{"id":"https://openalex.org/W4317553716","doi":"https://doi.org/10.1109/lra.2023.3238656","title":"Model-Free Safe Reinforcement Learning Through Neural Barrier Certificate","display_name":"Model-Free Safe Reinforcement Learning Through Neural Barrier Certificate","publication_year":2023,"publication_date":"2023-01-20","ids":{"openalex":"https://openalex.org/W4317553716","doi":"https://doi.org/10.1109/lra.2023.3238656"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3238656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3238656","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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"],"raw_orcid":"https://orcid.org/0000-0001-7222-0019","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/A5057254330","display_name":"Yuxuan Jiang","orcid":"https://orcid.org/0000-0003-4285-0495"},"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":"Yuxuan Jiang","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4285-0495","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/A5100605130","display_name":"Yichen Liu","orcid":"https://orcid.org/0000-0002-6011-7628"},"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":"Yichen Liu","raw_affiliation_strings":["Institute of Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"],"raw_orcid":null,"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/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","Shanghai Qizhi Institute, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0282-8621","affiliations":[{"raw_affiliation_string":"Institute of Interdisciplinary Information Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shanghai Qizhi Institute, Shanghai, China","institution_ids":[]}]},{"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"],"raw_orcid":"https://orcid.org/0000-0003-4923-3633","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":5,"corresponding_author_ids":["https://openalex.org/A5101620888"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":5.4373,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96531529,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"8","issue":"3","first_page":"1295","last_page":"1302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.995199978351593,"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"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.995199978351593,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9937999844551086,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9634000062942505,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7730850577354431},{"id":"https://openalex.org/keywords/certificate","display_name":"Certificate","score":0.7372204065322876},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6395872235298157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6118997931480408},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4982583522796631},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.48026180267333984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36414891481399536},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25640666484832764},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18094345927238464},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17954713106155396}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7730850577354431},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.7372204065322876},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6395872235298157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6118997931480408},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4982583522796631},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48026180267333984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36414891481399536},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25640666484832764},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18094345927238464},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17954713106155396},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3238656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3238656","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W1980569135","https://openalex.org/W2736601468","https://openalex.org/W2963148914","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/W3127561923","https://openalex.org/W3162902207","https://openalex.org/W3195968524","https://openalex.org/W3203076355","https://openalex.org/W3207110310","https://openalex.org/W4205626291","https://openalex.org/W4206497039","https://openalex.org/W4313173809","https://openalex.org/W4362650413","https://openalex.org/W6617021176","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6687063787","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6751535212","https://openalex.org/W6751725685","https://openalex.org/W6753691991","https://openalex.org/W6760405395","https://openalex.org/W6767277667","https://openalex.org/W6771280675","https://openalex.org/W6772100842","https://openalex.org/W6780587392","https://openalex.org/W6785187516","https://openalex.org/W6785471904","https://openalex.org/W6785513857","https://openalex.org/W6785978685","https://openalex.org/W6788898170","https://openalex.org/W6799934450","https://openalex.org/W6800776581","https://openalex.org/W6801468180","https://openalex.org/W6804655846","https://openalex.org/W6810354499"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2349580982"],"abstract_inverted_index":{"Safety":[0],"is":[1,73,92,157],"a":[2,57,77,80,95,124,176],"critical":[3],"concern":[4],"when":[5],"applying":[6],"reinforcement":[7],"learning":[8],"(RL)":[9],"to":[10,28,74,123,218],"real-world":[11],"control":[12,42,197],"tasks.":[13,233],"However,":[14],"existing":[15],"safe":[16,41,59],"RL":[17,60],"works":[18],"either":[19],"only":[20],"consider":[21],"expected":[22],"safety":[23,30,36,149],"constraint":[24,65,87,161,212],"violations":[25,66,101,213],"and":[26,48,79,127,139,145,150,202,214],"fail":[27],"maintain":[29],"guarantees,":[31],"or":[32],"use":[33],"overly":[34],"conservative":[35],"certificate":[37,83,91,122,144],"tools":[38],"borrowed":[39],"from":[40],"theory,":[43],"which":[44],"sacrifices":[45],"reward":[46],"optimization":[47],"relies":[49],"on":[50,106,192,231],"analytic":[51],"system":[52],"models.":[53],"This":[54,134],"letter":[55],"proposes":[56],"model-free":[58,96,177],"algorithm":[61,191,209],"that":[62,207],"achieves":[63,210],"near-zero":[64,211],"with":[67],"high":[68,215],"rewards.":[69],"Our":[70],"key":[71],"idea":[72],"jointly":[75],"learn":[76],"policy":[78,156,174],"neural":[81],"barrier":[82,90,104,121,143,224],"under":[84,159],"stepwise":[85],"state":[86],"setting.":[88],"The":[89,155],"learned":[93,223],"in":[94,175,185],"manner":[97,178],"by":[98,110,179],"minimizing":[99],"the":[100,111,115,120,129,137,142,148,153,160,163,168,173,186,219,222,228],"of":[102,119,141,152,162],"appropriate":[103],"properties":[105],"transition":[107],"data":[108],"collected":[109],"policy.":[112,154],"We":[113,171,188],"extend":[114],"single-step":[116],"invariant":[117,132,165],"property":[118,166],"multi-step":[125,131,164],"version":[126],"construct":[128],"corresponding":[130],"loss.":[133],"loss":[135],"balances":[136],"bias":[138],"variance":[140],"enhances":[146],"both":[147],"performance":[151,216],"optimized":[158],"using":[167],"Lagrangian":[169],"method.":[170],"optimize":[172],"introducing":[180],"an":[181],"importance":[182],"sampling":[183],"weight":[184],"constraint.":[187],"test":[189],"our":[190,208],"multiple":[193,232],"problems,":[194],"including":[195],"classic":[196],"tasks,":[198],"robot":[199],"collision":[200],"avoidance,":[201],"autonomous":[203],"driving.":[204],"Results":[205],"show":[206],"compared":[217],"baselines.":[220],"Moreover,":[221],"certificates":[225],"successfully":[226],"identify":[227],"feasible":[229],"regions":[230]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":7}],"updated_date":"2026-05-13T08:25:38.343686","created_date":"2025-10-10T00:00:00"}
