{"id":"https://openalex.org/W2972744417","doi":"https://doi.org/10.1109/cdc40024.2019.9028919","title":"Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees","display_name":"Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2972744417","doi":"https://doi.org/10.1109/cdc40024.2019.9028919","mag":"2972744417"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9028919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9028919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1909.05304","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085342880","display_name":"Mohammadhosein Hasanbeig","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"M. Hasanbeig","raw_affiliation_strings":["Department of Computer Science, University of Oxford, UK","University of Oxford"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014874021","display_name":"Yiannis Kantaros","orcid":"https://orcid.org/0000-0002-0257-7378"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Y. Kantaros","raw_affiliation_strings":["Department of Computer Science, University of Oxford, UK","University of Oxford"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091718585","display_name":"Alessandro Abate","orcid":"https://orcid.org/0000-0002-5627-9093"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"A. Abate","raw_affiliation_strings":["Department of Computer Science, University of Oxford, UK","University of Oxford"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086206346","display_name":"Daniel Kroening","orcid":"https://orcid.org/0000-0002-6681-5283"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"D. Kroening","raw_affiliation_strings":["Department of Computer Science, University of Oxford, UK","#N#               * University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029243115","display_name":"George J. Pappas","orcid":"https://orcid.org/0000-0001-9081-0637"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"G. J. Pappas","raw_affiliation_strings":["Department of Computer Science, University of Oxford, UK","#N#               * University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030456600","display_name":"Insup Lee","orcid":"https://orcid.org/0000-0003-2672-1132"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I. Lee","raw_affiliation_strings":["School of Engineering and Applied Science (SEAS), University of Pennsylvania, PA, USA","#N#               * University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Science (SEAS), University of Pennsylvania, PA, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5085342880"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":1.397,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83850932,"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":"5338","last_page":"5343"},"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9825000166893005,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8115675449371338},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7894742488861084},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"Linear temporal logic","score":0.662138819694519},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6614307761192322},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6233416795730591},{"id":"https://openalex.org/keywords/workspace","display_name":"Workspace","score":0.5303576588630676},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5190606713294983},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.5090067386627197},{"id":"https://openalex.org/keywords/b\u00fcchi-automaton","display_name":"B\u00fcchi automaton","score":0.5041455030441284},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4230797290802002},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.41874751448631287},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.37585973739624023},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.3437000513076782},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3413015902042389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2707134485244751},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2504264712333679},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.1706465482711792},{"id":"https://openalex.org/keywords/deterministic-automaton","display_name":"Deterministic automaton","score":0.08896595239639282}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8115675449371338},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7894742488861084},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.662138819694519},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6614307761192322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6233416795730591},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.5303576588630676},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5190606713294983},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.5090067386627197},{"id":"https://openalex.org/C165753454","wikidata":"https://www.wikidata.org/wiki/Q1020380","display_name":"B\u00fcchi automaton","level":4,"score":0.5041455030441284},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4230797290802002},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.41874751448631287},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37585973739624023},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.3437000513076782},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3413015902042389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2707134485244751},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2504264712333679},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.1706465482711792},{"id":"https://openalex.org/C194525867","wikidata":"https://www.wikidata.org/wiki/Q5265707","display_name":"Deterministic automaton","level":3,"score":0.08896595239639282},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cdc40024.2019.9028919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9028919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1909.05304","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.05304","pdf_url":"https://arxiv.org/pdf/1909.05304","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2972744417","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1909.05304.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1909.05304","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1909.05304","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1909.05304","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.05304","pdf_url":"https://arxiv.org/pdf/1909.05304","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972744417.pdf","grobid_xml":"https://content.openalex.org/works/W2972744417.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W16586245","https://openalex.org/W1494502909","https://openalex.org/W1498432697","https://openalex.org/W1556387789","https://openalex.org/W1862398452","https://openalex.org/W1943821960","https://openalex.org/W1970269621","https://openalex.org/W1977444293","https://openalex.org/W1993112505","https://openalex.org/W2023808162","https://openalex.org/W2030712766","https://openalex.org/W2059470663","https://openalex.org/W2078151802","https://openalex.org/W2080813827","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2134312936","https://openalex.org/W2157807654","https://openalex.org/W2178626170","https://openalex.org/W2487186542","https://openalex.org/W2521432080","https://openalex.org/W2554009248","https://openalex.org/W2620827312","https://openalex.org/W2624912704","https://openalex.org/W2784931892","https://openalex.org/W2787908307","https://openalex.org/W2798588334","https://openalex.org/W2912757393","https://openalex.org/W2931553127","https://openalex.org/W2950370525","https://openalex.org/W2953302092","https://openalex.org/W2962941388","https://openalex.org/W2963117388","https://openalex.org/W2963778636","https://openalex.org/W2963907727","https://openalex.org/W3104303413","https://openalex.org/W6638944184","https://openalex.org/W6751051826","https://openalex.org/W6755007425","https://openalex.org/W6755307484"],"related_works":["https://openalex.org/W3011250830","https://openalex.org/W3206858608","https://openalex.org/W2972520119","https://openalex.org/W2248015474","https://openalex.org/W2953302092","https://openalex.org/W3195923140","https://openalex.org/W3126786011","https://openalex.org/W2059470663","https://openalex.org/W3141484263","https://openalex.org/W3039276491","https://openalex.org/W2963778636","https://openalex.org/W3161194236","https://openalex.org/W2951966745","https://openalex.org/W2949183857","https://openalex.org/W2964131705","https://openalex.org/W3201878770","https://openalex.org/W3126402318","https://openalex.org/W2938272992","https://openalex.org/W3008651843","https://openalex.org/W1433129784"],"abstract_inverted_index":{"We":[0,69,124],"present":[1],"a":[2,46,65,76,96,116],"model-free":[3],"reinforcement":[4],"learning":[5],"algorithm":[6,114],"to":[7,45],"synthesize":[8],"control":[9,18],"policies":[10],"that":[11,111,118,128],"maximize":[12],"the":[13,31,34,37,40,72,91,102,106,112,120,130,133],"probability":[14,122],"of":[15,36,105,132],"satisfying":[16],"high-level":[17],"objectives":[19],"given":[20],"as":[21],"Linear":[22],"Temporal":[23],"Logic":[24],"(LTL)":[25],"formulas.":[26],"Uncertainty":[27],"is":[28,60,83],"considered":[29],"in":[30,86],"workspace":[32],"properties,":[33],"structure":[35,55],"workspace,":[38],"and":[39,56],"agent":[41],"actions,":[42],"giving":[43],"rise":[44],"Probabilistically-Labeled":[47],"Markov":[48],"Decision":[49],"Process":[50],"(PL-MDP)":[51],"with":[52,90],"unknown":[53,67],"graph":[54],"stochastic":[57],"behaviour,":[58],"which":[59,82],"even":[61],"more":[62],"general":[63],"than":[64],"fully":[66],"MDP.":[68],"first":[70],"translate":[71],"LTL":[73],"specification":[74],"into":[75],"Limit":[77],"Deterministic":[78],"B\u00fcchi":[79],"Automaton":[80],"(LDBA),":[81],"then":[84],"used":[85],"an":[87],"on-the-fly":[88],"product":[89],"PL-MDP.":[92],"Thereafter,":[93],"we":[94,109],"define":[95],"synchronous":[97],"reward":[98],"function":[99],"based":[100],"on":[101],"acceptance":[103],"condition":[104],"LDBA.":[107],"Finally,":[108],"show":[110],"RL":[113],"delivers":[115],"policy":[117],"maximizes":[119],"satisfaction":[121],"asymptotically.":[123],"provide":[125],"experimental":[126],"results":[127],"showcase":[129],"efficiency":[131],"proposed":[134],"method.":[135]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
