{"id":"https://openalex.org/W4290087551","doi":"https://doi.org/10.1007/978-3-031-13185-1_10","title":"Trainify: A CEGAR-Driven Training and\u00a0Verification Framework for\u00a0Safe Deep Reinforcement Learning","display_name":"Trainify: A CEGAR-Driven Training and\u00a0Verification Framework for\u00a0Safe Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4290087551","doi":"https://doi.org/10.1007/978-3-031-13185-1_10"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-13185-1_10","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-13185-1_10","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-13185-1_10.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/10.1007/978-3-031-13185-1_10.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089083556","display_name":"Jin Peng","orcid":"https://orcid.org/0000-0001-7354-5034"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Jin","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, ECNU, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing, ECNU, Shanghai, China","institution_ids":["https://openalex.org/I4210139618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032386338","display_name":"Jiaxu Tian","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxu Tian","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, ECNU, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing, ECNU, Shanghai, China","institution_ids":["https://openalex.org/I4210139618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089683084","display_name":"Dapeng Zhi","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dapeng Zhi","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, ECNU, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing, ECNU, Shanghai, China","institution_ids":["https://openalex.org/I4210139618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103526914","display_name":"Xuejun Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuejun Wen","raw_affiliation_strings":["Huawei International, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Huawei International, Singapore, Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402983","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0003-1938-2902"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China","Shanghai Key Laboratory of Trustworthy Computing, ECNU, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing, ECNU, Shanghai, China","institution_ids":["https://openalex.org/I4210139618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100402983"],"corresponding_institution_ids":["https://openalex.org/I116953780","https://openalex.org/I4210139618"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":8.2241,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.98092525,"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":"193","last_page":"218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9997000098228455,"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":0.9997000098228455,"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/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":0.989799976348877,"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/computer-science","display_name":"Computer science","score":0.819858968257904},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7991071939468384},{"id":"https://openalex.org/keywords/counterexample","display_name":"Counterexample","score":0.6534027457237244},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.6120241284370422},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5536599159240723},{"id":"https://openalex.org/keywords/formal-verification","display_name":"Formal verification","score":0.5025894641876221},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5000863075256348},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.49703720211982727},{"id":"https://openalex.org/keywords/model-checking","display_name":"Model checking","score":0.49335137009620667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4905778765678406},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.4676278233528137},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34660935401916504},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.29157838225364685},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.23585820198059082},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18717855215072632}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819858968257904},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7991071939468384},{"id":"https://openalex.org/C162838799","wikidata":"https://www.wikidata.org/wiki/Q596077","display_name":"Counterexample","level":2,"score":0.6534027457237244},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.6120241284370422},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5536599159240723},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.5025894641876221},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5000863075256348},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.49703720211982727},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.49335137009620667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4905778765678406},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.4676278233528137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34660935401916504},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29157838225364685},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.23585820198059082},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18717855215072632},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-13185-1_10","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-13185-1_10","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-13185-1_10.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:10.1007/978-3-031-13185-1_10","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-13185-1_10","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-13185-1_10.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":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2273800250","display_name":null,"funder_award_id":"NSFC-","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2530119350","display_name":null,"funder_award_id":"20DZ1100300","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G2981938667","display_name":null,"funder_award_id":"Shenzhen","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4676315439","display_name":null,"funder_award_id":", NSFC-","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5306782587","display_name":null,"funder_award_id":"202005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5676270524","display_name":null,"funder_award_id":"2020AAA0107800","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6956063465","display_name":null,"funder_award_id":"62161146001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7058271836","display_name":null,"funder_award_id":"20DZ1100300","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7068220248","display_name":null,"funder_award_id":"3420/21","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/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320321950","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4290087551.pdf","grobid_xml":"https://content.openalex.org/works/W4290087551.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1485969965","https://openalex.org/W1498432697","https://openalex.org/W1862398452","https://openalex.org/W1994348879","https://openalex.org/W2004306067","https://openalex.org/W2072887965","https://openalex.org/W2145339207","https://openalex.org/W2156051490","https://openalex.org/W2158395308","https://openalex.org/W2173248099","https://openalex.org/W2201570790","https://openalex.org/W2295244175","https://openalex.org/W2344321026","https://openalex.org/W2345092165","https://openalex.org/W2463627759","https://openalex.org/W2754517384","https://openalex.org/W2787908307","https://openalex.org/W2900153411","https://openalex.org/W2912640545","https://openalex.org/W2938701611","https://openalex.org/W2953466973","https://openalex.org/W2962692913","https://openalex.org/W2963847595","https://openalex.org/W2966735560","https://openalex.org/W2967595108","https://openalex.org/W2980176594","https://openalex.org/W2980603164","https://openalex.org/W3003257820","https://openalex.org/W3034442282","https://openalex.org/W3043284412","https://openalex.org/W3082528606","https://openalex.org/W3091798065","https://openalex.org/W3104371626","https://openalex.org/W3124237877","https://openalex.org/W3165816975","https://openalex.org/W3184441520","https://openalex.org/W3185438801","https://openalex.org/W3209881631","https://openalex.org/W3212787291","https://openalex.org/W4242599275","https://openalex.org/W6600175266","https://openalex.org/W6600339963","https://openalex.org/W6602430163","https://openalex.org/W6603115210","https://openalex.org/W6637967152"],"related_works":["https://openalex.org/W2953113086","https://openalex.org/W1552191998","https://openalex.org/W2056825861","https://openalex.org/W2765989158","https://openalex.org/W2952737788","https://openalex.org/W4226455345","https://openalex.org/W2006962382","https://openalex.org/W2149716943","https://openalex.org/W2037121848","https://openalex.org/W4312733571"],"abstract_inverted_index":{"Abstract":[0],"Deep":[1],"Reinforcement":[2],"Learning":[3],"(DRL)":[4],"has":[5,40],"demonstrated":[6],"its":[7],"strength":[8],"in":[9],"developing":[10,102],"intelligent":[11],"systems.":[12,174],"These":[13],"systems":[14,45,105,186],"shall":[15],"be":[16,20],"formally":[17,49],"guaranteed":[18],"to":[19,24,48,52],"trustworthy":[21],"when":[22],"applied":[23],"safety-critical":[25],"domains,":[26],"which":[27],"is":[28,151],"typically":[29],"achieved":[30],"by":[31,107],"formal":[32],"verification":[33,131],"performed":[34],"after":[35],"training.":[36],"This":[37],"train-then-verify":[38],"process":[39,150],"two":[41],"limits:":[42],"(i)":[43],"trained":[44,161],"are":[46,157],"difficult":[47],"verify":[50],"due":[51],"their":[53],"continuous":[54],"and":[55,59,69,82,87,110,141,198],"infinite":[56],"state":[57,128],"space":[58],"inexplicable":[60],"AI":[61],"components":[62],"(":[63],"i.e.":[64],",":[65],"deep":[66],"neural":[67],"networks),":[68],"(ii)":[70],"the":[71,80,135,145,160,165],"ex":[72],"post":[73],"facto":[74],"detection":[75],"of":[76,85,122,167],"bugs":[77],"increases":[78],"both":[79],"time-":[81],"money-wise":[83],"cost":[84],"training":[86,97],"deployment.":[88],"In":[89],"this":[90],"paper,":[91],"we":[92,133],"propose":[93],"a":[94,115,119],"novel":[95],"verification-in-the-loop":[96],"framework":[98,169,181],"called":[99],"Trainify":[100,113],"for":[101],"safe":[103],"DRL":[104,116,185,202],"driven":[106],"counterexample-guided":[108],"abstraction":[109,136],"refinement.":[111],"Specifically,":[112],"trains":[114],"system":[117,192],"on":[118,138,144,170],"finite":[120],"set":[121],"coarsely":[123],"abstracted":[124],"but":[125],"efficiently":[126],"verifiable":[127],"spaces.":[129],"When":[130],"fails,":[132],"refine":[134],"based":[137],"returned":[139],"counterexamples":[140],"train":[142],"again":[143],"finer":[146],"abstract":[147],"states.":[148],"The":[149,175],"iterated":[152],"until":[153],"all":[154],"predefined":[155],"properties":[156],"verified":[158],"against":[159],"system.":[162],"We":[163],"demonstrate":[164],"effectiveness":[166],"our":[168,180],"six":[171],"classic":[172],"control":[173],"experimental":[176],"results":[177],"show":[178],"that":[179],"yields":[182],"more":[183],"reliable":[184],"with":[187],"provable":[188],"guarantees":[189],"without":[190],"sacrificing":[191],"performance":[193],"such":[194],"as":[195],"cumulative":[196],"reward":[197],"robustness":[199],"than":[200],"conventional":[201],"approaches.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}