{"id":"https://openalex.org/W2524638160","doi":"https://doi.org/10.1109/cdc.2016.7799279","title":"Q-Learning for robust satisfaction of signal temporal logic specifications","display_name":"Q-Learning for robust satisfaction of signal temporal logic specifications","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2524638160","doi":"https://doi.org/10.1109/cdc.2016.7799279","mag":"2524638160"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2016.7799279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7799279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th 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/A5053550436","display_name":"Derya Aksaray","orcid":"https://orcid.org/0000-0003-4236-9116"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Derya Aksaray","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103266699","display_name":"Austin Jones","orcid":"https://orcid.org/0000-0003-0680-1477"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin Jones","raw_affiliation_strings":["Departments of Mechanical Engineering and Electrical Engineering, Georgia Institute of Technology, Atlanta, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Mechanical Engineering and Electrical Engineering, Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017663923","display_name":"Zhaodan Kong","orcid":"https://orcid.org/0000-0002-2493-1366"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaodan Kong","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of California Davis, Davis, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of California Davis, Davis, CA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081950488","display_name":"Mac Schwager","orcid":"https://orcid.org/0000-0002-7871-3663"},"institutions":[{"id":"https://openalex.org/I13805885","display_name":"Vaughn College of Aeronautics and Technology","ror":"https://ror.org/056e22e24","country_code":"US","type":"education","lineage":["https://openalex.org/I13805885"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mac Schwager","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Stanford University, Stanford, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I13805885","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086742095","display_name":"C\u0103lin Belta","orcid":"https://orcid.org/0000-0002-7141-2657"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calin Belta","raw_affiliation_strings":["Department of Mechanical Engineering, Boston University, Boston, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Boston University, Boston, MA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053550436"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":12.6162,"has_fulltext":false,"cited_by_count":160,"citation_normalized_percentile":{"value":0.98777908,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6565","last_page":"6570"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9965000152587891,"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":0.9965000152587891,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9850999712944031,"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":0.9611999988555908,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8132418990135193},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6933796405792236},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.654205322265625},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4656800627708435},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4454364776611328},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.43298307061195374},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.40786927938461304},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35571151971817017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32732659578323364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2270519733428955}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8132418990135193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6933796405792236},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.654205322265625},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4656800627708435},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4454364776611328},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.43298307061195374},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40786927938461304},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35571151971817017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32732659578323364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2270519733428955},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc.2016.7799279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7799279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:open.bu.edu:2144/29722","is_oa":false,"landing_page_url":"http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000400048106123&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=6e74115fe3da270499c3d65c9b17d654","pdf_url":null,"source":{"id":"https://openalex.org/S4306402183","display_name":"OpenBU/Boston University Institutional Repository (Boston University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I111088046","host_organization_name":"Boston University","host_organization_lineage":["https://openalex.org/I111088046"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference materials"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W141481420","https://openalex.org/W189973795","https://openalex.org/W1498432697","https://openalex.org/W1533557569","https://openalex.org/W1544022704","https://openalex.org/W1553647006","https://openalex.org/W1556387789","https://openalex.org/W1802858671","https://openalex.org/W1975219867","https://openalex.org/W2044223164","https://openalex.org/W2049399166","https://openalex.org/W2059470663","https://openalex.org/W2078151802","https://openalex.org/W2092884371","https://openalex.org/W2103931555","https://openalex.org/W2126147754","https://openalex.org/W2147750403","https://openalex.org/W2416117881","https://openalex.org/W2468777797","https://openalex.org/W2474788619","https://openalex.org/W2524638160","https://openalex.org/W2953302092","https://openalex.org/W4233696721","https://openalex.org/W6721299877"],"related_works":["https://openalex.org/W2315999538","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W1567439243","https://openalex.org/W4255368532","https://openalex.org/W1993731165","https://openalex.org/W2095860056","https://openalex.org/W2742871814","https://openalex.org/W2802778578","https://openalex.org/W2134216493"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,33,42,53,61,66,75,93,98,109,140,144,150],"problem":[4],"of":[5,37,63,77,96,100,113,123,149],"learning":[6],"optimal":[7],"policies":[8,141],"for":[9,139],"satisfying":[10],"signal":[11],"temporal":[12],"logic":[13],"(STL)":[14],"specifications":[15],"by":[16,59,143],"agents":[17],"with":[18],"unknown":[19],"stochastic":[20],"dynamics.":[21],"The":[22,147],"system":[23],"is":[24,57,83,153],"modeled":[25],"as":[26],"a":[27,38,72],"Markov":[28],"decision":[29],"process,":[30],"in":[31,108],"which":[32],"states":[34],"represent":[35],"partitions":[36],"continuous":[39],"space":[40],"and":[41,65,102,133],"transition":[43],"probabilities":[44],"are":[45,106],"unknown.":[46],"We":[47,79],"formulate":[48],"two":[49],"synthesis":[50,125],"problems":[51,89,126],"where":[52],"desired":[54],"STL":[55,124],"specification":[56],"enforced":[58],"maximizing":[60],"probability":[62,99],"satisfaction,":[64],"expected":[67,103],"robustness":[68,104],"degree,":[69],"that":[70,81,127],"is,":[71],"measure":[73],"quantifying":[74],"quality":[76],"satisfaction.":[78],"discuss":[80],"Q-learning":[82],"not":[84,107],"directly":[85],"applicable":[86],"to":[87],"these":[88],"because,":[90],"based":[91],"on":[92],"quantitative":[94],"semantics":[95],"STL,":[97],"satisfaction":[101],"degree":[105],"standard":[110],"objective":[111],"form":[112],"Q-learning.":[114],"To":[115],"resolve":[116],"this":[117],"issue,":[118],"we":[119,134],"propose":[120],"an":[121],"approximation":[122],"can":[128],"be":[129],"solved":[130],"via":[131,155],"Q-learning,":[132],"derive":[135],"some":[136],"performance":[137,148],"bounds":[138],"obtained":[142],"approximate":[145],"approach.":[146],"proposed":[151],"method":[152],"demonstrated":[154],"simulations.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":2}],"updated_date":"2026-05-14T08:36:36.166977","created_date":"2025-10-10T00:00:00"}