{"id":"https://openalex.org/W4312901059","doi":"https://doi.org/10.1109/iros47612.2022.9981874","title":"WFA-IRL: Inverse Reinforcement Learning of Autonomous Behaviors Encoded as Weighted Finite Automata","display_name":"WFA-IRL: Inverse Reinforcement Learning of Autonomous Behaviors Encoded as Weighted Finite Automata","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312901059","doi":"https://doi.org/10.1109/iros47612.2022.9981874"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981874","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/A5100417408","display_name":"Tianyu Wang","orcid":"https://orcid.org/0000-0001-6206-8359"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianyu Wang","raw_affiliation_strings":["University of California San Diego,Department of Electrical and Computer Engineering,La Jolla,CA,USA,92093"],"affiliations":[{"raw_affiliation_string":"University of California San Diego,Department of Electrical and Computer Engineering,La Jolla,CA,USA,92093","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066400889","display_name":"Nikolay Atanasov","orcid":"https://orcid.org/0000-0003-0272-7580"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolay Atanasov","raw_affiliation_strings":["University of California San Diego,Department of Electrical and Computer Engineering,La Jolla,CA,USA,92093"],"affiliations":[{"raw_affiliation_string":"University of California San Diego,Department of Electrical and Computer Engineering,La Jolla,CA,USA,92093","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100417408"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33117863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"24","issue":null,"first_page":"7429","last_page":"7435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T12288","display_name":"Optimization and Search Problems","score":0.9954000115394592,"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"}},{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9930999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7619751691818237},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7299617528915405},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7198237180709839},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7032665610313416},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.5997166037559509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5781490802764893},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.511971116065979},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5046788454055786},{"id":"https://openalex.org/keywords/finite-state-machine","display_name":"Finite-state machine","score":0.49794793128967285},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4885772168636322},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3862234354019165},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3435903489589691},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22631943225860596},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12590575218200684},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09050828218460083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619751691818237},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7299617528915405},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7198237180709839},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7032665610313416},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.5997166037559509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5781490802764893},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.511971116065979},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5046788454055786},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.49794793128967285},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4885772168636322},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3862234354019165},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3435903489589691},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22631943225860596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12590575218200684},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09050828218460083},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981874","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":0.75,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2356629721","display_name":null,"funder_award_id":"N00014-18-1-2828","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W1498432697","https://openalex.org/W1506437980","https://openalex.org/W1578332044","https://openalex.org/W1591675293","https://openalex.org/W1643571618","https://openalex.org/W1943821960","https://openalex.org/W1970269621","https://openalex.org/W1971086298","https://openalex.org/W2071797744","https://openalex.org/W2098432798","https://openalex.org/W2098774185","https://openalex.org/W2109910161","https://openalex.org/W2117675763","https://openalex.org/W2121092017","https://openalex.org/W2134312936","https://openalex.org/W2140756703","https://openalex.org/W2142641780","https://openalex.org/W2144588269","https://openalex.org/W2151958719","https://openalex.org/W2161076907","https://openalex.org/W2163941698","https://openalex.org/W2169498096","https://openalex.org/W2169528473","https://openalex.org/W2235884325","https://openalex.org/W2242407529","https://openalex.org/W2290104316","https://openalex.org/W2605016475","https://openalex.org/W2736601468","https://openalex.org/W2802897770","https://openalex.org/W2807059453","https://openalex.org/W2811472820","https://openalex.org/W2883140436","https://openalex.org/W2889713213","https://openalex.org/W2891540084","https://openalex.org/W2946892860","https://openalex.org/W2950989964","https://openalex.org/W2952854274","https://openalex.org/W2962951365","https://openalex.org/W2962994149","https://openalex.org/W2963262099","https://openalex.org/W2963277051","https://openalex.org/W2964227312","https://openalex.org/W2990750410","https://openalex.org/W3038945966","https://openalex.org/W3091379283","https://openalex.org/W3101648496","https://openalex.org/W3105174872","https://openalex.org/W3106302274","https://openalex.org/W3120742815","https://openalex.org/W4210678036","https://openalex.org/W4289145571","https://openalex.org/W4294578500","https://openalex.org/W4297795161","https://openalex.org/W4312901059","https://openalex.org/W6635261211","https://openalex.org/W6674884181","https://openalex.org/W6677555207","https://openalex.org/W6677631742","https://openalex.org/W6677939520","https://openalex.org/W6680724558","https://openalex.org/W6680939595","https://openalex.org/W6683620479","https://openalex.org/W6696380822","https://openalex.org/W6703271639","https://openalex.org/W6718092244","https://openalex.org/W6731334075","https://openalex.org/W6736050541","https://openalex.org/W6741002519","https://openalex.org/W6752871779","https://openalex.org/W6754362148","https://openalex.org/W6754484421","https://openalex.org/W6762533131","https://openalex.org/W6763210770","https://openalex.org/W6784396901","https://openalex.org/W6807484095"],"related_works":["https://openalex.org/W4242459863","https://openalex.org/W127357700","https://openalex.org/W1480528870","https://openalex.org/W2508541108","https://openalex.org/W4243191745","https://openalex.org/W2724597727","https://openalex.org/W2315419748","https://openalex.org/W1029445510","https://openalex.org/W187740018","https://openalex.org/W2072177288"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,51,57,70,80,98,131],"method":[4],"for":[5,21,75,85],"learning":[6,53,91],"logical":[7],"task":[8,33,65,77,128],"specifications":[9,16],"and":[10,24,38,79,107],"cost":[11,99],"functions":[12],"from":[13],"demonstrations.":[14],"Constructing":[15],"by":[17,45,101],"hand":[18],"is":[19,94,119],"challenging":[20],"complex":[22],"objectives":[23],"constraints":[25],"in":[26,130],"autonomous":[27,47],"systems.":[28],"Instead,":[29],"we":[30,68],"consider":[31],"demonstrated":[32],"executions,":[34],"whose":[35],"logic":[36],"structure":[37],"transition":[39],"costs":[40],"need":[41],"to":[42,55,96],"be":[43],"inferred":[44,127],"an":[46],"agent.":[48],"We":[49],"employ":[50],"spectral":[52],"approach":[54],"extract":[56],"weighted":[58],"finite":[59],"automaton":[60],"(WFA),":[61],"approximating":[62],"the":[63,73,103,111,123,126],"unknown":[64],"logic.":[66],"Thereafter,":[67],"define":[69],"product":[71],"between":[72,105],"WFA":[74],"high-level":[76],"guidance":[78],"labeled":[81],"Markov":[82],"decision":[83],"process":[84],"low-level":[86],"control.":[87],"An":[88],"inverse":[89],"reinforcement":[90],"(IRL)":[92],"problem":[93],"considered":[95],"learn":[97],"function":[100],"backpropagating":[102],"loss":[104],"agent":[106],"expert":[108],"behaviors":[109],"through":[110],"planning":[112],"algorithm.":[113],"Our":[114],"proposed":[115],"model,":[116],"termed":[117],"WFA-IRL,":[118],"capable":[120],"of":[121,125,133],"generalizing":[122],"execution":[124],"specification":[129],"suite":[132],"MiniGrid":[134],"environments.":[135]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}