{"id":"https://openalex.org/W1987974668","doi":"https://doi.org/10.1145/1143844.1143861","title":"Learning predictive state representations using non-blind policies","display_name":"Learning predictive state representations using non-blind policies","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W1987974668","doi":"https://doi.org/10.1145/1143844.1143861","mag":"1987974668"},"language":"en","primary_location":{"id":"doi:10.1145/1143844.1143861","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning  - ICML '06","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/A5081163135","display_name":"Michael Bowling","orcid":"https://orcid.org/0000-0003-2960-8418"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Michael Bowling","raw_affiliation_strings":["University of Alberta, Edmonton, Alberta., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Alberta., Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031588369","display_name":"Peter McCracken","orcid":"https://orcid.org/0000-0002-0145-4253"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Peter McCracken","raw_affiliation_strings":["University of Alberta, Edmonton, Alberta., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Alberta., Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Michael James","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael James","raw_affiliation_strings":["Toyota Technical Center, Ann Arbor, Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technical Center, Ann Arbor, Michigan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079219017","display_name":"James Neufeld","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"James Neufeld","raw_affiliation_strings":["University of Alberta, Edmonton, Alberta., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Alberta., Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014163352","display_name":"Dana Wilkinson","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dana Wilkinson","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, CANADA","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.935,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.98247677,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"129","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9746999740600586,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9714000225067139,"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/computer-science","display_name":"Computer science","score":0.6772165894508362},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5744136571884155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4772327244281769},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4007168412208557},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1219465434551239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6772165894508362},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5744136571884155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4772327244281769},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4007168412208557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1219465434551239}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1143844.1143861","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning  - ICML '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.3432","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.3432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://imls.engr.oregonstate.edu/www/htdocs/proceedings/icml2006/017_Learning_Predictive.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1540337045","https://openalex.org/W2042830238","https://openalex.org/W2058853801","https://openalex.org/W2086386133","https://openalex.org/W2123542217","https://openalex.org/W2154384352","https://openalex.org/W2158282517","https://openalex.org/W2166610875"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3209574120","https://openalex.org/W3107602296","https://openalex.org/W4312192474","https://openalex.org/W4210805261","https://openalex.org/W4387297750"],"abstract_inverted_index":{"Predictive":[0],"state":[1,21],"representations":[2],"(PSRs)":[3],"are":[4,62,127],"powerful":[5],"models":[6,15],"of":[7,27,43,65,76,88,134,146],"non-Markovian":[8],"decision":[9],"processes":[10],"that":[11,51],"differ":[12],"from":[13,36],"traditional":[14],"(e.g.,":[16],"HMMs,":[17],"POMDPs)":[18],"by":[19],"representing":[20],"using":[22,34,56],"only":[23],"observable":[24],"quantities.":[25],"Because":[26],"this,":[28],"PSRs":[29],"can":[30],"be":[31,54,117],"learned":[32],"solely":[33],"data":[35,53,135],"interaction":[37],"with":[38],"the":[39,89,95,132,144],"process.":[40],"The":[41,123],"majority":[42],"existing":[44,90],"techniques,":[45],"though,":[46],"explicitly":[47],"or":[48],"implicitly":[49],"require":[50],"this":[52,84],"gathered":[55],"a":[57,70,121],"blind":[58],"policy,":[59],"where":[60],"actions":[61],"selected":[63],"independently":[64],"preceding":[66],"observations.":[67],"This":[68],"is":[69,97,103],"severe":[71],"limitation":[72,85],"for":[73,82,111],"practical":[74],"learning":[75,120],"PSRs.":[77],"We":[78,105],"present":[79,107],"two":[80],"methods":[81],"fixing":[83],"in":[86],"most":[87],"PSR":[91],"algorithms:":[92],"one":[93,100],"when":[94,101,119],"policy":[96],"known":[98],"and":[99],"it":[102],"not.":[104],"then":[106],"an":[108,139],"efficient":[109],"optimization":[110],"computing":[112],"good":[113],"exploration":[114,124],"policies":[115],"to":[116,137],"used":[118],"PSR.":[122],"policies,":[125],"which":[126],"not":[128],"blind,":[129],"significantly":[130],"lower":[131],"amount":[133],"needed":[136],"build":[138],"accurate":[140],"model,":[141],"thus":[142],"demonstrating":[143],"importance":[145],"non-blind":[147],"policies.":[148],"1.":[149]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}