{"id":"https://openalex.org/W3113192171","doi":"https://doi.org/10.1109/smc42975.2020.9282929","title":"A Reinforcement Learning Approach to Design Verification Strategies of Engineered Systems","display_name":"A Reinforcement Learning Approach to Design Verification Strategies of Engineered Systems","publication_year":2020,"publication_date":"2020-10-11","ids":{"openalex":"https://openalex.org/W3113192171","doi":"https://doi.org/10.1109/smc42975.2020.9282929","mag":"3113192171"},"language":"en","primary_location":{"id":"doi:10.1109/smc42975.2020.9282929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9282929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5027980821","display_name":"Peng Xu","orcid":"https://orcid.org/0000-0002-7323-6394"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng Xu","raw_affiliation_strings":["Virginia Tech Blacksburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088616769","display_name":"Alejandro Salado","orcid":"https://orcid.org/0000-0001-9378-0795"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alejandro Salado","raw_affiliation_strings":["Virginia Tech Blacksburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035006590","display_name":"Guangrui Xie","orcid":"https://orcid.org/0000-0001-6338-1427"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guangrui Xie","raw_affiliation_strings":["Virginia Tech Blacksburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":1.5905,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85114933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3543","last_page":"3550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9663000106811523,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.9624999761581421,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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":0.8504105806350708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7880172729492188},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7129048705101013},{"id":"https://openalex.org/keywords/functional-verification","display_name":"Functional verification","score":0.5239670276641846},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5152402520179749},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4894203245639801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46180835366249084},{"id":"https://openalex.org/keywords/formal-verification","display_name":"Formal verification","score":0.46124523878097534},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45971229672431946},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4508504569530487},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4499828815460205},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4285617470741272},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.41240835189819336},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.34302616119384766},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.29016777873039246},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1978306770324707},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0916225016117096}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8504105806350708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7880172729492188},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7129048705101013},{"id":"https://openalex.org/C62460635","wikidata":"https://www.wikidata.org/wiki/Q5508853","display_name":"Functional verification","level":3,"score":0.5239670276641846},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5152402520179749},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4894203245639801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46180835366249084},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.46124523878097534},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45971229672431946},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4508504569530487},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4499828815460205},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4285617470741272},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.41240835189819336},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34302616119384766},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29016777873039246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1978306770324707},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0916225016117096},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc42975.2020.9282929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9282929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1496395723","https://openalex.org/W1511986666","https://openalex.org/W1584456573","https://openalex.org/W1601081659","https://openalex.org/W1654016072","https://openalex.org/W1861050369","https://openalex.org/W2096630263","https://openalex.org/W2101927907","https://openalex.org/W2121863487","https://openalex.org/W2137766593","https://openalex.org/W2145339207","https://openalex.org/W2159080219","https://openalex.org/W2318485605","https://openalex.org/W2485292563","https://openalex.org/W2487144912","https://openalex.org/W2520654854","https://openalex.org/W2606788990","https://openalex.org/W2766447205","https://openalex.org/W2888003435","https://openalex.org/W2902098903","https://openalex.org/W2903482397","https://openalex.org/W2921907362","https://openalex.org/W2976012116","https://openalex.org/W3011120880","https://openalex.org/W4237591687","https://openalex.org/W6680313055","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W4308702637","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2156021013","https://openalex.org/W2903299703","https://openalex.org/W2016648086","https://openalex.org/W2808418668","https://openalex.org/W75359960","https://openalex.org/W3120172095"],"abstract_inverted_index":{"System":[0],"verification":[1,30,37,49,59,73],"is":[2,24,52,81,119,132,156,162,181],"a":[3,48,103,111,122,129,140,146,159],"critical":[4],"process":[5,125],"in":[6,15,78,89,127,164],"the":[7,16,20,33,40,70,90,96,115,150,153,175,185,188],"development":[8,43],"of":[9,19,36,72,95,187],"engineered":[10],"systems.":[11],"Engineers":[12],"gain":[13],"confidence":[14],"correct":[17],"functionality":[18],"system":[21,42],"before":[22],"it":[23],"deployed":[25],"into":[26],"operation":[27],"by":[28],"executing":[29],"activities.":[31],"Choosing":[32],"right":[34,41],"set":[35],"activities":[38],"at":[39],"stage,":[44],"that":[45,161],"is,":[46],"designing":[47],"strategy":[50],"(VS),":[51],"essential":[53],"to":[54,68,84,108,144,183],"balancing":[55],"information":[56],"discovery":[57],"and":[58,139],"cost.":[60],"Only":[61],"recently,":[62],"quantitative":[63],"methods":[64],"have":[65],"been":[66],"proposed":[67,189],"support":[69],"design":[71,117,145],"strategies.":[74],"However,":[75],"their":[76,85],"applicability":[77],"real-life":[79],"scenarios":[80],"impractical":[82],"due":[83],"limited":[86],"computational":[87],"efficiency":[88],"high":[91],"dimensional":[92],"solution":[93],"space":[94],"VS":[97,116,170],"selection":[98],"problem.":[99],"This":[100],"paper":[101],"presents":[102],"reinforcement":[104],"learning":[105],"(RL)":[106],"approach":[107],"search":[109,138],"for":[110],"near-optimal":[112,169],"VS.":[113],"Specifically,":[114],"problem":[118],"formulated":[120],"as":[121,158],"Markov":[123],"decision":[124],"(MDP)":[126],"which":[128],"value":[130,154],"function":[131,155],"required.":[133],"Then":[134],"we":[135],"combine":[136],"tree":[137],"neural":[141],"network":[142],"(NN)":[143],"RL":[147,151],"algorithm.":[148],"In":[149],"algorithm,":[152],"approximated":[157],"NN":[160],"trained":[163,176],"an":[165],"iterative":[166],"way.":[167],"The":[168],"can":[171],"be":[172],"generated":[173],"from":[174],"NN.":[177],"A":[178],"case":[179],"study":[180],"presented":[182],"show":[184],"superiority":[186],"method.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}