{"id":"https://openalex.org/W2999973955","doi":"https://doi.org/10.1109/lcsys.2020.2980552","title":"Reinforcement Learning of Control Policy for Linear Temporal Logic Specifications Using Limit-Deterministic Generalized B\u00fcchi Automata","display_name":"Reinforcement Learning of Control Policy for Linear Temporal Logic Specifications Using Limit-Deterministic Generalized B\u00fcchi Automata","publication_year":2020,"publication_date":"2020-03-13","ids":{"openalex":"https://openalex.org/W2999973955","doi":"https://doi.org/10.1109/lcsys.2020.2980552","mag":"2999973955"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2020.2980552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2020.2980552","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Control Systems Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.04669","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023077795","display_name":"Ryohei Oura","orcid":"https://orcid.org/0000-0001-9864-4506"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryohei Oura","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University, Toyonaka, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9864-4506","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Toyonaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071519227","display_name":"Ami Sakakibara","orcid":"https://orcid.org/0000-0001-7997-1237"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ami Sakakibara","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University, Toyonaka, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7997-1237","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Toyonaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046686505","display_name":"Toshimitsu Ushio","orcid":"https://orcid.org/0000-0002-4009-270X"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshimitsu Ushio","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University, Toyonaka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4009-270X","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Toyonaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":null,"apc_paid":null,"fwci":2.6245,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.91663043,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"4","issue":"3","first_page":"761","last_page":"766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9865000247955322,"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":0.9858999848365784,"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":0.772742748260498},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7397346496582031},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.6530171632766724},{"id":"https://openalex.org/keywords/b\u00fcchi-automaton","display_name":"B\u00fcchi automaton","score":0.6091427803039551},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.5939257740974426},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"Linear temporal logic","score":0.5654890537261963},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5415636897087097},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5401446223258972},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5245200395584106},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4814828634262085},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.46571969985961914},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.44551798701286316},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43660610914230347},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.425353467464447},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.42472442984580994},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4118039309978485},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4109839200973511},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27646806836128235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26247870922088623},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2534939646720886},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08319705724716187},{"id":"https://openalex.org/keywords/deterministic-automaton","display_name":"Deterministic automaton","score":0.08267444372177124}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.772742748260498},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7397346496582031},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.6530171632766724},{"id":"https://openalex.org/C165753454","wikidata":"https://www.wikidata.org/wiki/Q1020380","display_name":"B\u00fcchi automaton","level":4,"score":0.6091427803039551},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.5939257740974426},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.5654890537261963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5415636897087097},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5401446223258972},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5245200395584106},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4814828634262085},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.46571969985961914},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.44551798701286316},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43660610914230347},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.425353467464447},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.42472442984580994},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4118039309978485},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4109839200973511},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27646806836128235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26247870922088623},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2534939646720886},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08319705724716187},{"id":"https://openalex.org/C194525867","wikidata":"https://www.wikidata.org/wiki/Q5265707","display_name":"Deterministic automaton","level":3,"score":0.08267444372177124},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lcsys.2020.2980552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2020.2980552","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Control Systems Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2001.04669","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.04669","pdf_url":"https://arxiv.org/pdf/2001.04669","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.04669","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.04669","pdf_url":"https://arxiv.org/pdf/2001.04669","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","id":"https://metadata.un.org/sdg/16","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G3503112064","display_name":null,"funder_award_id":"JP19J13487","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6803372825","display_name":"\u30cf\u30a4\u30d6\u30ea\u30c3\u30c9\u4ed5\u69d8\u3092\u7528\u3044\u305f\uff23\uff30\uff33\u306e\u5f62\u5f0f\u7684\u5236\u5fa1\u7cfb\u8a2d\u8a08","funder_award_id":"19J13487","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1494502909","https://openalex.org/W1498432697","https://openalex.org/W2026615297","https://openalex.org/W2078151802","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2150339816","https://openalex.org/W2334782222","https://openalex.org/W2487186542","https://openalex.org/W2594675090","https://openalex.org/W2784931892","https://openalex.org/W2798588334","https://openalex.org/W2895196950","https://openalex.org/W2931553127","https://openalex.org/W2972520119","https://openalex.org/W2972744417","https://openalex.org/W2995074243","https://openalex.org/W3011250830","https://openalex.org/W3026026050","https://openalex.org/W3090827750","https://openalex.org/W6751051826","https://openalex.org/W6767883789"],"related_works":["https://openalex.org/W2108751562","https://openalex.org/W2110468917","https://openalex.org/W1513159096","https://openalex.org/W2338673411","https://openalex.org/W1604890813","https://openalex.org/W2359102888","https://openalex.org/W1967076997","https://openalex.org/W2283260145","https://openalex.org/W1986033227","https://openalex.org/W1988027993"],"abstract_inverted_index":{"This":[0],"letter":[1],"proposes":[2],"a":[3,12,16,21,35,45,80,94,115],"novel":[4],"reinforcement":[5],"learning":[6],"method":[7,140],"for":[8,114],"the":[9,29,42,61,72,83,87,130,138,147],"synthesis":[10],"of":[11,82,118,122],"control":[13,17],"policy":[14,145],"satisfying":[15,60],"specification":[18,43],"described":[19],"by":[20,34],"linear":[22],"temporal":[23],"logic":[24],"formula.":[25,62],"We":[26,40,78,135],"assume":[27],"that":[28,55,68,109,137],"controlled":[30],"system":[31],"is":[32,65,124,150],"modeled":[33],"Markov":[36],"decision":[37],"process":[38],"(MDP).":[39],"convert":[41],"to":[44,75,153],"limit-deterministic":[46],"generalized":[47],"B\u00fcchi":[48],"automaton":[49],"(LDGBA)":[50],"with":[51],"several":[52],"accepting":[53,76,107,131],"sets":[54,132],"accepts":[56],"all":[57],"infinite":[58],"sequences":[59],"The":[63,97],"LDGBA":[64,85],"augmented":[66,84],"so":[67],"it":[69],"explicitly":[70],"records":[71],"previous":[73],"visits":[74],"sets.":[77],"take":[79],"product":[81],"and":[86,126],"MDP,":[88],"based":[89],"on":[90],"which":[91],"we":[92],"define":[93],"reward":[95],"function.":[96],"agent":[98],"gets":[99],"rewards":[100,123],"whenever":[101],"state":[102],"transitions":[103],"are":[104,133],"in":[105],"an":[106,143],"set":[108],"has":[110],"not":[111],"been":[112],"visited":[113],"certain":[116],"number":[117],"steps.":[119],"Consequently,":[120],"sparsity":[121],"relaxed":[125],"optimal":[127,144],"circulations":[128],"among":[129],"learned.":[134],"show":[136],"proposed":[139],"can":[141],"learn":[142],"when":[146],"discount":[148],"factor":[149],"sufficiently":[151],"close":[152],"one.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}