{"id":"https://openalex.org/W4388816578","doi":"https://doi.org/10.1016/j.artint.2023.104048","title":"Pessimistic value iteration for multi-task data sharing in Offline Reinforcement Learning","display_name":"Pessimistic value iteration for multi-task data sharing in Offline Reinforcement Learning","publication_year":2023,"publication_date":"2023-11-20","ids":{"openalex":"https://openalex.org/W4388816578","doi":"https://doi.org/10.1016/j.artint.2023.104048"},"language":"en","primary_location":{"id":"doi:10.1016/j.artint.2023.104048","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.artint.2023.104048","pdf_url":null,"source":{"id":"https://openalex.org/S196139623","display_name":"Artificial Intelligence","issn_l":"0004-3702","issn":["0004-3702","1872-7921"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.19346","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044788927","display_name":"Chenjia Bai","orcid":"https://orcid.org/0000-0002-8379-9385"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenjia Bai","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China","Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8379-9385","affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779971","display_name":"Lingxiao Wang","orcid":"https://orcid.org/0000-0002-1654-4681"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingxiao Wang","raw_affiliation_strings":["Department of Industrial Engineering and Management Sciences, Northwestern University, Evanston, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Management Sciences, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727948","display_name":"Zhuoran Yang","orcid":"https://orcid.org/0000-0001-5269-9958"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoran Yang","raw_affiliation_strings":["Department of Statistics and Data Science, Yale University, New Haven, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science, Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101496244","display_name":"Bin Zhao","orcid":"https://orcid.org/0000-0002-0294-8538"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhao","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China","Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422377","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0002-8182-2852"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106943753","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0003-2924-946X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China","Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100422377","https://openalex.org/A5106943753"],"corresponding_institution_ids":["https://openalex.org/I17145004","https://openalex.org/I4210100255","https://openalex.org/I4391012619"],"apc_list":{"value":3670,"currency":"USD","value_usd":3670},"apc_paid":null,"fwci":1.1769,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83372454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"326","issue":null,"first_page":"104048","last_page":"104048"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9846000075340271,"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":0.8305981159210205},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6521419286727905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6419225335121155},{"id":"https://openalex.org/keywords/pessimism","display_name":"Pessimism","score":0.5303953886032104},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44786494970321655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44506147503852844},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4395676255226135},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3110770583152771},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10097363591194153},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05956891179084778}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8305981159210205},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6521419286727905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6419225335121155},{"id":"https://openalex.org/C9992130","wikidata":"https://www.wikidata.org/wiki/Q484954","display_name":"Pessimism","level":2,"score":0.5303953886032104},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44786494970321655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44506147503852844},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4395676255226135},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3110770583152771},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10097363591194153},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05956891179084778},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.artint.2023.104048","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.artint.2023.104048","pdf_url":null,"source":{"id":"https://openalex.org/S196139623","display_name":"Artificial Intelligence","issn_l":"0004-3702","issn":["0004-3702","1872-7921"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2404.19346","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.19346","pdf_url":"https://arxiv.org/pdf/2404.19346","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:2404.19346","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.19346","pdf_url":"https://arxiv.org/pdf/2404.19346","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":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G224305718","display_name":null,"funder_award_id":"2022ZD0160100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7108700631","display_name":null,"funder_award_id":"62306242","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"},{"id":"https://openalex.org/F4320334953","display_name":"China National Funds for Distinguished Young Scientists","ror":"https://ror.org/01pab2602"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4388816578.pdf"},"referenced_works_count":88,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2145339207","https://openalex.org/W2525579820","https://openalex.org/W2552194003","https://openalex.org/W2559655401","https://openalex.org/W2604272474","https://openalex.org/W2755611049","https://openalex.org/W2760506156","https://openalex.org/W2807588596","https://openalex.org/W2902907165","https://openalex.org/W2948194985","https://openalex.org/W2963946945","https://openalex.org/W2982316857","https://openalex.org/W3007848632","https://openalex.org/W3008970887","https://openalex.org/W3020125231","https://openalex.org/W3035060554","https://openalex.org/W3037440645","https://openalex.org/W3175206595","https://openalex.org/W3178225342","https://openalex.org/W3206005330","https://openalex.org/W3212887262","https://openalex.org/W4212774754","https://openalex.org/W4253749043","https://openalex.org/W4281794919","https://openalex.org/W4287865629","https://openalex.org/W4288319859","https://openalex.org/W4298206671","https://openalex.org/W4308364487","https://openalex.org/W4361229151","https://openalex.org/W6607789263","https://openalex.org/W6617145748","https://openalex.org/W6639039794","https://openalex.org/W6678092311","https://openalex.org/W6695011786","https://openalex.org/W6736209634","https://openalex.org/W6748073499","https://openalex.org/W6748839928","https://openalex.org/W6750106230","https://openalex.org/W6751494529","https://openalex.org/W6752244597","https://openalex.org/W6757469721","https://openalex.org/W6757560991","https://openalex.org/W6762639926","https://openalex.org/W6763087592","https://openalex.org/W6763704811","https://openalex.org/W6764053384","https://openalex.org/W6765804866","https://openalex.org/W6769022465","https://openalex.org/W6773555910","https://openalex.org/W6774321585","https://openalex.org/W6774784542","https://openalex.org/W6774967489","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6778000925","https://openalex.org/W6779265984","https://openalex.org/W6779326418","https://openalex.org/W6779596781","https://openalex.org/W6779758137","https://openalex.org/W6779963924","https://openalex.org/W6780159193","https://openalex.org/W6780964083","https://openalex.org/W6782022165","https://openalex.org/W6782858274","https://openalex.org/W6785193213","https://openalex.org/W6785559887","https://openalex.org/W6787043984","https://openalex.org/W6791413555","https://openalex.org/W6792049622","https://openalex.org/W6793985147","https://openalex.org/W6795014841","https://openalex.org/W6795425552","https://openalex.org/W6796070028","https://openalex.org/W6796289742","https://openalex.org/W6796429164","https://openalex.org/W6796589144","https://openalex.org/W6797702751","https://openalex.org/W6797881406","https://openalex.org/W6800570120","https://openalex.org/W6801798027","https://openalex.org/W6801801719","https://openalex.org/W6802648193","https://openalex.org/W6810030924","https://openalex.org/W6810764721","https://openalex.org/W6810828452","https://openalex.org/W6838240175","https://openalex.org/W6841141121"],"related_works":["https://openalex.org/W4380987628","https://openalex.org/W2418537576","https://openalex.org/W2557514562","https://openalex.org/W214945085","https://openalex.org/W1987935396","https://openalex.org/W3126025002","https://openalex.org/W2354456418","https://openalex.org/W3197683035","https://openalex.org/W2006807542","https://openalex.org/W2374935031"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
