{"id":"https://openalex.org/W3185438801","doi":"https://doi.org/10.1007/978-3-030-81685-8_22","title":"An Iterative Scheme of Safe Reinforcement Learning for Nonlinear Systems via Barrier Certificate Generation","display_name":"An Iterative Scheme of Safe Reinforcement Learning for Nonlinear Systems via Barrier Certificate Generation","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3185438801","doi":"https://doi.org/10.1007/978-3-030-81685-8_22","mag":"3185438801"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-81685-8_22","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-81685-8_22","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-81685-8_22.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-81685-8_22.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103026076","display_name":"Zhengfeng Yang","orcid":"https://orcid.org/0000-0001-6316-1723"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengfeng Yang","raw_affiliation_strings":["Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652603","display_name":"Yidan Zhang","orcid":"https://orcid.org/0000-0002-7589-530X"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidan Zhang","raw_affiliation_strings":["Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703485","display_name":"Lin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1328775524","display_name":"Zhejiang Sci-Tech University","ror":"https://ror.org/03893we55","country_code":"CN","type":"education","lineage":["https://openalex.org/I1328775524"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wang Lin","raw_affiliation_strings":["School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, China","institution_ids":["https://openalex.org/I1328775524"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079927285","display_name":"Xia Zeng","orcid":"https://orcid.org/0000-0003-2575-7045"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xia Zeng","raw_affiliation_strings":["School of Computer and Information Science, Southwest University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information Science, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014039749","display_name":"Xiaochao Tang","orcid":"https://orcid.org/0000-0001-7357-8864"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochao Tang","raw_affiliation_strings":["Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058328411","display_name":"Zhenbing Zeng","orcid":"https://orcid.org/0000-0002-9728-1114"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenbing Zeng","raw_affiliation_strings":["Department of Mathematics, Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100405109","display_name":"Zhiming Liu","orcid":"https://orcid.org/0000-0001-9771-3071"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]},{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiming Liu","raw_affiliation_strings":["Centre for Intelligent and Embedded Software, Northwestern Polytechnical University, Suzhou, China","School of Computer and Information Science, Southwest University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Intelligent and Embedded Software, Northwestern Polytechnical University, Suzhou, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer and Information Science, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100703485"],"corresponding_institution_ids":["https://openalex.org/I1328775524"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":3.2314,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9336685,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"467","last_page":"490"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9988999962806702,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9988999962806702,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.994700014591217,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9837999939918518,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6676927804946899},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6329723596572876},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5415568351745605},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5290024876594543},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5266672968864441},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5202130675315857},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4956601858139038},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.44926732778549194},{"id":"https://openalex.org/keywords/certificate","display_name":"Certificate","score":0.43114978075027466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.329012006521225},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25720280408859253},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13363194465637207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6676927804946899},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6329723596572876},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5415568351745605},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5290024876594543},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5266672968864441},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5202130675315857},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4956601858139038},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.44926732778549194},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.43114978075027466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.329012006521225},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25720280408859253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13363194465637207},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-81685-8_22","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-81685-8_22","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-81685-8_22.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-81685-8_22","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-81685-8_22","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-81685-8_22.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G1198626777","display_name":null,"funder_award_id":"SWU117058","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G1386706470","display_name":null,"funder_award_id":"62032019","funder_id":"https://openalex.org/F4320323711","funder_display_name":"Southwest University"},{"id":"https://openalex.org/G2827232581","display_name":"\u57fa\u4e8e\u8ba1\u7b97\u5b9e\u4ee3\u6570\u51e0\u4f55\u7684\u6df7\u6210\u7cfb\u7edf\u9a8c\u8bc1\u7814\u7a76","funder_award_id":"61772203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3323081998","display_name":null,"funder_award_id":"61732019","funder_id":"https://openalex.org/F4320323711","funder_display_name":"Southwest University"},{"id":"https://openalex.org/G4164304690","display_name":"\u9762\u5411\u9700\u6c42\u4e0d\u786e\u5b9a\u6027\u7684\u667a\u80fd\u670d\u52a1\u67b6\u6784\u7814\u7a76","funder_award_id":"61732019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4193409221","display_name":null,"funder_award_id":"2018AAA0100902","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G780884354","display_name":null,"funder_award_id":"SWU116007","funder_id":"https://openalex.org/F4320323711","funder_display_name":"Southwest University"},{"id":"https://openalex.org/G8592490694","display_name":null,"funder_award_id":"62032019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323711","display_name":"Southwest University","ror":"https://ror.org/01kj4z117"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3185438801.pdf","grobid_xml":"https://content.openalex.org/works/W3185438801.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W2033118636","https://openalex.org/W2091565802","https://openalex.org/W2137470393","https://openalex.org/W2170665905","https://openalex.org/W2173248099","https://openalex.org/W2492490179","https://openalex.org/W2530699422","https://openalex.org/W2787908307","https://openalex.org/W2791251367","https://openalex.org/W2796726869","https://openalex.org/W2800473699","https://openalex.org/W2889490035","https://openalex.org/W2899087494","https://openalex.org/W2937290319","https://openalex.org/W2938701611","https://openalex.org/W2953466973","https://openalex.org/W2963186766","https://openalex.org/W2963334980","https://openalex.org/W2963655224","https://openalex.org/W2964130946","https://openalex.org/W2968945909","https://openalex.org/W2980176926","https://openalex.org/W2998402843","https://openalex.org/W3012097656","https://openalex.org/W3100014918","https://openalex.org/W3104371626","https://openalex.org/W3108060258","https://openalex.org/W3142708584","https://openalex.org/W4238726034","https://openalex.org/W6600529467","https://openalex.org/W6603830522","https://openalex.org/W6611525070","https://openalex.org/W6637162671"],"related_works":["https://openalex.org/W2165589608","https://openalex.org/W3093557575","https://openalex.org/W2378211422","https://openalex.org/W3182767856","https://openalex.org/W2354231916","https://openalex.org/W2162140574","https://openalex.org/W4321353415","https://openalex.org/W2354073393","https://openalex.org/W2361009070","https://openalex.org/W2378988399"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"this":[2],"paper,":[3],"we":[4],"propose":[5],"a":[6,33,36,47,63,93,125,144],"safe":[7,41,65,105,139],"reinforcement":[8,52],"learning":[9],"approach":[10,27,136],"to":[11,22,39,150],"synthesize":[12,40],"deep":[13,51],"neural":[14],"network":[15],"(DNN)":[16],"controllers":[17,98,106,141],"for":[18,143],"nonlinear":[19,145],"systems":[20],"subject":[21],"safety":[23],"constraints.":[24],"The":[25,44,130],"proposed":[26],"employs":[28],"an":[29],"iterative":[30,90],"scheme":[31,96],"where":[32],"learner":[34,45],"and":[35,54,68,77,99,120],"verifier":[37,56],"interact":[38],"DNN":[42,48,140],"controllers.":[43],"trains":[46],"controller":[49,60],"via":[50],"learning,":[53],"the":[55,58,84,117],"certifies":[57],"learned":[59],"through":[61],"computing":[62],"maximal":[64],"initial":[66],"region":[67],"its":[69,122],"corresponding":[70],"barrier":[71,100,109],"certificate,":[72],"based":[73],"on":[74],"polynomial":[75],"abstraction":[76],"bilinear":[78],"matrix":[79],"inequalities":[80],"solving.":[81],"Compared":[82],"with":[83,107,147],"existing":[85],"verification-in-the-loop":[86],"synthesis":[87,95],"methods,":[88],"our":[89,135],"framework":[91],"is":[92],"sequential":[94],"of":[97,127],"certificates,":[101],"which":[102],"can":[103],"learn":[104],"adaptive":[108],"certificates":[110],"rather":[111],"than":[112],"user-defined":[113],"ones.":[114],"We":[115],"implement":[116],"tool":[118],"SRLBC":[119],"evaluate":[121],"performance":[123],"over":[124],"set":[126],"benchmark":[128],"examples.":[129],"experimental":[131],"results":[132],"demonstrate":[133],"that":[134],"efficiently":[137],"synthesizes":[138],"even":[142],"system":[146],"dimension":[148],"up":[149],"12.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}