{"id":"https://openalex.org/W4313016741","doi":"https://doi.org/10.1109/iros47612.2022.9981759","title":"Accelerated Reinforcement Learning for Temporal Logic Control Objectives","display_name":"Accelerated Reinforcement Learning for Temporal Logic Control Objectives","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4313016741","doi":"https://doi.org/10.1109/iros47612.2022.9981759"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981759","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5014874021","display_name":"Yiannis Kantaros","orcid":"https://orcid.org/0000-0002-0257-7378"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yiannis Kantaros","raw_affiliation_strings":["Washington University in St. Louis,Department of Electrical and Systems Engineering,St. Louis,MO,USA,63130"],"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis,Department of Electrical and Systems Engineering,St. Louis,MO,USA,63130","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5014874021"],"corresponding_institution_ids":["https://openalex.org/I204465549"],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.68519716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5077","last_page":"5082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10142","display_name":"Formal Methods in Verification","score":0.991100013256073,"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/T12288","display_name":"Optimization and Search Problems","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8523286581039429},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"Linear temporal logic","score":0.7566972970962524},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7507033944129944},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6853354573249817},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6788415312767029},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.627812385559082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.556690514087677},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5379740595817566},{"id":"https://openalex.org/keywords/workspace","display_name":"Workspace","score":0.4883803725242615},{"id":"https://openalex.org/keywords/learning-automata","display_name":"Learning automata","score":0.4360790550708771},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43227332830429077},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4279574155807495},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4274590313434601},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.39672306180000305},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.31786346435546875},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.31579411029815674},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.16209059953689575},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10782113671302795},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09896618127822876}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8523286581039429},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.7566972970962524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507033944129944},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6853354573249817},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6788415312767029},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.627812385559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.556690514087677},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5379740595817566},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.4883803725242615},{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.4360790550708771},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43227332830429077},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4279574155807495},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4274590313434601},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.39672306180000305},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.31786346435546875},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.31579411029815674},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.16209059953689575},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10782113671302795},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09896618127822876},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981759","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W1498432697","https://openalex.org/W1989315746","https://openalex.org/W2107726111","https://openalex.org/W2124623089","https://openalex.org/W2226453522","https://openalex.org/W2334782222","https://openalex.org/W2554009248","https://openalex.org/W2736666525","https://openalex.org/W2767313115","https://openalex.org/W2895196950","https://openalex.org/W2931553127","https://openalex.org/W2953302092","https://openalex.org/W3011250830","https://openalex.org/W3014472602","https://openalex.org/W3021964239","https://openalex.org/W3026873144","https://openalex.org/W3090827750","https://openalex.org/W3092156990","https://openalex.org/W3176904019","https://openalex.org/W3206858608","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4220923746","https://openalex.org/W4221157983","https://openalex.org/W4287017924","https://openalex.org/W4288372726","https://openalex.org/W6738568706","https://openalex.org/W6745497480","https://openalex.org/W6752298494","https://openalex.org/W6760985608","https://openalex.org/W6775686349","https://openalex.org/W6786111744","https://openalex.org/W6797705063","https://openalex.org/W6800089562","https://openalex.org/W6810361831","https://openalex.org/W7075680496"],"related_works":["https://openalex.org/W2124110813","https://openalex.org/W3021103820","https://openalex.org/W2763487042","https://openalex.org/W2521108391","https://openalex.org/W2031188261","https://openalex.org/W4285022830","https://openalex.org/W4232446061","https://openalex.org/W2077520193","https://openalex.org/W1513400763","https://openalex.org/W2032651852"],"abstract_inverted_index":{"This":[0,116],"paper":[1],"addresses":[2],"the":[3,37,41,57,125,143,147],"problem":[4],"of":[5,43,59,93,124,146],"learning":[6,83,94],"control":[7,44,47,53,88,95],"policies":[8,96],"for":[9,86,154],"mobile":[10],"robots,":[11],"modeled":[12],"as":[13,27,65,128,130],"unknown":[14],"Markov":[15],"Decision":[16],"Processes":[17],"(MDPs),":[18],"that":[19,55,90,110,141],"are":[20],"tasked":[21],"with":[22],"temporal":[23],"logic":[24],"missions,":[25],"such":[26],"sequencing,":[28],"coverage,":[29],"or":[30],"surveillance.":[31],"The":[32,46],"MDP":[33,134],"captures":[34],"uncertainty":[35],"in":[36],"workspace":[38],"structure":[39],"and":[40],"outcomes":[42],"decisions.":[45],"objective":[48],"is":[49,91,117],"to":[50,113],"synthesize":[51],"a":[52,61,66,78,131],"policy":[54],"maximizes":[56],"probability":[58],"accomplishing":[60],"high-level":[62],"task,":[63],"specified":[64],"Linear":[67],"Temporal":[68],"Logic":[69],"(LTL)":[70],"formula.":[71],"To":[72],"address":[73],"this":[74],"problem,":[75],"we":[76,137],"propose":[77],"novel":[79],"accelerated":[80],"model-based":[81],"reinforcement":[82],"(RL)":[84],"algorithm":[85],"LTL":[87,126,155],"objectives":[89],"capable":[92],"significantly":[97],"faster":[98],"than":[99],"related":[100],"approaches.":[101],"Its":[102],"sample-efficiency":[103],"relies":[104],"on":[105],"biasing":[106],"exploration":[107],"towards":[108],"directions":[109],"may":[111],"contribute":[112],"task":[114,127],"satisfaction.":[115],"accomplished":[118],"by":[119],"leveraging":[120],"an":[121],"automaton":[122],"representation":[123],"well":[129],"continuously":[132],"learned":[133],"model.":[135],"Finally,":[136],"provide":[138],"comparative":[139],"experiments":[140],"demonstrate":[142],"sample":[144],"efficiency":[145],"proposed":[148],"method":[149],"against":[150],"recent":[151],"RL":[152],"methods":[153],"objectives.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}