{"id":"https://openalex.org/W4388033982","doi":"https://doi.org/10.1109/tpami.2023.3328397","title":"False Correlation Reduction for Offline Reinforcement Learning","display_name":"False Correlation Reduction for Offline Reinforcement Learning","publication_year":2023,"publication_date":"2023-10-30","ids":{"openalex":"https://openalex.org/W4388033982","doi":"https://doi.org/10.1109/tpami.2023.3328397","pmid":"https://pubmed.ncbi.nlm.nih.gov/37903051"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3328397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3328397","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101810080","display_name":"Zhi\u2010Hong Deng","orcid":"https://orcid.org/0000-0002-6088-7534"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhihong Deng","raw_affiliation_strings":["Faculty of Engineering and Information Technology, Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6088-7534","affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025567827","display_name":"Zuyue Fu","orcid":"https://orcid.org/0009-0003-9217-543X"},"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":"Zuyue Fu","raw_affiliation_strings":["Department of Industrial Engineering and Management Sciences, Northwestern University, Evanston, IL, USA"],"raw_orcid":"https://orcid.org/0009-0003-9217-543X","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/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":"https://orcid.org/0000-0002-1654-4681","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/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/A5044788927","display_name":"Chenjia Bai","orcid":"https://orcid.org/0000-0002-8379-9385"},"institutions":[{"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":"CN","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"],"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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039076312","display_name":"Tianyi Zhou","orcid":"https://orcid.org/0000-0001-5348-0632"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Zhou","raw_affiliation_strings":["Department of Computer Science and UMIACS, University of Maryland, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-5348-0632","affiliations":[{"raw_affiliation_string":"Department of Computer Science and UMIACS, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101934111","display_name":"Zhaoran Wang","orcid":"https://orcid.org/0000-0002-6617-4842"},"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":"Zhaoran 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":"last","author":{"id":"https://openalex.org/A5057139422","display_name":"Jing Jiang","orcid":"https://orcid.org/0000-0001-5301-7779"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jing Jiang","raw_affiliation_strings":["Faculty of Engineering and Information Technology, Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5301-7779","affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3185,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84122373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"46","issue":"2","first_page":"1199","last_page":"1211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944000244140625,"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":0.9944000244140625,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9829999804496765,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.741456151008606},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.694440484046936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6335710287094116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6206734776496887},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5563470721244812},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5385561585426331},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4858267307281494},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4523055851459503},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3410276472568512},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23011118173599243}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.741456151008606},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.694440484046936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6335710287094116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6206734776496887},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5563470721244812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5385561585426331},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4858267307281494},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4523055851459503},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3410276472568512},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23011118173599243},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3328397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3328397","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37903051","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37903051","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1889629917","https://openalex.org/W2979211489","https://openalex.org/W2991355586","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W4287756699","https://openalex.org/W4312072401","https://openalex.org/W6639430172","https://openalex.org/W6684205842","https://openalex.org/W6695011786","https://openalex.org/W6730042731","https://openalex.org/W6748009081","https://openalex.org/W6748839928","https://openalex.org/W6752244597","https://openalex.org/W6754627483","https://openalex.org/W6757469721","https://openalex.org/W6757677476","https://openalex.org/W6761973403","https://openalex.org/W6763704811","https://openalex.org/W6763800524","https://openalex.org/W6764366976","https://openalex.org/W6767334564","https://openalex.org/W6768617876","https://openalex.org/W6771270455","https://openalex.org/W6771404325","https://openalex.org/W6772092215","https://openalex.org/W6774679390","https://openalex.org/W6774823833","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/W6780426602","https://openalex.org/W6780571964","https://openalex.org/W6780964083","https://openalex.org/W6781960742","https://openalex.org/W6783603189","https://openalex.org/W6787043984","https://openalex.org/W6790644358","https://openalex.org/W6791413555","https://openalex.org/W6792049622","https://openalex.org/W6795014841","https://openalex.org/W6795063903","https://openalex.org/W6796429164","https://openalex.org/W6796589144","https://openalex.org/W6800570120","https://openalex.org/W6801801719","https://openalex.org/W6810030924"],"related_works":["https://openalex.org/W90906771","https://openalex.org/W2018828772","https://openalex.org/W2529185025","https://openalex.org/W2809723425","https://openalex.org/W2052708136","https://openalex.org/W2005302727","https://openalex.org/W3082028334","https://openalex.org/W4289097813","https://openalex.org/W4321153757","https://openalex.org/W2906263995"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"harnesses":[4],"the":[5,31,70,113,116,124],"power":[6],"of":[7,99,115],"massive":[8],"datasets":[9],"for":[10,54,104],"resolving":[11],"sequential":[12],"decision":[13],"problems.":[14],"Most":[15],"existing":[16],"papers":[17],"only":[18],"discuss":[19],"defending":[20],"against":[21],"out-of-distribution":[22],"(OOD)":[23],"actions":[24],"while":[25],"we":[26,48,111],"investigate":[27],"a":[28,57,80,96,128],"broader":[29],"issue,":[30],"false":[32,106],"correlations":[33,107],"between":[34],"epistemic":[35],"uncertainty":[36,100],"and":[37,60,119],"decision-making,":[38],"an":[39,88],"essential":[40],"factor":[41],"that":[42,67],"causes":[43],"suboptimality.":[44,109],"In":[45],"this":[46],"paper,":[47],"propose":[49],"falSe":[50],"COrrelation":[51],"REduction":[52],"(SCORE)":[53],"offline":[55],"RL,":[56],"practically":[58],"effective":[59],"theoretically":[61],"provable":[62],"algorithm.":[63],"We":[64],"empirically":[65],"show":[66],"SCORE":[68],"achieves":[69],"SoTA":[71],"performance":[72],"with":[73,127],"3.1x":[74],"acceleration":[75],"on":[76],"various":[77],"tasks":[78],"in":[79],"standard":[81],"benchmark":[82],"(D4RL).":[83],"The":[84],"proposed":[85,117],"algorithm":[86],"introduces":[87],"annealing":[89],"behavior":[90],"cloning":[91],"regularizer":[92],"to":[93,123],"help":[94],"produce":[95],"high-quality":[97],"estimation":[98],"which":[101],"is":[102],"critical":[103],"eliminating":[105],"from":[108],"Theoretically,":[110],"justify":[112],"rationality":[114],"method":[118],"prove":[120],"its":[121],"convergence":[122],"optimal":[125],"policy":[126],"sublinear":[129],"rate":[130],"under":[131],"mild":[132],"assumptions.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
