{"id":"https://openalex.org/W4387172171","doi":"https://doi.org/10.3233/faia230247","title":"Learning Task Automata for Reinforcement Learning Using Hidden Markov Models","display_name":"Learning Task Automata for Reinforcement Learning Using Hidden Markov Models","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387172171","doi":"https://doi.org/10.3233/faia230247"},"language":"en","primary_location":{"id":"doi:10.3233/faia230247","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230247","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230247","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230247","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091718585","display_name":"Alessandro Abate","orcid":"https://orcid.org/0000-0002-5627-9093"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alessandro Abate","raw_affiliation_strings":["University of Oxford, aabate@cs.ox.ac.uk, james.fox@cs.ox.ac.uk, david.hyland@cs.ox.ac.uk, mjw@cs.ox.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, aabate@cs.ox.ac.uk, james.fox@cs.ox.ac.uk, david.hyland@cs.ox.ac.uk, mjw@cs.ox.ac.uk","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020881081","display_name":"Yousif Almulla","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Yousif Almulla","raw_affiliation_strings":["Microsoft Azure Quantum, yalmulla@microsoft.com","University of Oxford, aabate@cs.ox.ac.uk, james.fox@cs.ox.ac.uk, david.hyland@cs.ox.ac.uk, mjw@cs.ox.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Azure Quantum, yalmulla@microsoft.com","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"University of Oxford, aabate@cs.ox.ac.uk, james.fox@cs.ox.ac.uk, david.hyland@cs.ox.ac.uk, mjw@cs.ox.ac.uk","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091000235","display_name":"James Fox","orcid":"https://orcid.org/0000-0003-1485-2995"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Fox","raw_affiliation_strings":["University of Oxford, aabate@cs.ox.ac.uk, james.fox@cs.ox.ac.uk, david.hyland@cs.ox.ac.uk, mjw@cs.ox.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, aabate@cs.ox.ac.uk, james.fox@cs.ox.ac.uk, david.hyland@cs.ox.ac.uk, mjw@cs.ox.ac.uk","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114255781","display_name":"David C. Hyland","orcid":"https://orcid.org/0000-0001-9726-3509"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Hyland","raw_affiliation_strings":["University of Oxford, aabate@cs.ox.ac.uk, james.fox@cs.ox.ac.uk, david.hyland@cs.ox.ac.uk, mjw@cs.ox.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, aabate@cs.ox.ac.uk, james.fox@cs.ox.ac.uk, david.hyland@cs.ox.ac.uk, mjw@cs.ox.ac.uk","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065393757","display_name":"Michael Wooldridge","orcid":"https://orcid.org/0000-0002-9329-8410"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael Wooldridge","raw_affiliation_strings":["University of Oxford, aabate@cs.ox.ac.uk, james.fox@cs.ox.ac.uk, david.hyland@cs.ox.ac.uk, mjw@cs.ox.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, aabate@cs.ox.ac.uk, james.fox@cs.ox.ac.uk, david.hyland@cs.ox.ac.uk, mjw@cs.ox.ac.uk","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8076,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87184896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9927999973297119,"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"}},"topics":[{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9927999973297119,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9919999837875366,"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":0.9822999835014343,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8151645660400391},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7478460073471069},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.7221192121505737},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.599315881729126},{"id":"https://openalex.org/keywords/learning-automata","display_name":"Learning automata","score":0.5450353026390076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4729345142841339},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.46355167031288147},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4558119475841522},{"id":"https://openalex.org/keywords/finite-state-machine","display_name":"Finite-state machine","score":0.45173180103302},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.44974732398986816},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.41738513112068176},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.41159674525260925},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3339345455169678},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26034241914749146},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13371652364730835}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8151645660400391},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7478460073471069},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.7221192121505737},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.599315881729126},{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.5450353026390076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4729345142841339},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.46355167031288147},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4558119475841522},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.45173180103302},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.44974732398986816},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41738513112068176},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.41159674525260925},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3339345455169678},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26034241914749146},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13371652364730835},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230247","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230247","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230247","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230247","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230247","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230247","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387172171.pdf","grobid_xml":"https://content.openalex.org/works/W4387172171.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W259536784","https://openalex.org/W1498432697","https://openalex.org/W1825640910","https://openalex.org/W1976268573","https://openalex.org/W1989445634","https://openalex.org/W2007321142","https://openalex.org/W2017603160","https://openalex.org/W2044811734","https://openalex.org/W2054801208","https://openalex.org/W2076343783","https://openalex.org/W2098774185","https://openalex.org/W2122493035","https://openalex.org/W2125838338","https://openalex.org/W2133180954","https://openalex.org/W2164114810","https://openalex.org/W2285691875","https://openalex.org/W2462906003","https://openalex.org/W2605514557","https://openalex.org/W2798588334","https://openalex.org/W2887933419","https://openalex.org/W2953708620","https://openalex.org/W2964326464","https://openalex.org/W2970673985","https://openalex.org/W2972500268","https://openalex.org/W2990130865","https://openalex.org/W2993025150","https://openalex.org/W2997022832","https://openalex.org/W3009415314","https://openalex.org/W3035701987","https://openalex.org/W3037924899","https://openalex.org/W3083905601","https://openalex.org/W3088974622","https://openalex.org/W3092156990","https://openalex.org/W3129150792","https://openalex.org/W3139531864","https://openalex.org/W3175871729","https://openalex.org/W3197209873","https://openalex.org/W4212875940","https://openalex.org/W4224995922","https://openalex.org/W4253573210","https://openalex.org/W4281688128","https://openalex.org/W4283821610","https://openalex.org/W4293328180","https://openalex.org/W4294578500","https://openalex.org/W4297948695","https://openalex.org/W4312701204","https://openalex.org/W4312844584","https://openalex.org/W4387172171"],"related_works":["https://openalex.org/W2489338148","https://openalex.org/W2124961391","https://openalex.org/W127357700","https://openalex.org/W2724597727","https://openalex.org/W1480528870","https://openalex.org/W2508541108","https://openalex.org/W4243191745","https://openalex.org/W2315419748","https://openalex.org/W576785828","https://openalex.org/W1545451257"],"abstract_inverted_index":{"Training":[0],"reinforcement":[1],"learning":[2,85],"(RL)":[3],"agents":[4],"using":[5],"scalar":[6],"reward":[7,23],"signals":[8],"is":[9,27,129,161],"often":[10],"infeasible":[11],"when":[12],"an":[13,117,123,131],"environment":[14],"has":[15],"sparse":[16],"and":[17,64,79],"non-Markovian":[18,33],"rewards.":[19],"Moreover,":[20],"handcrafting":[21],"these":[22],"functions":[24],"before":[25],"training":[26],"prone":[28],"to":[29,95,111],"misspecification.":[30],"We":[31],"learn":[32,53],"finite":[34,99],"task":[35,92,110,136],"specifications":[36],"as":[37,74],"finite-state":[38],"\u2018task":[39],"automata\u2019":[40],"from":[41,101],"episodes":[42],"of":[43,60,134],"agent":[44,119],"experience":[45],"within":[46],"environments":[47],"with":[48],"unknown":[49],"dynamics.":[50],"First,":[51],"we":[52,88,152],"a":[54,57,75,81,97,109,139],"product":[55,104],"MDP,":[56],"model":[58,84],"composed":[59],"the":[61,65,91,102,144,159],"specification\u2019s":[62],"automaton":[63,93,107,160],"environment\u2019s":[66],"MDP":[67,78],"(both":[68],"initially":[69],"unknown),":[70],"by":[71],"treating":[72],"it":[73,164],"partially":[76],"observable":[77],"employing":[80],"hidden":[82],"Markov":[83],"algorithm.":[86],"Second,":[87],"efficiently":[89],"distil":[90],"(assumed":[94],"be":[96,112],"deterministic":[98],"automaton)":[100],"learnt":[103,146],"MDP.":[105],"Our":[106],"enables":[108],"decomposed":[113],"into":[114],"sub-tasks,":[115],"so":[116,138],"RL":[118],"can":[120,141],"later":[121],"synthesise":[122],"optimal":[124],"policy":[125],"more":[126],"efficiently.":[127],"It":[128],"also":[130,153],"interpretable":[132],"encoding":[133],"high-level":[135],"features,":[137],"human":[140],"verify":[142],"that":[143,158],"agent\u2019s":[145],"tasks":[147],"have":[148],"no":[149],"misspecifications.":[150],"Finally,":[151],"take":[154],"steps":[155],"towards":[156],"ensuring":[157],"environment-agnostic,":[162],"making":[163],"well-suited":[165],"for":[166],"use":[167],"in":[168],"transfer":[169],"learning.":[170]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}