai201700, China","with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","Beijing Institute of Technology, Beijing 100811, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Shanghai201700, China","institution_ids":["https://openalex.org/I4210091156"]},{"raw_affiliation_string":"with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","institution_ids":["https://openalex.org/I70983195"]},{"raw_affiliation_string":"Beijing Institute of Technology, Beijing 100811, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101945772","display_name":"Feifei Feng","orcid":"https://orcid.org/0009-0003-8612-5022"},"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"]},{"id":"https://openalex.org/I4210091156","display_name":"SAIC-GM (China)","ror":"https://ror.org/00h64t852","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091156"]},{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Feifei Feng","raw_affiliation_strings":["Midea Group, Shanghai, China","Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","Beijing Institute of Technology, Beijing 100811, China","Shanghai201700, China","with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China"],"affiliations":[{"raw_affiliation_string":"Midea Group, Shanghai, China","institution_ids":["https://openalex.org/I4210093653"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","institution_ids":["https://openalex.org/I70983195"]},{"raw_affiliation_string":"Beijing Institute of Technology, Beijing 100811, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Shanghai201700, China","institution_ids":["https://openalex.org/I4210091156"]},{"raw_affiliation_string":"with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108985652","display_name":"Jian Tang","orcid":"https://orcid.org/0009-0007-9524-3986"},"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"]},{"id":"https://openalex.org/I4210091156","display_name":"SAIC-GM (China)","ror":"https://ror.org/00h64t852","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091156"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jian Tang","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics, Beijing, China","Beijing Institute of Technology, Beijing 100811, China","with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","Shanghai201700, China"],"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Beijing Institute of Technology, Beijing 100811, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"with Beijing Innovation Center of Humanoid Robotics, Beijing 101111, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244","institution_ids":["https://openalex.org/I70983195"]},{"raw_affiliation_string":"Shanghai201700, China","institution_ids":["https://openalex.org/I4210091156"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5116592777"],"corresponding_institution_ids":["https://openalex.org/I125839683","https://openalex.org/I4210091156","https://openalex.org/I4210165198","https://openalex.org/I70983195"],"apc_list":null,"apc_paid":null,"fwci":1.3627,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84936475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"36","issue":"6","first_page":"11399","last_page":"11413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9943000078201294,"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":0.9894999861717224,"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":0.783136785030365},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.654712975025177},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5907058715820312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4549205005168915},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34307795763015747},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2805333733558655},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07788917422294617}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.783136785030365},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.654712975025177},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5907058715820312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4549205005168915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34307795763015747},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2805333733558655},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07788917422294617}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2024.3497667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3497667","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40030344","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030344","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:arXiv.org:2412.16848","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.16848","pdf_url":"https://arxiv.org/pdf/2412.16848","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.16848","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.16848","pdf_url":"https://arxiv.org/pdf/2412.16848","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8472827588","display_name":null,"funder_award_id":"and O","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404810339.pdf"},"referenced_works_count":130,"referenced_works":["https://openalex.org/W51508254","https://openalex.org/W192920577","https://openalex.org/W1547925194","https://openalex.org/W2087617385","https://openalex.org/W2126316555","https://openalex.org/W2132908009","https://openalex.org/W2158782408","https://openalex.org/W2158796564","https://openalex.org/W2167224731","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2280163991","https://openalex.org/W2529970964","https://openalex.org/W2747402019","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2792643794","https://openalex.org/W2793798239","https://openalex.org/W2802164917","https://openalex.org/W2890192685","https://openalex.org/W2902332709","https://openalex.org/W2904453761","https://openalex.org/W2924131335","https://openalex.org/W2947150733","https://openalex.org/W2953981431","https://openalex.org/W2962821147","https://openalex.org/W2963296584","https://openalex.org/W2963411833","https://openalex.org/W2963761387","https://openalex.org/W2964015378","https://openalex.org/W2972435663","https://openalex.org/W2978455699","https://openalex.org/W2981030070","https://openalex.org/W2982041329","https://openalex.org/W2991355586","https://openalex.org/W2993185773","https://openalex.org/W2995706821","https://openalex.org/W3009584650","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3025606523","https://openalex.org/W3028766998","https://openalex.org/W3028830971","https://openalex.org/W3033324992","https://openalex.org/W3034084488","https://openalex.org/W3037134744","https://openalex.org/W3037440645","https://openalex.org/W3117215073","https://openalex.org/W3166795773","https://openalex.org/W3169291081","https://openalex.org/W3172360140","https://openalex.org/W3198999478","https://openalex.org/W3200377072","https://openalex.org/W3201700917","https://openalex.org/W3205794883","https://openalex.org/W3207654079","https://openalex.org/W3211583675","https://openalex.org/W3212887262","https://openalex.org/W3212948944","https://openalex.org/W4214717370","https://openalex.org/W4225712251","https://openalex.org/W4225937744","https://openalex.org/W4286965539","https://openalex.org/W4287080123","https://openalex.org/W4287118283","https://openalex.org/W4287126489","https://openalex.org/W4287724235","https://openalex.org/W4287756699","https://openalex.org/W4288319859","https://openalex.org/W4288560585","https://openalex.org/W4298857966","https://openalex.org/W4308364487","https://openalex.org/W4318619777","https://openalex.org/W4360584316","https://openalex.org/W4385245566","https://openalex.org/W4386524114","https://openalex.org/W4388469888","https://openalex.org/W4394666657","https://openalex.org/W6602057636","https://openalex.org/W6632901617","https://openalex.org/W6637967152","https://openalex.org/W6679661297","https://openalex.org/W6682968728","https://openalex.org/W6684338915","https://openalex.org/W6687681856","https://openalex.org/W6695011786","https://openalex.org/W6726873649","https://openalex.org/W6742945991","https://openalex.org/W6747473740","https://openalex.org/W6748554570","https://openalex.org/W6748839928","https://openalex.org/W6749029207","https://openalex.org/W6754479021","https://openalex.org/W6756287877","https://openalex.org/W6757469721","https://openalex.org/W6760724441","https://openalex.org/W6760755450","https://openalex.org/W6763704811","https://openalex.org/W6764053384","https://openalex.org/W6764976746","https://openalex.org/W6769035977","https://openalex.org/W6769342953","https://openalex.org/W6771270455","https://openalex.org/W6771428195","https://openalex.org/W6771886500","https://openalex.org/W6774583691","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/W6780135261","https://openalex.org/W6780159193","https://openalex.org/W6780559895","https://openalex.org/W6785559887","https://openalex.org/W6791413555","https://openalex.org/W6792049622","https://openalex.org/W6796289742","https://openalex.org/W6796589144","https://openalex.org/W6796926305","https://openalex.org/W6801009634","https://openalex.org/W6801798027","https://openalex.org/W6802659552","https://openalex.org/W6804160314","https://openalex.org/W6804244202","https://openalex.org/W6840739175","https://openalex.org/W6849658737","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2952356279"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1,223],"learning":[2,21,224],"(RL),":[3],"which":[4,105,144,177],"operates":[5],"solely":[6],"on":[7,117,215],"static":[8],"datasets":[9,219],"without":[10],"further":[11],"interactions":[12],"with":[13,62,240],"the":[14,38,66,87,107,118,127,141,145,149,168,186,203,216,234],"environment,":[15],"provides":[16],"an":[17,52],"appealing":[18],"alternative":[19],"to":[20,36,47,51,69,161,184,201,232],"a":[22,33,74,82,92,97,110,156,173,195],"safe":[23],"and":[24,113,133,159,198,208,227,236],"promising":[25],"control":[26,70,116,185],"policy.":[27,55],"The":[28],"prevailing":[29],"methods":[30],"typically":[31],"learn":[32],"conservative":[34,54,71,100,119,146,187],"policy":[35,209],"mitigate":[37],"problem":[39],"of":[40,148],"Q-value":[41],"overestimation,":[42],"but":[43],"it":[44],"is":[45],"prone":[46],"overdo":[48],"it,":[49],"leading":[50],"overly":[53],"Moreover,":[56],"they":[57],"optimize":[58,162],"all":[59],"samples":[60],"equally":[61],"fixed":[63],"constraints,":[64],"lacking":[65],"nuanced":[67],"ability":[68],"levels":[72],"in":[73,81,91,102,109,155],"fine-grained":[75],"manner.":[76],"Consequently,":[77],"this":[78],"limitation":[79],"results":[80],"performance":[83,238],"decline.":[84],"To":[85],"address":[86],"above":[88],"two":[89,179],"challenges":[90],"united":[93],"way,":[94],"we":[95,171,193],"propose":[96,172],"framework,":[98],"adaptive":[99,115,181,204],"level":[101,120,147,188],"Q-learning":[103],"(ACL-QL),":[104],"limits":[106],"Q-values":[108,128],"mild":[111,157],"range":[112,158],"enables":[114],"over":[121,189],"each":[122,163,190],"state-action":[123],"pair,":[124],"i.e.,":[125],"lifting":[126],"more":[129],"for":[130,135,220],"good":[131],"transitions":[132],"less":[134],"bad":[136],"transitions.":[137],"We":[138,212],"theoretically":[139],"analyze":[140],"conditions":[142],"under":[143],"learned":[150],"Q-function":[151],"can":[152],"be":[153],"limited":[154],"how":[160],"transition":[164],"adaptively.":[165],"Motivated":[166],"by":[167],"theoretical":[169],"analysis,":[170],"novel":[174],"algorithm,":[175],"ACL-QL,":[176],"uses":[178],"learnable":[180],"weight":[182,205],"functions":[183],"transition.":[191],"Subsequently,":[192],"design":[194],"monotonicity":[196],"loss":[197],"surrogate":[199],"losses":[200],"train":[202],"functions,":[206],"Q-function,":[207],"network":[210],"alternatively.":[211],"evaluate":[213],"ACL-QL":[214],"commonly":[217],"used":[218],"deep":[221],"data-driven":[222],"(D4RL)":[225],"benchmark":[226],"conduct":[228],"extensive":[229],"ablation":[230],"studies":[231],"illustrate":[233],"effectiveness":[235],"state-of-the-art":[237],"compared":[239],"existing":[241],"offline":[242],"DRL":[243],"baselines.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}