{"id":"https://openalex.org/W3119337186","doi":"https://doi.org/10.1109/cdc42340.2020.9303982","title":"Statistically Model Checking PCTL Specifications on Markov Decision Processes via Reinforcement Learning","display_name":"Statistically Model Checking PCTL Specifications on Markov Decision Processes via Reinforcement Learning","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3119337186","doi":"https://doi.org/10.1109/cdc42340.2020.9303982","mag":"3119337186"},"language":"en","primary_location":{"id":"doi:10.1109/cdc42340.2020.9303982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9303982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-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/A5100445144","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0002-0431-1039"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Duke University, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058817216","display_name":"Nima Roohi","orcid":"https://orcid.org/0000-0003-2025-0528"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima Roohi","raw_affiliation_strings":["University of California, San Diego, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001110474","display_name":"Matthew West","orcid":"https://orcid.org/0000-0002-7605-0050"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew West","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076852218","display_name":"Mahesh Viswanathan","orcid":"https://orcid.org/0000-0001-7977-0080"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahesh Viswanathan","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061952552","display_name":"Geir E. Dullerud","orcid":"https://orcid.org/0000-0003-0596-6050"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geir E. Dullerud","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100445144"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":0.8443,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79886539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9915000200271606,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9901000261306763,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7157477140426636},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7087833881378174},{"id":"https://openalex.org/keywords/probabilistic-ctl","display_name":"Probabilistic CTL","score":0.6649445295333862},{"id":"https://openalex.org/keywords/model-checking","display_name":"Model checking","score":0.6440545916557312},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.600102961063385},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.5864869952201843},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5782777070999146},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4449140429496765},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.4137660562992096},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.38772204518318176},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3694397211074829},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3391290009021759},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32074981927871704},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24476119875907898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2230607569217682},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2183840572834015},{"id":"https://openalex.org/keywords/probabilistic-analysis-of-algorithms","display_name":"Probabilistic analysis of algorithms","score":0.18072572350502014}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7157477140426636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7087833881378174},{"id":"https://openalex.org/C52063229","wikidata":"https://www.wikidata.org/wiki/Q7246845","display_name":"Probabilistic CTL","level":4,"score":0.6649445295333862},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.6440545916557312},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.600102961063385},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.5864869952201843},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5782777070999146},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4449140429496765},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4137660562992096},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.38772204518318176},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3694397211074829},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3391290009021759},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32074981927871704},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24476119875907898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2230607569217682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2183840572834015},{"id":"https://openalex.org/C24404364","wikidata":"https://www.wikidata.org/wiki/Q7246846","display_name":"Probabilistic analysis of algorithms","level":3,"score":0.18072572350502014},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc42340.2020.9303982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9303982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1498432697","https://openalex.org/W1533572394","https://openalex.org/W1556387789","https://openalex.org/W1792768639","https://openalex.org/W1862398452","https://openalex.org/W1963943927","https://openalex.org/W1993536119","https://openalex.org/W2071797744","https://openalex.org/W2073384958","https://openalex.org/W2097452095","https://openalex.org/W2121863487","https://openalex.org/W2141881497","https://openalex.org/W2236968622","https://openalex.org/W2405166594","https://openalex.org/W2567705466","https://openalex.org/W2605514557","https://openalex.org/W2784743256","https://openalex.org/W2787596386","https://openalex.org/W2788909595","https://openalex.org/W2889125056","https://openalex.org/W2895196950","https://openalex.org/W2899427426","https://openalex.org/W2912640545","https://openalex.org/W2943876157","https://openalex.org/W2950929549","https://openalex.org/W2962806365","https://openalex.org/W2963778636","https://openalex.org/W2965020757","https://openalex.org/W2965290738","https://openalex.org/W2971096715","https://openalex.org/W3011250830","https://openalex.org/W3090827750","https://openalex.org/W3105134387","https://openalex.org/W4211221179","https://openalex.org/W6682124619","https://openalex.org/W6689927692","https://openalex.org/W6735993290","https://openalex.org/W6748255240"],"related_works":["https://openalex.org/W2884574904","https://openalex.org/W2168246878","https://openalex.org/W4213436577","https://openalex.org/W4214926706","https://openalex.org/W2403555318","https://openalex.org/W2753578936","https://openalex.org/W925418074","https://openalex.org/W187740018","https://openalex.org/W2087152645","https://openalex.org/W2162286586"],"abstract_inverted_index":{"Probabilistic":[0],"Computation":[1],"Tree":[2],"Logic":[3],"(PCTL)":[4],"is":[5,54],"frequently":[6],"used":[7],"to":[8,63,96,110],"formally":[9],"specify":[10],"control":[11],"objectives":[12],"such":[13,45,66],"as":[14],"probabilistic":[15],"reachability":[16],"and":[17,73,105,124],"safety.":[18],"In":[19],"this":[20,108],"work,":[21],"we":[22,89,132],"focus":[23],"on":[24,30,85],"model":[25,78],"checking":[26,38,79,120],"PCTL":[27,71,103,122],"specifications":[28,112],"statistically":[29],"Markov":[31],"Decision":[32],"Processes":[33],"(MDPs)":[34],"by":[35,113,119,137],"sampling,":[36],"e.g.,":[37],"whether":[39],"there":[40],"exists":[41],"a":[42,57,67,76,115],"feasible":[43,68],"policy":[44,69],"that":[46],"the":[47,121,128,134],"probability":[48],"of":[49],"reaching":[50],"certain":[51],"goal":[52],"states":[53],"greater":[55],"than":[56],"threshold.":[58],"We":[59],"use":[60,91],"reinforcement":[61],"learning":[62],"search":[64],"for":[65,70,101],"specifications,":[72,104],"then":[74,106],"develop":[75],"statistical":[77],"(SMC)":[80],"method":[81,136],"with":[82],"provable":[83],"guarantees":[84],"its":[86,125],"error.":[87],"Specifically,":[88],"first":[90],"upper-confidence-bound":[92],"(UCB)":[93],"based":[94],"Q-learning":[95],"design":[97],"an":[98],"SMC":[99],"algorithm":[100,109],"bounded-time":[102],"extend":[107],"unbounded-time":[111],"identifying":[114],"proper":[116],"truncation":[117],"time":[118],"specification":[123],"negation":[126],"at":[127],"same":[129],"time.":[130],"Finally,":[131],"evaluate":[133],"proposed":[135],"case":[138],"studies.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}