{"id":"https://openalex.org/W4388952994","doi":"https://doi.org/10.1109/tac.2023.3336263","title":"Synthesizing Control Barrier Functions With Feasible Region Iteration for Safe Reinforcement Learning","display_name":"Synthesizing Control Barrier Functions With Feasible Region Iteration for Safe Reinforcement Learning","publication_year":2023,"publication_date":"2023-11-23","ids":{"openalex":"https://openalex.org/W4388952994","doi":"https://doi.org/10.1109/tac.2023.3336263"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2023.3336263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2023.3336263","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-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/A5101620888","display_name":"Yujie Yang","orcid":"https://orcid.org/0000-0001-7222-0019"},"institutions":[{"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"],"is_corresponding":true,"raw_author_name":"Yujie Yang","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028357638","display_name":"Yuhang Zhang","orcid":"https://orcid.org/0009-0006-4272-5730"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Yuhang Zhang","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009217428","display_name":"Wenjun Zou","orcid":"https://orcid.org/0009-0009-5331-0938"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Wenjun Zou","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072222039","display_name":"Jianyu Chen","orcid":"https://orcid.org/0000-0003-0282-8621"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Jianyu Chen","raw_affiliation_strings":["Institute of Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Interdisciplinary Information Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021699314","display_name":"Yuming Yin","orcid":"https://orcid.org/0000-0002-2854-921X"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Yin","raw_affiliation_strings":["College of Mechanical Engineering, Zhejiang University of Technology, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"College of Mechanical Engineering, Zhejiang University of Technology, Zhejiang, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"https://orcid.org/0000-0003-4923-3633"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101620888"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.6458,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8418253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"69","issue":"4","first_page":"2713","last_page":"2720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9902999997138977,"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/T10142","display_name":"Formal Methods in Verification","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7119686007499695},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6982675790786743},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6680414080619812},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5870299339294434},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5726011991500854},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5351406335830688},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5281426906585693},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32596713304519653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26446855068206787}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7119686007499695},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6982675790786743},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6680414080619812},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5870299339294434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5726011991500854},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5351406335830688},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5281426906585693},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32596713304519653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26446855068206787},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2023.3336263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2023.3336263","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320322622","display_name":"Toyota Motor Corporation","ror":"https://ror.org/02zqm6r10"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W2560504659","https://openalex.org/W2735010720","https://openalex.org/W2963525569","https://openalex.org/W2964040381","https://openalex.org/W2966735560","https://openalex.org/W2968945909","https://openalex.org/W2989847975","https://openalex.org/W2990747716","https://openalex.org/W3118210634","https://openalex.org/W3119862069","https://openalex.org/W3131411499","https://openalex.org/W3150718622","https://openalex.org/W3195647294","https://openalex.org/W3195968524","https://openalex.org/W3207727352","https://openalex.org/W4210279164","https://openalex.org/W4210899143","https://openalex.org/W4224216677","https://openalex.org/W4226245271","https://openalex.org/W4252517507","https://openalex.org/W4293370597","https://openalex.org/W4362650413","https://openalex.org/W4382935993","https://openalex.org/W6737893269","https://openalex.org/W6747473740","https://openalex.org/W6751725685","https://openalex.org/W6760405395","https://openalex.org/W6774126978","https://openalex.org/W6804655846"],"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/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W1510768092","https://openalex.org/W2611003898","https://openalex.org/W2230808081"],"abstract_inverted_index":{"Safety":[0],"is":[1,21,83,112],"a":[2,24,84,92],"critical":[3],"concern":[4],"when":[5],"applying":[6],"reinforcement":[7],"learning":[8],"(RL)":[9],"to":[10,22,74,98],"real-world":[11],"control":[12,25],"problems.":[13],"A":[14],"widely":[15],"used":[16],"method":[17],"for":[18],"ensuring":[19],"safety":[20],"learn":[23],"barrier":[26],"function":[27,87],"with":[28,91],"heuristic":[29],"feasibility":[30,77],"labels":[31],"that":[32,68,128],"come":[33],"from":[34],"expert":[35],"demonstrations":[36],"[1]":[37],"or":[38,137],"constraint":[39,85,100,133],"functions":[40],"[2].":[41],"However,":[42],"their":[43],"forward":[44],"invariant":[45],"sets":[46],"fall":[47],"short":[48],"of":[49,55,81,117],"the":[50,70,99,108,115,141],"maximum":[51,71,109],"feasible":[52,64,72,110,118,122],"region":[53,65,73,119,123],"because":[54],"inaccurate":[56],"labels.":[57,78],"This":[58],"paper":[59],"proposes":[60],"an":[61],"algorithm":[62,130],"called":[63],"iteration":[66,116],"(FRI)":[67],"learns":[69],"generate":[75],"accurate":[76],"The":[79,103],"core":[80],"FRI":[82],"decay":[86],"(CDF),":[88],"which":[89,106],"comes":[90],"self-consistency":[93],"condition":[94],"and":[95,121,135],"naturally":[96],"leads":[97],"Bellman":[101],"equation.":[102],"optimal":[104],"CDF,":[105],"represents":[107],"region,":[111],"learned":[113],"through":[114],"identification":[120],"expansion.":[124],"Experiment":[125],"results":[126],"show":[127],"our":[129],"achieves":[131],"near-zero":[132],"violations":[134],"comparable":[136],"higher":[138],"performance":[139],"than":[140],"baselines.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}