{"id":"https://openalex.org/W2972520119","doi":"https://doi.org/10.1109/icra40945.2020.9196796","title":"Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning","display_name":"Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W2972520119","doi":"https://doi.org/10.1109/icra40945.2020.9196796","mag":"2972520119"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9196796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9196796","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 Robotics and Automation (ICRA)","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/1909.07299","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083621014","display_name":"Alper Kamil Bozkurt","orcid":"https://orcid.org/0000-0001-5845-4003"},"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":"Alper Kamil Bozkurt","raw_affiliation_strings":["Duke University, Durham, NC, USA","Duke University,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Duke University,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","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":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Duke University, Durham, NC, USA","Duke University,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Duke University,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080808780","display_name":"Michael M. Zavlanos","orcid":"https://orcid.org/0000-0003-1748-8228"},"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":false,"raw_author_name":"Michael M. Zavlanos","raw_affiliation_strings":["Duke University, Durham, NC, USA","Duke University,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Duke University,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086742584","display_name":"Miroslav Paji\u0107","orcid":"https://orcid.org/0000-0002-5357-0117"},"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":false,"raw_author_name":"Miroslav Pajic","raw_affiliation_strings":["Duke University, Durham, NC, USA","Duke University#TAB#"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Duke University#TAB#","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083621014"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":1.5883,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86706283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"10349","last_page":"10355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9993000030517578,"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":0.9993000030517578,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9866999983787537,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.97079998254776,"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":0.8611831665039062},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.813628613948822},{"id":"https://openalex.org/keywords/discounting","display_name":"Discounting","score":0.722815215587616},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"Linear temporal logic","score":0.6417855024337769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6304620504379272},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5390256643295288},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.49466297030448914},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4881039559841156},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.483576238155365},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4794863164424896},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4768349230289459},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4706411063671112},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4579007625579834},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43576058745384216},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.4234941005706787},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.42191070318222046},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.36349132657051086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28820136189460754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2783307433128357},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21621105074882507},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17741024494171143},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15457767248153687},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08078157901763916}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8611831665039062},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.813628613948822},{"id":"https://openalex.org/C6177178","wikidata":"https://www.wikidata.org/wiki/Q10998070","display_name":"Discounting","level":2,"score":0.722815215587616},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.6417855024337769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6304620504379272},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5390256643295288},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.49466297030448914},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4881039559841156},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.483576238155365},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4794863164424896},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4768349230289459},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4706411063671112},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4579007625579834},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43576058745384216},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.4234941005706787},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.42191070318222046},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.36349132657051086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28820136189460754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2783307433128357},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21621105074882507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17741024494171143},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15457767248153687},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08078157901763916},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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":4,"locations":[{"id":"doi:10.1109/icra40945.2020.9196796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9196796","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 Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1909.07299","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.07299","pdf_url":"https://arxiv.org/pdf/1909.07299","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:2972520119","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1909.07299","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.1909.07299","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1909.07299","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:1909.07299","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.07299","pdf_url":"https://arxiv.org/pdf/1909.07299","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":0.7400000095367432,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972520119.pdf","grobid_xml":"https://content.openalex.org/works/W2972520119.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W117911312","https://openalex.org/W1498432697","https://openalex.org/W1556387789","https://openalex.org/W1792768639","https://openalex.org/W1971086298","https://openalex.org/W2004620590","https://openalex.org/W2059470663","https://openalex.org/W2073548775","https://openalex.org/W2077578897","https://openalex.org/W2078151802","https://openalex.org/W2091682553","https://openalex.org/W2112271657","https://openalex.org/W2117927826","https://openalex.org/W2121863487","https://openalex.org/W2124339220","https://openalex.org/W2129670787","https://openalex.org/W2157807654","https://openalex.org/W2163941698","https://openalex.org/W2165131254","https://openalex.org/W2487186542","https://openalex.org/W2524638160","https://openalex.org/W2567705466","https://openalex.org/W2607319504","https://openalex.org/W2624912704","https://openalex.org/W2784931892","https://openalex.org/W2798588334","https://openalex.org/W2808386811","https://openalex.org/W2884525686","https://openalex.org/W2895196950","https://openalex.org/W2931553127","https://openalex.org/W2962806365","https://openalex.org/W2963117388","https://openalex.org/W2963190533","https://openalex.org/W2963604565","https://openalex.org/W2963778636","https://openalex.org/W2964514675","https://openalex.org/W6682124619","https://openalex.org/W6751051826","https://openalex.org/W6752155926"],"related_works":["https://openalex.org/W3090827750","https://openalex.org/W3141484263","https://openalex.org/W3206858608","https://openalex.org/W2972744417","https://openalex.org/W2953302092","https://openalex.org/W2248015474","https://openalex.org/W2059470663","https://openalex.org/W3039276491","https://openalex.org/W3126402318","https://openalex.org/W3095977506","https://openalex.org/W3183867501","https://openalex.org/W2964131705","https://openalex.org/W3195923140","https://openalex.org/W3126786011","https://openalex.org/W3201878770","https://openalex.org/W2949183857","https://openalex.org/W3208792968","https://openalex.org/W3161194236","https://openalex.org/W2236968622","https://openalex.org/W2895196950"],"abstract_inverted_index":{"We":[0,54],"present":[1],"a":[2,9,13,30,38,56,88,104],"reinforcement":[3],"learning":[4,50],"(RL)":[5],"frame-work":[6],"to":[7,100,102],"synthesize":[8],"control":[10],"policy":[11,39,72],"from":[12],"given":[14],"linear":[15],"temporal":[16],"logic":[17],"(LTL)":[18],"specification":[19],"in":[20],"an":[21,70],"unknown":[22],"stochastic":[23],"environment":[24],"that":[25,40,68],"can":[26],"be":[27],"modeled":[28],"as":[29],"Markov":[31],"Decision":[32],"Process":[33],"(MDP).":[34],"Specifically,":[35],"we":[36,107],"learn":[37],"maximizes":[41,79],"the":[42,46,51,64,74,80,109],"probability":[43],"of":[44,82,111],"satisfying":[45,83],"LTL":[47,65,84],"formula":[48,66],"without":[49],"transition":[52],"probabilities.":[53],"introduce":[55],"novel":[57],"rewarding":[58],"and":[59,86,95],"discounting":[60],"mechanism":[61],"based":[62],"on":[63,116],"such":[67,103],"(i)":[69],"optimal":[71],"maximizing":[73],"total":[75],"discounted":[76],"reward":[77],"effectively":[78],"probabilities":[81],"objectives,":[85],"(ii)":[87],"model-free":[89],"RL":[90],"algorithm":[91],"using":[92],"these":[93],"rewards":[94],"discount":[96],"factors":[97],"is":[98],"guaranteed":[99],"converge":[101],"policy.":[105],"Finally,":[106],"illustrate":[108],"applicability":[110],"our":[112],"RL-based":[113],"synthesis":[114],"approach":[115],"two":[117],"motion":[118],"planning":[119],"case":[120],"studies.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}