{"id":"https://openalex.org/W4285606945","doi":"https://doi.org/10.24963/ijcai.2022/510","title":"Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk","display_name":"Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285606945","doi":"https://doi.org/10.24963/ijcai.2022/510"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/510","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/510","pdf_url":"https://www.ijcai.org/proceedings/2022/0510.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0510.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102656708","display_name":"Chengyang Ying","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145457","display_name":"Robert Bosch (Taiwan)","ror":"https://ror.org/046as2g47","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210145457","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I4210148639","display_name":"Wuhan Engineering Science & Technology Institute","ror":"https://ror.org/04ez3r306","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210148639"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"ChengYang Ying","raw_affiliation_strings":["Tsinghua University","Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University;","Department of Computer Science & Technology, Institute for AI, BNRist Center,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University;","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210145457"]},{"raw_affiliation_string":"Department of Computer Science & Technology, Institute for AI, BNRist Center,","institution_ids":["https://openalex.org/I4210148639"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060724443","display_name":"Xinning Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145457","display_name":"Robert Bosch (Taiwan)","ror":"https://ror.org/046as2g47","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210145457","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I4210148639","display_name":"Wuhan Engineering Science & Technology Institute","ror":"https://ror.org/04ez3r306","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210148639"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Xinning Zhou","raw_affiliation_strings":["Tsinghua University","Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University;","Department of Computer Science & Technology, Institute for AI, BNRist Center,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University;","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210145457"]},{"raw_affiliation_string":"Department of Computer Science & Technology, Institute for AI, BNRist Center,","institution_ids":["https://openalex.org/I4210148639"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035606234","display_name":"Hang Su","orcid":"https://orcid.org/0000-0003-4889-1669"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I4210145457","display_name":"Robert Bosch (Taiwan)","ror":"https://ror.org/046as2g47","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210145457","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I4210148639","display_name":"Wuhan Engineering Science & Technology Institute","ror":"https://ror.org/04ez3r306","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210148639"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Hang Su","raw_affiliation_strings":["Peng Cheng Laboratory","Tsinghua University","Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute","Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University;","Department of Computer Science & Technology, Institute for AI, BNRist Center,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute","institution_ids":["https://openalex.org/I180662265","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University;","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210145457"]},{"raw_affiliation_string":"Department of Computer Science & Technology, Institute for AI, BNRist Center,","institution_ids":["https://openalex.org/I4210148639"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080233678","display_name":"Dong Yan","orcid":"https://orcid.org/0000-0003-4549-9469"},"institutions":[{"id":"https://openalex.org/I4210145457","display_name":"Robert Bosch (Taiwan)","ror":"https://ror.org/046as2g47","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210145457","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I4210148639","display_name":"Wuhan Engineering Science & Technology Institute","ror":"https://ror.org/04ez3r306","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210148639"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Dong Yan","raw_affiliation_strings":["Tsinghua University","Department of Computer Science & Technology, Institute for AI, BNRist Center,","Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science & Technology, Institute for AI, BNRist Center,","institution_ids":["https://openalex.org/I4210148639"]},{"raw_affiliation_string":"Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University;","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210145457"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446701","display_name":"Ning Chen","orcid":"https://orcid.org/0000-0002-6742-0048"},"institutions":[{"id":"https://openalex.org/I4210145457","display_name":"Robert Bosch (Taiwan)","ror":"https://ror.org/046as2g47","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210145457","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I4210148639","display_name":"Wuhan Engineering Science & Technology Institute","ror":"https://ror.org/04ez3r306","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210148639"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Ning Chen","raw_affiliation_strings":["Tsinghua University","Department of Computer Science & Technology, Institute for AI, BNRist Center,","Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science & Technology, Institute for AI, BNRist Center,","institution_ids":["https://openalex.org/I4210148639"]},{"raw_affiliation_string":"Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University;","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210145457"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104028660","display_name":"Jun Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I4210145457","display_name":"Robert Bosch (Taiwan)","ror":"https://ror.org/046as2g47","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210145457","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I4210148639","display_name":"Wuhan Engineering Science & Technology Institute","ror":"https://ror.org/04ez3r306","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210148639"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Jun Zhu","raw_affiliation_strings":["Peng Cheng Laboratory","Tsinghua University","Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute","Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University;","Department of Computer Science & Technology, Institute for AI, BNRist Center,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute","institution_ids":["https://openalex.org/I180662265","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University;","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210145457"]},{"raw_affiliation_string":"Department of Computer Science & Technology, Institute for AI, BNRist Center,","institution_ids":["https://openalex.org/I4210148639"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0756,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.89037901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3673","last_page":"3680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9966999888420105,"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":0.9966999888420105,"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":0.9860000014305115,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9574999809265137,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/cvar","display_name":"CVAR","score":0.8684029579162598},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8560848236083984},{"id":"https://openalex.org/keywords/disturbance","display_name":"Disturbance (geology)","score":0.555541455745697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5402708649635315},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5371841192245483},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4962010979652405},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.48858484625816345},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.44828665256500244},{"id":"https://openalex.org/keywords/pessimism","display_name":"Pessimism","score":0.43350666761398315},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4217436909675598},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.365130752325058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3583962917327881},{"id":"https://openalex.org/keywords/expected-shortfall","display_name":"Expected shortfall","score":0.3476299047470093},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2780582308769226},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27566829323768616},{"id":"https://openalex.org/keywords/risk-management","display_name":"Risk management","score":0.2000691294670105},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18369612097740173},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11191004514694214}],"concepts":[{"id":"https://openalex.org/C2779922397","wikidata":"https://www.wikidata.org/wiki/Q5014755","display_name":"CVAR","level":4,"score":0.8684029579162598},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8560848236083984},{"id":"https://openalex.org/C2777601987","wikidata":"https://www.wikidata.org/wiki/Q5283581","display_name":"Disturbance (geology)","level":2,"score":0.555541455745697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5402708649635315},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5371841192245483},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4962010979652405},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48858484625816345},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.44828665256500244},{"id":"https://openalex.org/C9992130","wikidata":"https://www.wikidata.org/wiki/Q484954","display_name":"Pessimism","level":2,"score":0.43350666761398315},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4217436909675598},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.365130752325058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3583962917327881},{"id":"https://openalex.org/C5496284","wikidata":"https://www.wikidata.org/wiki/Q5420856","display_name":"Expected shortfall","level":3,"score":0.3476299047470093},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2780582308769226},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27566829323768616},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.2000691294670105},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18369612097740173},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11191004514694214},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2022/510","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/510","pdf_url":"https://www.ijcai.org/proceedings/2022/0510.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04934770v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04934770","pdf_url":"https://hal.science/hal-04934770v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025","raw_type":"info:eu-repo/semantics/preprint"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/510","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/510","pdf_url":"https://www.ijcai.org/proceedings/2022/0510.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G162864083","display_name":null,"funder_award_id":"U19A2081","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G168428553","display_name":null,"funder_award_id":"PCL2021A12","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1919465925","display_name":null,"funder_award_id":"61621136008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1948779041","display_name":null,"funder_award_id":"62076147","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3178445835","display_name":null,"funder_award_id":"2020AAA0106302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3763772386","display_name":null,"funder_award_id":"2020AAA0106302","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4381173361","display_name":null,"funder_award_id":"2020AAA0104304","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5372072380","display_name":null,"funder_award_id":"U1811461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5379697419","display_name":null,"funder_award_id":"62061136001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6645987955","display_name":null,"funder_award_id":"U19B2034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7024251178","display_name":null,"funder_award_id":"2020AAA0106000","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285606945.pdf","grobid_xml":"https://content.openalex.org/works/W4285606945.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W134786152","https://openalex.org/W580164506","https://openalex.org/W1522301498","https://openalex.org/W1771410628","https://openalex.org/W1845972764","https://openalex.org/W1965878388","https://openalex.org/W2121183216","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2154756406","https://openalex.org/W2155027007","https://openalex.org/W2155153696","https://openalex.org/W2158782408","https://openalex.org/W2197493596","https://openalex.org/W2257979135","https://openalex.org/W2736601468","https://openalex.org/W2803308811","https://openalex.org/W2949103145","https://openalex.org/W2949963197","https://openalex.org/W2953174175","https://openalex.org/W2986399309","https://openalex.org/W3098237412","https://openalex.org/W3162902207","https://openalex.org/W3176452384","https://openalex.org/W4250739957","https://openalex.org/W4287329986","https://openalex.org/W4287810981"],"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/W2008510020","https://openalex.org/W2014298110","https://openalex.org/W2096554740","https://openalex.org/W2147389337","https://openalex.org/W2989754218"],"abstract_inverted_index":{"Though":[0],"deep":[1],"reinforcement":[2,31,127],"learning":[3,32,128],"(DRL)":[4],"has":[5],"obtained":[6],"substantial":[7],"success,":[8],"it":[9],"may":[10,58],"encounter":[11],"catastrophic":[12],"failures":[13],"due":[14],"to":[15,60,94],"the":[16,26,51,54,73,95,98,102,106,111,135],"intrinsic":[17],"uncertainty":[18],"of":[19,25,45,50,87,121,130,171],"both":[20,163],"transition":[21,36,77,166],"and":[22,79,105,123,158,165],"observation.":[23],"Most":[24],"existing":[27],"methods":[28],"for":[29],"safe":[30],"can":[33],"only":[34],"handle":[35],"disturbance":[37,40,46,78,81],"or":[38],"observation":[39,80,164],"since":[41],"these":[42,66],"two":[43],"kinds":[44],"affect":[47],"different":[48],"parts":[49],"agent;":[52],"besides,":[53],"popular":[55],"worst-case":[56],"return":[57],"lead":[59],"overly":[61],"pessimistic":[62],"policies.":[63],"To":[64],"address":[65],"issues,":[67],"we":[68,113],"first":[69],"theoretically":[70],"prove":[71],"that":[72,151],"performance":[74],"degradation":[75],"under":[76,144],"depends":[82],"on":[83,110,168],"a":[84,125,145,154,169],"novel":[85,126],"metric":[86],"Value":[88],"Function":[89],"Range":[90],"(VFR),":[91],"which":[92,133],"corresponds":[93],"gap":[96],"in":[97,175],"value":[99],"function":[100],"between":[101],"best":[103],"state":[104],"worst":[107],"state.":[108],"Based":[109],"analysis,":[112],"adopt":[114],"conditional":[115],"value-at-risk":[116],"(CVaR)":[117],"as":[118],"an":[119],"assessment":[120],"risk":[122],"propose":[124],"algorithm":[129],"CVaR-Proximal-Policy-Optimization":[131],"(CPPO)":[132],"formalizes":[134],"risk-sensitive":[136],"constrained":[137],"optimization":[138],"problem":[139],"by":[140],"keeping":[141],"its":[142],"CVaR":[143],"given":[146],"threshold.":[147],"Experimental":[148],"results":[149],"show":[150],"CPPO":[152],"achieves":[153],"higher":[155],"cumulative":[156],"reward":[157],"is":[159],"more":[160],"robust":[161],"against":[162],"disturbances":[167],"series":[170],"continuous":[172],"control":[173],"tasks":[174],"MuJoCo.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2022-07-16T00:00:00"}