{"id":"https://openalex.org/W4311418673","doi":"https://doi.org/10.1080/09540091.2022.2151567","title":"Safe reinforcement learning for dynamical systems using barrier certificates","display_name":"Safe reinforcement learning for dynamical systems using barrier certificates","publication_year":2022,"publication_date":"2022-12-12","ids":{"openalex":"https://openalex.org/W4311418673","doi":"https://doi.org/10.1080/09540091.2022.2151567"},"language":"en","primary_location":{"id":"doi:10.1080/09540091.2022.2151567","is_oa":true,"landing_page_url":"https://doi.org/10.1080/09540091.2022.2151567","pdf_url":null,"source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1080/09540091.2022.2151567","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066401407","display_name":"Qingye Zhao","orcid":"https://orcid.org/0000-0002-7503-6759"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingye Zhao","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, People's Republic of China"],"raw_orcid":"https://orcid.org/0000-0002-7503-6759","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, People's Republic of China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077719990","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0003-0214-8917"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, People's Republic of China"],"raw_orcid":"https://orcid.org/0000-0003-0214-8917","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, People's Republic of China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090810072","display_name":"Xuandong Li","orcid":"https://orcid.org/0000-0003-3090-9568"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuandong Li","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, People's Republic of China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066401407"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":{"value":1270,"currency":"USD","value_usd":1270},"apc_paid":{"value":1270,"currency":"USD","value_usd":1270},"fwci":0.6944,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75903679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"34","issue":"1","first_page":"2822","last_page":"2844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9776999950408936,"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":0.9776999950408936,"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/T10217","display_name":"Cardiac electrophysiology and arrhythmias","score":0.9467999935150146,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10917","display_name":"Smart Grid Security and Resilience","score":0.9311000108718872,"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":0.8972363471984863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8040097951889038},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.581360399723053},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5538182258605957},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.45836031436920166},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4580494463443756},{"id":"https://openalex.org/keywords/counterexample","display_name":"Counterexample","score":0.4462340474128723},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4330657422542572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41582220792770386},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36757904291152954},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09473159909248352},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.07251894474029541}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8972363471984863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040097951889038},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.581360399723053},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5538182258605957},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.45836031436920166},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4580494463443756},{"id":"https://openalex.org/C162838799","wikidata":"https://www.wikidata.org/wiki/Q596077","display_name":"Counterexample","level":2,"score":0.4462340474128723},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4330657422542572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41582220792770386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36757904291152954},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09473159909248352},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07251894474029541},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/09540091.2022.2151567","is_oa":true,"landing_page_url":"https://doi.org/10.1080/09540091.2022.2151567","pdf_url":null,"source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:04bba19aafa14115b823278f19a094fd","is_oa":false,"landing_page_url":"https://doaj.org/article/04bba19aafa14115b823278f19a094fd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Connection Science, Vol 34, Iss 1, Pp 2822-2844 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1080/09540091.2022.2151567","is_oa":true,"landing_page_url":"https://doi.org/10.1080/09540091.2022.2151567","pdf_url":null,"source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2041196870","display_name":null,"funder_award_id":"62172210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7381784321","display_name":null,"funder_award_id":"62172211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8333389840","display_name":null,"funder_award_id":"62172200","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1480909796","https://openalex.org/W1607353007","https://openalex.org/W2053572490","https://openalex.org/W2075268401","https://openalex.org/W2121506959","https://openalex.org/W2166280160","https://openalex.org/W2173248099","https://openalex.org/W2561666900","https://openalex.org/W2594877703","https://openalex.org/W2618318883","https://openalex.org/W2625874945","https://openalex.org/W2787908307","https://openalex.org/W2791251367","https://openalex.org/W2792734461","https://openalex.org/W2796726869","https://openalex.org/W2798356176","https://openalex.org/W2889490035","https://openalex.org/W2889711700","https://openalex.org/W2890218953","https://openalex.org/W2899116309","https://openalex.org/W2900153411","https://openalex.org/W2904246096","https://openalex.org/W2919234322","https://openalex.org/W2942515073","https://openalex.org/W2945623569","https://openalex.org/W2963496101","https://openalex.org/W2963575966","https://openalex.org/W2966735560","https://openalex.org/W2980176926","https://openalex.org/W2996196387","https://openalex.org/W2996568167","https://openalex.org/W2998402843","https://openalex.org/W3003931103","https://openalex.org/W3006344226","https://openalex.org/W3021850381","https://openalex.org/W3024917158","https://openalex.org/W3034514558","https://openalex.org/W3036821294","https://openalex.org/W3041244724","https://openalex.org/W3099352109","https://openalex.org/W3100014918","https://openalex.org/W3113369941","https://openalex.org/W3119933750","https://openalex.org/W3120409696","https://openalex.org/W3148337675","https://openalex.org/W3150718622","https://openalex.org/W3161844359","https://openalex.org/W3190791531","https://openalex.org/W3193012498","https://openalex.org/W4225401163","https://openalex.org/W4226438853","https://openalex.org/W4281480521","https://openalex.org/W6684205842","https://openalex.org/W6713134421","https://openalex.org/W6779657896","https://openalex.org/W6780559895","https://openalex.org/W6784630725"],"related_works":["https://openalex.org/W2349952486","https://openalex.org/W1489260687","https://openalex.org/W2775700832","https://openalex.org/W3204670144","https://openalex.org/W2163101548","https://openalex.org/W1988934358","https://openalex.org/W2587222766","https://openalex.org/W4389574038","https://openalex.org/W4387718369","https://openalex.org/W3014450817"],"abstract_inverted_index":{"Safety":[0],"control":[1,136],"is":[2,12,57,79],"a":[3,42,124],"fundamental":[4],"problem":[5],"in":[6,41,118],"policy":[7,16,69,78,99,117,126],"design.":[8],"Basic":[9],"reinforcement":[10,38,54,156],"learning":[11,15,39,55,127,157],"effective":[13],"at":[14],"with":[17,145],"goal-reaching":[18,72],"property.":[19],"However,":[20],"it":[21],"does":[22],"not":[23,88],"guarantee":[24],"safety":[25,74,144],"property":[26],"of":[27,59,164],"the":[28,68,77,84,92,97,101,105,110,116,119,154,160],"learned":[29,98],"policy.":[30],"This":[31],"paper":[32],"integrates":[33],"barrier":[34],"certificates":[35],"into":[36],"actor-critic-based":[37],"methods":[40],"feedback-driven":[43],"framework":[44,56],"to":[45,70,112,153],"learn":[46],"safe":[47,53,125],"policies":[48],"for":[49,114],"dynamical":[50],"systems.":[51],"The":[52],"composed":[58],"two":[60,85],"interactive":[61],"parts:":[62],"Learner":[63,66,113],"and":[64,73,130,162],"Verifier.":[65],"trains":[67],"satisfy":[71],"properties.":[75],"Since":[76],"trained":[80],"on":[81,91,100,134],"training":[82],"datasets,":[83],"properties":[86],"may":[87],"be":[89],"retained":[90],"whole":[93,102],"system.":[94,103],"Verifier":[95,108],"validates":[96],"If":[104],"validation":[106],"fails,":[107],"returns":[109],"counterexamples":[111],"retraining":[115],"next":[120],"iteration.":[121],"We":[122],"implement":[123],"tool":[128],"SRLBC":[129,142],"evaluate":[131],"its":[132],"performance":[133],"three":[135],"tasks.":[137],"Experimental":[138],"results":[139],"show":[140],"that":[141],"achieves":[143],"no":[146],"more":[147],"than":[148],"0.5\u00d7":[149],"time":[150],"overhead":[151],"compared":[152],"baseline":[155],"method,":[158],"showing":[159],"feasibility":[161],"effectiveness":[163],"our":[165],"framework.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}