{"id":"https://openalex.org/W4308364487","doi":"https://doi.org/10.1109/tnnls.2022.3217189","title":"Monotonic Quantile Network for Worst-Case Offline Reinforcement Learning","display_name":"Monotonic Quantile Network for Worst-Case Offline Reinforcement Learning","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4308364487","doi":"https://doi.org/10.1109/tnnls.2022.3217189","pmid":"https://pubmed.ncbi.nlm.nih.gov/36331649"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3217189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3217189","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":["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/A5044788927","display_name":"Chenjia Bai","orcid":"https://orcid.org/0000-0002-8379-9385"},"institutions":[{"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 AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8379-9385","affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101645983","display_name":"Ting Xiao","orcid":"https://orcid.org/0000-0003-1694-0294"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Xiao","raw_affiliation_strings":["School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102003533","display_name":"Zhoufan Zhu","orcid":"https://orcid.org/0000-0001-9800-6344"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhoufan Zhu","raw_affiliation_strings":["School of Statistics and Management, Shanghai University of Finance and Economics, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9800-6344","affiliations":[{"raw_affiliation_string":"School of Statistics and Management, Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"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 the Department of 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 the Department of Management Sciences, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403433","display_name":"Fan Zhou","orcid":"https://orcid.org/0000-0002-0900-6965"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhou","raw_affiliation_strings":["School of Statistics and Management, Shanghai University of Finance and Economics, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Statistics and Management, Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061193324","display_name":"Animesh Garg","orcid":"https://orcid.org/0000-0003-0482-4296"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Animesh Garg","raw_affiliation_strings":["Vector Institute, University of Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0482-4296","affiliations":[{"raw_affiliation_string":"Vector Institute, University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049557511","display_name":"Bin He","orcid":"https://orcid.org/0000-0003-3193-6269"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin He","raw_affiliation_strings":["School of Electronic and Information Engineering, Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China","Shanghai Research Institute for Intelligent Autonomous Systems, School of Electronic and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3193-6269","affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Shanghai Research Institute for Intelligent Autonomous Systems, School of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346747","display_name":"Peng Liu","orcid":"https://orcid.org/0000-0001-6568-1335"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-6568-1335","affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101934110","display_name":"Zhaoran Wang","orcid":"https://orcid.org/0000-0002-1824-2580"},"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 the Department of Management Sciences, Northwestern University, Evanston, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and the Department of Management Sciences, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7404,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86522052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"35","issue":"7","first_page":"8954","last_page":"8968"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.991100013256073,"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":0.991100013256073,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.906499981880188,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/quantile","display_name":"Quantile","score":0.8518914580345154},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7994056344032288},{"id":"https://openalex.org/keywords/quantile-regression","display_name":"Quantile regression","score":0.690162181854248},{"id":"https://openalex.org/keywords/cvar","display_name":"CVAR","score":0.6820594072341919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6664685606956482},{"id":"https://openalex.org/keywords/quantile-function","display_name":"Quantile function","score":0.5375188589096069},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.5326625108718872},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5221688747406006},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4970696270465851},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.46938464045524597},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45636600255966187},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.41120994091033936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39845010638237},{"id":"https://openalex.org/keywords/expected-shortfall","display_name":"Expected shortfall","score":0.3868638873100281},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3370243310928345},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.32661595940589905},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.19678610563278198},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17004072666168213},{"id":"https://openalex.org/keywords/cumulative-distribution-function","display_name":"Cumulative distribution function","score":0.16172462701797485},{"id":"https://openalex.org/keywords/risk-management","display_name":"Risk management","score":0.13569232821464539},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12796655297279358},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11390399932861328},{"id":"https://openalex.org/keywords/probability-density-function","display_name":"Probability density function","score":0.07848188281059265}],"concepts":[{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.8518914580345154},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7994056344032288},{"id":"https://openalex.org/C63817138","wikidata":"https://www.wikidata.org/wiki/Q3455889","display_name":"Quantile regression","level":2,"score":0.690162181854248},{"id":"https://openalex.org/C2779922397","wikidata":"https://www.wikidata.org/wiki/Q5014755","display_name":"CVAR","level":4,"score":0.6820594072341919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664685606956482},{"id":"https://openalex.org/C47121976","wikidata":"https://www.wikidata.org/wiki/Q3489473","display_name":"Quantile function","level":4,"score":0.5375188589096069},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.5326625108718872},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5221688747406006},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4970696270465851},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.46938464045524597},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45636600255966187},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.41120994091033936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39845010638237},{"id":"https://openalex.org/C5496284","wikidata":"https://www.wikidata.org/wiki/Q5420856","display_name":"Expected shortfall","level":3,"score":0.3868638873100281},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3370243310928345},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.32661595940589905},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.19678610563278198},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17004072666168213},{"id":"https://openalex.org/C103784038","wikidata":"https://www.wikidata.org/wiki/Q386228","display_name":"Cumulative distribution function","level":3,"score":0.16172462701797485},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.13569232821464539},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12796655297279358},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11390399932861328},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.07848188281059265},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3217189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3217189","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:36331649","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36331649","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}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W2041946752","https://openalex.org/W2053984877","https://openalex.org/W2095247603","https://openalex.org/W2328111639","https://openalex.org/W2761873684","https://openalex.org/W2765302304","https://openalex.org/W2784092749","https://openalex.org/W2982316857","https://openalex.org/W2989186172","https://openalex.org/W2998059334","https://openalex.org/W3015082424","https://openalex.org/W3092804041","https://openalex.org/W3123216837","https://openalex.org/W3178318699","https://openalex.org/W3179631121","https://openalex.org/W3192508890","https://openalex.org/W3197854638","https://openalex.org/W3215494060","https://openalex.org/W3216656735","https://openalex.org/W4214717370","https://openalex.org/W4236818056","https://openalex.org/W4241996101","https://openalex.org/W6683300800","https://openalex.org/W6683517036","https://openalex.org/W6741832134","https://openalex.org/W6747473740","https://openalex.org/W6751629939","https://openalex.org/W6757469721","https://openalex.org/W6758417531","https://openalex.org/W6763704811","https://openalex.org/W6767112054","https://openalex.org/W6767776290","https://openalex.org/W6771270455","https://openalex.org/W6774321585","https://openalex.org/W6774583691","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6779594309","https://openalex.org/W6780159193","https://openalex.org/W6784643869","https://openalex.org/W6786019710","https://openalex.org/W6789730260","https://openalex.org/W6791413555","https://openalex.org/W6792049622","https://openalex.org/W6795014841","https://openalex.org/W6795425552","https://openalex.org/W6796289742","https://openalex.org/W6796589144","https://openalex.org/W6797154179","https://openalex.org/W6798790070","https://openalex.org/W6801798027","https://openalex.org/W6801801719","https://openalex.org/W6802648193","https://openalex.org/W6810030924","https://openalex.org/W6838240175"],"related_works":["https://openalex.org/W4316167276","https://openalex.org/W2002736235","https://openalex.org/W2232143283","https://openalex.org/W1647779468","https://openalex.org/W48101171","https://openalex.org/W2014298110","https://openalex.org/W2096554740","https://openalex.org/W2147389337","https://openalex.org/W2989754218","https://openalex.org/W3124407081"],"abstract_inverted_index":{"A":[0],"key":[1],"challenge":[2],"in":[3,19,33,49,124,153,159,178],"offline":[4,14,34,50,125,164],"reinforcement":[5],"learning":[6,28],"(RL)":[7],"is":[8,16,60],"how":[9],"to":[10,68,94,119],"ensure":[11],"the":[12,56,63,96,104,112,121,135,140,150,167],"learned":[13],"policy":[15,87,132],"safe,":[17],"especially":[18],"safety-critical":[20],"domains.":[21],"In":[22],"this":[23,72],"article,":[24],"we":[25,74,90,107,128,145],"focus":[26],"on":[27],"a":[29,38,45,130],"distributional":[30,46,141],"value":[31,47,142],"function":[32,48],"RL":[35,51],"and":[36,62,162,166,175],"optimizing":[37,44,134],"worst-case":[39,131],"criterion":[40],"of":[41,103,139,149],"returns.":[42],"However,":[43],"can":[52],"be":[53,69],"hard,":[54],"since":[55],"crossing":[57],"quantile":[58,77,82,113],"issue":[59],"serious,":[61],"distribution":[64,97,122],"shift":[65,123],"problem":[66],"needs":[67],"addressed.":[70],"To":[71],"end,":[73],"propose":[75,91],"monotonic":[76],"network":[78],"(MQN)":[79],"with":[80,100],"conservative":[81,176],"regression":[83],"(CQR)":[84],"for":[85,115],"risk-averse":[86],"learning.":[88],"First,":[89],"an":[92],"MQN":[93],"learn":[95,129],"over":[98],"returns":[99],"non-crossing":[101],"guarantees":[102],"quantiles.":[105],"Then,":[106],"perform":[108],"CQR":[109],"by":[110,133],"penalizing":[111],"estimation":[114],"out-of-distribution":[116],"(OOD)":[117],"actions":[118],"address":[120],"RL.":[126],"Finally,":[127],"conditional":[136],"value-at-risk":[137],"(CVaR)":[138],"function.":[143],"Furthermore,":[144],"provide":[146],"theoretical":[147],"analysis":[148],"fixed-point":[151],"convergence":[152],"our":[154,171],"method.":[155],"We":[156],"conduct":[157],"experiments":[158],"both":[160],"risk-neutral":[161],"risk-sensitive":[163],"settings,":[165],"results":[168],"show":[169],"that":[170],"method":[172],"obtains":[173],"safe":[174],"behaviors":[177],"robotic":[179],"locomotion":[180],"tasks.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}