{"id":"https://openalex.org/W2966537673","doi":"https://doi.org/10.24963/ijcai.2019/840","title":"LTL and Beyond: Formal Languages for Reward Function Specification in Reinforcement Learning","display_name":"LTL and Beyond: Formal Languages for Reward Function Specification in Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2966537673","doi":"https://doi.org/10.24963/ijcai.2019/840","mag":"2966537673"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/840","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/840","pdf_url":"https://www.ijcai.org/proceedings/2019/0840.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0840.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001444744","display_name":"Alberto Rivas","orcid":"https://orcid.org/0000-0002-9558-9895"},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Alberto Camacho","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Canada","Vector Institute, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Vector Institute, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006732213","display_name":"Rodrigo Toro Icarte","orcid":"https://orcid.org/0000-0002-7734-099X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rodrigo Toro Icarte","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Canada","Vector Institute, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Vector Institute, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008606761","display_name":"Toryn Q. Klassen","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Toryn Q. Klassen","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055185956","display_name":"Richard Valenzano","orcid":"https://orcid.org/0000-0001-5954-7869"},"institutions":[{"id":"https://openalex.org/I4210123574","display_name":"Centre for Social Innovation","ror":"https://ror.org/03trz9s27","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210123574"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Richard Valenzano","raw_affiliation_strings":["Element AI, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Element AI, Toronto, Canada","institution_ids":["https://openalex.org/I4210123574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041982650","display_name":"Sheila A. McIlraith","orcid":"https://orcid.org/0000-0003-4953-0945"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sheila A. McIlraith","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Canada","Vector Institute, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Vector Institute, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001444744"],"corresponding_institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4210127509"],"apc_list":null,"apc_paid":null,"fwci":17.1968,"has_fulltext":false,"cited_by_count":148,"citation_normalized_percentile":{"value":0.99438742,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6065","last_page":"6073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9922000169754028,"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"}},{"id":"https://openalex.org/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.9900000095367432,"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":0.9031413793563843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7446142435073853},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6686267256736755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5796125531196594},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.5270314812660217},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5184051990509033},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.44275885820388794},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44010427594184875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36972522735595703},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07061794400215149}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9031413793563843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7446142435073853},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6686267256736755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5796125531196594},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.5270314812660217},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5184051990509033},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.44275885820388794},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44010427594184875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36972522735595703},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07061794400215149},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/840","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/840","pdf_url":"https://www.ijcai.org/proceedings/2019/0840.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/840","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/840","pdf_url":"https://www.ijcai.org/proceedings/2019/0840.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8284766523","display_name":null,"funder_award_id":"(NSERC)","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G907567576","display_name":null,"funder_award_id":"Becas","funder_id":"https://openalex.org/F4320334812","funder_display_name":"Comisi\u00f3n Nacional de Investigaci\u00f3n Cient\u00edfica y Tecnol\u00f3gica"}],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320334812","display_name":"Comisi\u00f3n Nacional de Investigaci\u00f3n Cient\u00edfica y Tecnol\u00f3gica","ror":"https://ror.org/02ap3w078"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2966537673.pdf","grobid_xml":"https://content.openalex.org/works/W2966537673.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1262127546","https://openalex.org/W1504504841","https://openalex.org/W1562936359","https://openalex.org/W1612453857","https://openalex.org/W1700264732","https://openalex.org/W1761635979","https://openalex.org/W1777239053","https://openalex.org/W2075773711","https://openalex.org/W2133180954","https://openalex.org/W2145339207","https://openalex.org/W2201581102","https://openalex.org/W2406423292","https://openalex.org/W2734058336","https://openalex.org/W2746553466","https://openalex.org/W2789027502","https://openalex.org/W2804948070","https://openalex.org/W2808386811","https://openalex.org/W2890192685","https://openalex.org/W2963149920","https://openalex.org/W3150132563","https://openalex.org/W4297669644","https://openalex.org/W4302339081"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370"],"abstract_inverted_index":{"In":[0],"Reinforcement":[1],"Learning":[2],"(RL),":[3],"an":[4],"agent":[5],"is":[6],"guided":[7],"by":[8,112,152],"the":[9,14,24,91,102,106,125],"rewards":[10],"it":[11,18,32],"receives":[12],"from":[13,28],"reward":[15,38,48,57,66,73,95,107,118],"function.":[16],"Unfortunately,":[17],"may":[19],"take":[20],"many":[21],"interactions":[22],"with":[23],"environment":[25],"to":[26,36,123],"learn":[27],"sparse":[29],"rewards,":[30],"and":[31,80,116],"can":[33,84,109],"be":[34,85,110,150],"challenging":[35],"specify":[37],"functions":[39],"that":[40,55,134,146],"reflect":[41],"complex":[42,94],"reward-worthy":[43],"behavior.":[44],"We":[45,68,98],"propose":[46],"using":[47],"machines":[49],"(RMs),":[50],"which":[51],"are":[52],"automata-based":[53],"representations":[54],"expose":[56],"function":[58,96,108],"structure,":[59],"as":[60],"a":[61],"normal":[62],"form":[63],"representation":[64],"for":[65],"functions.":[67],"show":[69,100,133],"how":[70,101],"specifications":[71],"of":[72,93,105,128],"in":[74,121],"various":[75],"formal":[76],"languages,":[77,83],"including":[78],"LTL":[79],"other":[81],"regular":[82],"automatically":[86],"translated":[87],"into":[88],"RMs,":[89],"easing":[90],"burden":[92],"specification.":[97],"then":[99],"exposed":[103],"structure":[104],"exploited":[111],"tailored":[113],"q-learning":[114],"algorithms":[115],"automated":[117],"shaping":[119],"techniques":[120,137],"order":[122],"improve":[124],"sample":[126],"efficiency":[127],"reinforcement":[129],"learning":[130],"methods.":[131],"Experiments":[132],"these":[135],"RM-tailored":[136],"significantly":[138],"outperform":[139],"state-of-the-art":[140],"(deep)":[141],"RL":[142],"algorithms,":[143],"solving":[144],"problems":[145],"otherwise":[147],"cannot":[148],"reasonably":[149],"solved":[151],"existing":[153],"approaches.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}