{"id":"https://openalex.org/W3093240915","doi":"https://doi.org/10.1109/icra48506.2021.9561903","title":"Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfaction","display_name":"Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfaction","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3093240915","doi":"https://doi.org/10.1109/icra48506.2021.9561903","mag":"3093240915"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/2010.06797","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001420415","display_name":"Mingyu Cai","orcid":"https://orcid.org/0000-0002-2967-2703"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mingyu Cai","raw_affiliation_strings":["Department of Mechanical Engineering, The University of Iowa, Iowa City, IA, USA","The University of Iowa Department of Mechanical Engineering Iowa City, IA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, The University of Iowa, Iowa City, IA, USA","institution_ids":["https://openalex.org/I126307644"]},{"raw_affiliation_string":"The University of Iowa Department of Mechanical Engineering Iowa City, IA, USA","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025292957","display_name":"Shaoping Xiao","orcid":"https://orcid.org/0000-0001-9658-7149"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaoping Xiao","raw_affiliation_strings":["Department of Mechanical Engineering, The University of Iowa, Iowa City, IA, USA","The University of Iowa Department of Mechanical Engineering Iowa City, IA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, The University of Iowa, Iowa City, IA, USA","institution_ids":["https://openalex.org/I126307644"]},{"raw_affiliation_string":"The University of Iowa Department of Mechanical Engineering Iowa City, IA, USA","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010421547","display_name":"Baoluo Li","orcid":"https://orcid.org/0000-0002-5796-0550"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoluo Li","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China","University of Science and technology of China,Department of Automation,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and technology of China,Department of Automation,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103009727","display_name":"Zhiliang Li","orcid":"https://orcid.org/0000-0003-4528-1830"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiliang Li","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China","University of Science and technology of China,Department of Automation,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and technology of China,Department of Automation,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018344952","display_name":"Zhen Kan","orcid":"https://orcid.org/0000-0003-2069-9544"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Kan","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China","University of Science and technology of China,Department of Automation,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and technology of China,Department of Automation,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001420415"],"corresponding_institution_ids":["https://openalex.org/I126307644"],"apc_list":null,"apc_paid":null,"fwci":0.1515,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47109394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"806","last_page":"812"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9990000128746033,"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":0.9990000128746033,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.989799976348877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8451194763183594},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6980633735656738},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6872802376747131},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6445714831352234},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"Linear temporal logic","score":0.5873852372169495},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5016937255859375},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.47609269618988037},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.47054368257522583},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.39563482999801636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3944089114665985},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.366895854473114},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3006579577922821},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2596934139728546},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23915359377861023}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8451194763183594},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6980633735656738},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6872802376747131},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6445714831352234},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.5873852372169495},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5016937255859375},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.47609269618988037},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.47054368257522583},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.39563482999801636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3944089114665985},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.366895854473114},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3006579577922821},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2596934139728546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23915359377861023},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9561903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.06797","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.06797","pdf_url":"https://arxiv.org/pdf/2010.06797","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:3093240915","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.06797.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.2010.06797","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.06797","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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.06797","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.06797","pdf_url":"https://arxiv.org/pdf/2010.06797","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":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1494502909","https://openalex.org/W1498432697","https://openalex.org/W1792768639","https://openalex.org/W2059470663","https://openalex.org/W2078151802","https://openalex.org/W2487186542","https://openalex.org/W2489939061","https://openalex.org/W2620827312","https://openalex.org/W2624912704","https://openalex.org/W2804948070","https://openalex.org/W2892537867","https://openalex.org/W2895196950","https://openalex.org/W2914702425","https://openalex.org/W2931553127","https://openalex.org/W2951796861","https://openalex.org/W2953302092","https://openalex.org/W2963778636","https://openalex.org/W2966537673","https://openalex.org/W2978782407","https://openalex.org/W2995074243","https://openalex.org/W2999973955","https://openalex.org/W3011250830","https://openalex.org/W3014472602","https://openalex.org/W3021964239","https://openalex.org/W3039276491","https://openalex.org/W3045306771","https://openalex.org/W3045834210","https://openalex.org/W3090827750","https://openalex.org/W3098613855","https://openalex.org/W3175871729","https://openalex.org/W6752298494","https://openalex.org/W6759275947","https://openalex.org/W6775686349","https://openalex.org/W6781508003","https://openalex.org/W6784388912"],"related_works":["https://openalex.org/W3206858608","https://openalex.org/W3090827750","https://openalex.org/W3126786011","https://openalex.org/W2972744417","https://openalex.org/W3195923140","https://openalex.org/W3039276491","https://openalex.org/W3126402318","https://openalex.org/W3141484263","https://openalex.org/W2964131705","https://openalex.org/W2248015474","https://openalex.org/W2938272992","https://openalex.org/W2059470663","https://openalex.org/W3095977506","https://openalex.org/W3161194236","https://openalex.org/W3045834210","https://openalex.org/W2058327921","https://openalex.org/W2236968622","https://openalex.org/W3201878770","https://openalex.org/W3026873144","https://openalex.org/W1482467703"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,11,46,68,99],"model-free":[4,170],"reinforcement":[5],"learning":[6],"(RL)":[7],"algorithm":[8],"to":[9,32,67,79,91,121,155,160,177],"synthesize":[10],"control":[12,190],"policy":[13,159,181],"that":[14,140],"maximizes":[15],"the":[16,33,42,105,117,123,145,150,157,162,166,179,188],"satisfaction":[17,163],"probability":[18,164],"of":[19,35,87,107,111,116,125,149,165,187],"complex":[20],"tasks,":[21],"which":[22,103,143],"are":[23],"expressed":[24],"by":[25,97],"linear":[26],"temporal":[27],"logic":[28],"(LTL)":[29],"specifications.":[30,168],"Due":[31],"consideration":[34],"environment":[36],"and":[37,57,134,196],"motion":[38,44,172],"uncertainties,":[39],"we":[40],"model":[41],"robot":[43],"as":[45],"probabilistic":[47,58],"labeled":[48],"Markov":[49],"decision":[50],"process":[51],"(PL-MDP)":[52],"with":[53,75],"unknown":[54],"transition":[55],"probabilities":[56],"labeling":[59],"functions.":[60],"The":[61,85,185],"LTL":[62,167],"task":[63],"specification":[64],"is":[65,90,153,175,192],"converted":[66],"limit":[69],"deterministic":[70],"generalized":[71],"B\u00fcchi":[72],"automaton":[73],"(LDGBA)":[74],"several":[76],"accepting":[77,109],"sets":[78,110],"maintain":[80],"dense":[81],"rewards":[82],"during":[83],"learning.":[84],"novelty":[86],"applying":[88,127],"LDGBA":[89,95,112],"construct":[92],"an":[93],"embedded":[94],"(E-LDGBA)":[96],"designing":[98],"synchronous":[100],"tracking-frontier":[101],"function,":[102],"enables":[104],"record":[106],"non-visited":[108],"at":[113],"each":[114],"round":[115],"repeated":[118],"visiting":[119],"pattern,":[120],"overcome":[122],"difficulties":[124],"directly":[126],"conventional":[128],"LDGBA.":[129],"With":[130],"appropriate":[131],"dependent":[132],"reward":[133],"discount":[135,147],"functions,":[136],"rigorous":[137],"analysis":[138],"shows":[139],"any":[141],"method,":[142],"optimizes":[144],"expected":[146],"return":[148],"RL-based":[151,171,189],"approach,":[152],"guaranteed":[154],"find":[156],"optimal":[158,180],"maximize":[161],"A":[169],"planning":[173],"strategy":[174],"developed":[176],"generate":[178],"in":[182],"this":[183],"paper.":[184],"effectiveness":[186],"synthesis":[191],"demonstrated":[193],"via":[194],"simulation":[195],"experimental":[197],"results.":[198]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}