{"id":"https://openalex.org/W4385488780","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191540","title":"Offline Reinforcement Learning with Uncertainty Critic Regularization Based on Density Estimation","display_name":"Offline Reinforcement Learning with Uncertainty Critic Regularization Based on Density Estimation","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488780","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191540"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191540","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5077931058","display_name":"Chao Li","orcid":"https://orcid.org/0000-0002-3782-7955"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chao Li","raw_affiliation_strings":["University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences,Beijing,China","University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210128818"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030271803","display_name":"Fengge Wu","orcid":"https://orcid.org/0000-0002-1958-8321"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengge Wu","raw_affiliation_strings":["University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences,Beijing,China","University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210128818"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069584904","display_name":"Junsuo Zhao","orcid":"https://orcid.org/0000-0001-8950-4157"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junsuo Zhao","raw_affiliation_strings":["University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences,Beijing,China","University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210128818"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077931058"],"corresponding_institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08513386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9900000095367432,"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":0.9879999756813049,"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/estimator","display_name":"Estimator","score":0.681799590587616},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6674163341522217},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6550806760787964},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5935918092727661},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5233240127563477},{"id":"https://openalex.org/keywords/valuation","display_name":"Valuation (finance)","score":0.48904165625572205},{"id":"https://openalex.org/keywords/penalty-method","display_name":"Penalty method","score":0.4790871739387512},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46945708990097046},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4229889512062073},{"id":"https://openalex.org/keywords/probability-density-function","display_name":"Probability density function","score":0.41427183151245117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4077778160572052},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36997950077056885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21061262488365173},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1949654221534729}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.681799590587616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6674163341522217},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6550806760787964},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5935918092727661},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5233240127563477},{"id":"https://openalex.org/C186027771","wikidata":"https://www.wikidata.org/wiki/Q4008379","display_name":"Valuation (finance)","level":2,"score":0.48904165625572205},{"id":"https://openalex.org/C6180225","wikidata":"https://www.wikidata.org/wiki/Q3411771","display_name":"Penalty method","level":2,"score":0.4790871739387512},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46945708990097046},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4229889512062073},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.41427183151245117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4077778160572052},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36997950077056885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21061262488365173},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1949654221534729},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191540","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W2201581102","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2904453761","https://openalex.org/W2919013397","https://openalex.org/W2947150733","https://openalex.org/W2978455699","https://openalex.org/W2991355586","https://openalex.org/W3009584650","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3025019304","https://openalex.org/W3025606523","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3127561923","https://openalex.org/W3152878473","https://openalex.org/W3166795773","https://openalex.org/W3170059879","https://openalex.org/W3172115140","https://openalex.org/W3172360140","https://openalex.org/W3201700917","https://openalex.org/W3203827806","https://openalex.org/W3205794883","https://openalex.org/W3208796191","https://openalex.org/W4221158443","https://openalex.org/W4225495521","https://openalex.org/W4225619808","https://openalex.org/W4287118283","https://openalex.org/W4287756699","https://openalex.org/W4298857966","https://openalex.org/W4360584316","https://openalex.org/W6637967152","https://openalex.org/W6639732818","https://openalex.org/W6640963894","https://openalex.org/W6687681856","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6757469721","https://openalex.org/W6759896672","https://openalex.org/W6763704811","https://openalex.org/W6771270455","https://openalex.org/W6773319185","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/W6780571964","https://openalex.org/W6791413555","https://openalex.org/W6792049622","https://openalex.org/W6795014841","https://openalex.org/W6796589144","https://openalex.org/W6796926305","https://openalex.org/W6797702751","https://openalex.org/W6801801719","https://openalex.org/W6802659552","https://openalex.org/W6810030924","https://openalex.org/W6810450869","https://openalex.org/W6810466897","https://openalex.org/W6810936812"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2018662469","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2062802260"],"abstract_inverted_index":{"By":[0],"utilizing":[1],"previously":[2],"offline":[3,5,28,174,220],"data,":[4],"reinforcement":[6],"learning":[7],"(offline":[8],"RL)":[9],"can":[10,98],"develop":[11],"effective":[12],"policies":[13],"for":[14,187],"the":[15,24,30,60,68,73,80,86,107,112,116,123,139,144,154,159,163,173,188,196,199,205,216,228,236,241],"environment":[16,125],"with":[17,240],"complex":[18,124],"online":[19,208,223],"interaction.":[20],"However,":[21],"due":[22,121],"to":[23,45,58,76,101,122,138,181,203],"incomplete":[25],"coverage":[26],"of":[27,33,109,162,198,207,219],"datasets,":[29],"estimation":[31,57,118,160],"errors":[32],"Q-functions":[34,165],"caused":[35,214],"by":[36,157,215],"out-of-distribution":[37],"(OOD)":[38],"actions":[39,110,156],"may":[40],"cause":[41,99],"current":[42],"off-policy":[43],"methods":[44],"fail.":[46],"Offline":[47],"RL":[48],"uses":[49],"policy":[50,62,69,75,237],"constraints,":[51],"value":[52,87,242],"function":[53,88,243],"regularization,":[54],"or":[55,126],"uncertainty":[56,117,185,193],"drive":[59],"learned":[61,74],"from":[63],"resembling":[64],"behavioral":[65,82],"policy.":[66,83],"Unfortunately,":[67],"constraints":[70,238],"approach":[71,90,239],"restricts":[72],"a":[77,136,148,167,178],"region":[78],"near":[79],"sub-optimal":[81],"In":[84],"addition,":[85],"regularization":[89,244],"does":[91],"not":[92],"accurately":[93],"assess":[94],"OOD":[95,155],"actions,":[96],"which":[97],"it":[100],"be":[102],"too":[103],"conservative":[104],"in":[105,130],"estimating":[106],"Q-value":[108],"within":[111],"proximity":[113],"distribution.":[114],"Finally,":[115],"is":[119],"biased":[120],"inaccurate":[127],"valuation":[128],"early":[129],"training.":[131],"We":[132],"suggest":[133],"Density-UCR":[134,142,171,191,233,247],"as":[135,166,195],"solution":[137],"aforementioned":[140],"issues.":[141],"makes":[143],"Q-function":[145],"estimate":[146],"have":[147],"lower-confidence":[149],"bound":[150],"(LCB)":[151],"and":[152,210],"penalizes":[153],"using":[158,177],"error":[161],"ensemble":[164],"penalty":[168,189],"value.":[169,190],"Additionally,":[170],"models":[172],"data's":[175],"distribution":[176,217],"density":[179],"estimator":[180],"derive":[182],"more":[183],"accurate":[184],"weights":[186],"employs":[192],"estimates":[194],"weight":[197],"priority":[200],"replay":[201],"buffer":[202],"increase":[204],"stability":[206],"fine-tuning":[209,251],"prevent":[211],"performance":[212],"degradation":[213],"shift":[218],"samples":[221],"over":[222],"samples.":[224],"Our":[225],"experiments":[226],"on":[227],"D4RL":[229],"benchmark":[230],"show":[231],"that":[232],"significantly":[234],"outperforms":[235],"approach.":[245],"Furthermore,":[246],"also":[248],"offers":[249],"excellent":[250],"performance.":[252]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}