{"id":"https://openalex.org/W2108519123","doi":"https://doi.org/10.1145/1015330.1015346","title":"Utile distinction hidden Markov models","display_name":"Utile distinction hidden Markov models","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2108519123","doi":"https://doi.org/10.1145/1015330.1015346","mag":"2108519123"},"language":"en","primary_location":{"id":"doi:10.1145/1015330.1015346","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twenty-first international conference on Machine learning  - ICML '04","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/node?id=1292332","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053990531","display_name":"Daan Wierstra","orcid":null},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Daan Wierstra","raw_affiliation_strings":["Utrecht University, The Netherlands","Utrecht Universitythe Netherlands"],"affiliations":[{"raw_affiliation_string":"Utrecht University, The Netherlands","institution_ids":["https://openalex.org/I193662353"]},{"raw_affiliation_string":"Utrecht Universitythe Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060596453","display_name":"Marco Wiering","orcid":"https://orcid.org/0000-0003-4331-7537"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marco Wiering","raw_affiliation_strings":["Utrecht University, The Netherlands","Utrecht Universitythe Netherlands"],"affiliations":[{"raw_affiliation_string":"Utrecht University, The Netherlands","institution_ids":["https://openalex.org/I193662353"]},{"raw_affiliation_string":"Utrecht Universitythe Netherlands","institution_ids":["https://openalex.org/I193662353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053990531"],"corresponding_institution_ids":["https://openalex.org/I193662353"],"apc_list":null,"apc_paid":null,"fwci":1.8485,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.87926901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"108","last_page":"108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9933000206947327,"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":0.9915000200271606,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8032042980194092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7138264775276184},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.6814212799072266},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6183519959449768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6099945902824402},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.5569964051246643},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5547277331352234},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5407043099403381},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5369311571121216},{"id":"https://openalex.org/keywords/hidden-semi-markov-model","display_name":"Hidden semi-Markov model","score":0.5244677066802979},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5123604536056519},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5041037797927856},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49204131960868835},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.4793294668197632},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4668349027633667},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.4468039572238922},{"id":"https://openalex.org/keywords/forward-algorithm","display_name":"Forward algorithm","score":0.4120102524757385},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4002543091773987},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18291988968849182}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8032042980194092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7138264775276184},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.6814212799072266},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6183519959449768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6099945902824402},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.5569964051246643},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5547277331352234},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5407043099403381},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5369311571121216},{"id":"https://openalex.org/C64939953","wikidata":"https://www.wikidata.org/wiki/Q3859882","display_name":"Hidden semi-Markov model","level":5,"score":0.5244677066802979},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5123604536056519},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5041037797927856},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49204131960868835},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.4793294668197632},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4668349027633667},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.4468039572238922},{"id":"https://openalex.org/C196455857","wikidata":"https://www.wikidata.org/wiki/Q5473264","display_name":"Forward algorithm","level":5,"score":0.4120102524757385},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4002543091773987},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18291988968849182},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1015330.1015346","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twenty-first international conference on Machine learning  - ICML '04","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.712.3169","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.712.3169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ai.rug.nl/%7Emwiering/GROUP/ARTICLES/udhmm.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.79.2708","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.79.2708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uu.nl/people/marco/GROUP/ARTICLES/udhmm.ps.gz","raw_type":"text"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1292332","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1292332","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:uu:oai:dspace.library.uu.nl:1874/20839","is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/20839","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Twenty-first International Conference on Machine Learning (ICML'04), 855. ACM Press","raw_type":"info:eu-repo/semantics/bookpart"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1292332","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1292332","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W6242441","https://openalex.org/W1176136657","https://openalex.org/W1499371387","https://openalex.org/W1515851193","https://openalex.org/W1539216098","https://openalex.org/W1555801537","https://openalex.org/W1570690983","https://openalex.org/W1583380718","https://openalex.org/W1657674574","https://openalex.org/W2052117683","https://openalex.org/W2107726111","https://openalex.org/W2121863487","https://openalex.org/W2125838338","https://openalex.org/W2161523118","https://openalex.org/W4214717370","https://openalex.org/W4253365321","https://openalex.org/W4253573210"],"related_works":["https://openalex.org/W2382132287","https://openalex.org/W2161328464","https://openalex.org/W1615861041","https://openalex.org/W4302561434","https://openalex.org/W3142992254","https://openalex.org/W1510894296","https://openalex.org/W2379333870","https://openalex.org/W2183072182","https://openalex.org/W2379938888","https://openalex.org/W1840407238"],"abstract_inverted_index":{"This":[0,61],"paper":[1],"addresses":[2],"the":[3,40,88],"problem":[4,124],"of":[5,20,39,73,90,115],"constructing":[6],"good":[7,128],"action":[8],"selection":[9],"policies":[10],"for":[11,44],"agents":[12],"acting":[13],"in":[14,57,93,121],"partially":[15],"observable":[16],"environments,":[17],"a":[18,32,37,46,58],"class":[19],"problems":[21],"generally":[22],"known":[23],"as":[24],"Partially":[25],"Observable":[26],"Markov":[27,48,84],"Decision":[28],"Processes.":[29],"We":[30],"present":[31],"novel":[33],"approach":[34],"that":[35,94],"uses":[36],"modification":[38],"well-known":[41],"Baum-Welch":[42],"algorithm":[43],"learning":[45],"Hidden":[47,83],"Model":[49],"(HMM)":[50],"to":[51,65,97],"predict":[52],"both":[53],"percepts":[54],"and":[55,76,100],"utility":[56,101],"non-deterministic":[59],"world.":[60],"enables":[62],"an":[63],"agent":[64],"make":[66],"decisions":[67],"based":[68,112],"on":[69,113],"its":[70],"previous":[71],"history":[72],"actions,":[74],"observations,":[75],"rewards.":[77],"Our":[78],"algorithm,":[79],"called":[80],"Utile":[81],"Distinction":[82],"Models":[85],"(UDHMM),":[86],"handles":[87],"creation":[89],"memory":[91],"well":[92],"it":[95,107],"tends":[96],"create":[98],"perceptual":[99],"distinctions":[102],"only":[103],"when":[104],"needed,":[105],"while":[106],"can":[108],"still":[109],"discriminate":[110],"states":[111],"histories":[114],"arbitrary":[116],"length.":[117],"The":[118],"experimental":[119],"results":[120],"highly":[122],"stochastic":[123],"domains":[125],"show":[126],"very":[127],"performance.":[129]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}