{"id":"https://openalex.org/W4386872349","doi":"https://doi.org/10.1109/lra.2023.3313969","title":"Reinforcement Learning of Action and Query Policies With LTL Instructions Under Uncertain Event Detector","display_name":"Reinforcement Learning of Action and Query Policies With LTL Instructions Under Uncertain Event Detector","publication_year":2023,"publication_date":"2023-09-19","ids":{"openalex":"https://openalex.org/W4386872349","doi":"https://doi.org/10.1109/lra.2023.3313969"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3313969","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lra.2023.3313969","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-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/A5036929872","display_name":"Wataru Hatanaka","orcid":"https://orcid.org/0009-0006-4030-5142"},"institutions":[{"id":"https://openalex.org/I24193003","display_name":"Ricoh (Japan)","ror":"https://ror.org/02h4myp42","country_code":"JP","type":"company","lineage":["https://openalex.org/I24193003"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wataru Hatanaka","raw_affiliation_strings":["Digital Strategy Division, RICOH Company, Ltd., Tokyo, Japan","Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan"],"raw_orcid":"https://orcid.org/0009-0006-4030-5142","affiliations":[{"raw_affiliation_string":"Digital Strategy Division, RICOH Company, Ltd., Tokyo, Japan","institution_ids":["https://openalex.org/I24193003"]},{"raw_affiliation_string":"Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065798083","display_name":"Ryota YAMASHINA","orcid":null},"institutions":[{"id":"https://openalex.org/I24193003","display_name":"Ricoh (Japan)","ror":"https://ror.org/02h4myp42","country_code":"JP","type":"company","lineage":["https://openalex.org/I24193003"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryota Yamashina","raw_affiliation_strings":["Digital Strategy Division, RICOH Company, Ltd., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Strategy Division, RICOH Company, Ltd., Tokyo, Japan","institution_ids":["https://openalex.org/I24193003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042074952","display_name":"Takamitsu Matsubara","orcid":"https://orcid.org/0000-0003-3545-4814"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takamitsu Matsubara","raw_affiliation_strings":["Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3545-4814","affiliations":[{"raw_affiliation_string":"Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4759,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69218355,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"8","issue":"11","first_page":"7010","last_page":"7017"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.9951000213623047,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9922000169754028,"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/computer-science","display_name":"Computer science","score":0.753652811050415},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6949206590652466},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6540558338165283},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5566709637641907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5492234230041504},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5395241975784302},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5202614068984985},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44254687428474426},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3554302752017975},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.24187687039375305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753652811050415},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6949206590652466},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6540558338165283},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5566709637641907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5492234230041504},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5395241975784302},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5202614068984985},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44254687428474426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3554302752017975},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.24187687039375305},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3313969","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lra.2023.3313969","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1498432697","https://openalex.org/W2023808162","https://openalex.org/W2088716439","https://openalex.org/W2141088850","https://openalex.org/W2604314403","https://openalex.org/W2736601468","https://openalex.org/W2948430169","https://openalex.org/W2966537673","https://openalex.org/W2997350486","https://openalex.org/W3011250830","https://openalex.org/W3034655091","https://openalex.org/W3045306771","https://openalex.org/W3089737863","https://openalex.org/W3098613855","https://openalex.org/W3103548289","https://openalex.org/W3130777366","https://openalex.org/W3132564992","https://openalex.org/W3176904019","https://openalex.org/W3185868470","https://openalex.org/W3205193395","https://openalex.org/W3213974477","https://openalex.org/W4287758155","https://openalex.org/W4309799447","https://openalex.org/W6638005391","https://openalex.org/W6741002519","https://openalex.org/W6752155926","https://openalex.org/W6752298494","https://openalex.org/W6762640273","https://openalex.org/W6766842884","https://openalex.org/W6780268074","https://openalex.org/W6790722625","https://openalex.org/W6800004206","https://openalex.org/W6847100305"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W4306674287","https://openalex.org/W3111983280","https://openalex.org/W4319083788"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"with":[3,81,190],"linear":[4],"temporal":[5],"logic":[6],"(LTL)":[7],"objectives":[8],"can":[9,29,102],"allow":[10],"robots":[11],"to":[12,34,64,97,110,119,161,185],"carry":[13],"out":[14],"symbolic":[15,35],"event":[16,27,43,49,67,112,165,192],"plans":[17],"in":[18,47,168],"unknown":[19],"environments.":[20],"Most":[21],"existing":[22],"methods":[23],"assume":[24],"that":[25,101,156,179],"the":[26,62,65,71,76,104,120,164],"detector":[28,50],"accurately":[30],"map":[31],"environmental":[32],"states":[33],"events;":[36],"however,":[37],"uncertainty":[38,46,77],"is":[39,135],"inevitable":[40],"for":[41,70,163],"real-world":[42],"detectors.":[44,193],"Such":[45],"an":[48,86,99,129,148],"generates":[51],"multiple":[52,136],"branching":[53,137],"possibilities":[54,138],"on":[55,139],"LTL":[56,95,107,140,187],"instructions,":[57],"confusing":[58],"action":[59,149],"decisions.":[60],"Moreover,":[61],"queries":[63],"uncertain":[66,111,191],"detector,":[68],"necessary":[69],"task's":[72],"progress,":[73],"may":[74],"increase":[75],"further.":[78],"To":[79],"cope":[80],"those":[82],"issues,":[83],"we":[84],"propose":[85],"RL":[87],"framework,":[88],"Learning":[89],"Action":[90],"and":[91,151,173],"Query":[92],"over":[93],"Belief":[94],"(LAQBL),":[96],"learn":[98],"agent":[100],"consider":[103],"diversity":[105],"of":[106,131],"instructions":[108,141,188],"due":[109,118],"detection":[113],"while":[114],"avoiding":[115],"task":[116],"failure":[117],"unnecessary":[121],"event-detection":[122],"query.":[123],"Our":[124],"framework":[125],"simultaneously":[126],"learns":[127,183],"1)":[128],"embedding":[130],"belief":[132],"LTL,":[133],"which":[134],"using":[142],"a":[143,153,169],"graph":[144],"neural":[145],"network,":[146],"2)":[147],"policy,":[150],"3)":[152],"query":[154,162],"policy":[155],"decides":[157],"whether":[158],"or":[159],"not":[160],"detector.":[166],"Simulations":[167],"2D":[170],"grid":[171],"world":[172],"image-input":[174],"robotic":[175],"inspection":[176],"environments":[177],"show":[178],"our":[180],"method":[181],"successfully":[182],"actions":[184],"follow":[186],"even":[189]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}