{"id":"https://openalex.org/W4298306847","doi":null,"title":"Sample Efficient On-line Learning of Optimal Dialogue Policies with Kalman Temporal Differences","display_name":"Sample Efficient On-line Learning of Optimal Dialogue Policies with Kalman Temporal Differences","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W4298306847"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-00618252v1","doi":null,"is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-00618252","pdf_url":"https://centralesupelec.hal.science/hal-00618252v1/file/IJCAI_2011_OPMGSC.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"IJCAI 2011, Jul 2011, Barcelona, Spain. pp.1878-1883","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://centralesupelec.hal.science/hal-00618252v1/file/IJCAI_2011_OPMGSC.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065100569","display_name":"Olivier Pietquin","orcid":"https://orcid.org/0000-0002-5386-465X","observed_orcids":["https://orcid.org/0000-0002-5386-465X"]},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099","https://openalex.org/I277688954","https://openalex.org/I4210107720"]},{"id":"https://openalex.org/I1288283403","display_name":"Georgia Tech-Europe","ror":"https://ror.org/02m5dy175","country_code":"FR","type":"education","lineage":["https://openalex.org/I1288283403"]},{"id":"https://openalex.org/I4210089931","display_name":"Georgia Tech-CNRS Laboratory","ror":"https://ror.org/00avmbz91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I130701444","https://openalex.org/I4210089931","https://openalex.org/I4210095849","https://openalex.org/I4405256580"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Pietquin","raw_affiliation_strings":["Georgia Tech Lorraine [Metz]","SUPELEC-Campus Metz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech Lorraine [Metz]","institution_ids":["https://openalex.org/I1288283403","https://openalex.org/I4210089931"]},{"raw_affiliation_string":"SUPELEC-Campus Metz","institution_ids":["https://openalex.org/I102475099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110482875","display_name":"Matthieu Geist","orcid":"https://orcid.org/0009-0002-7888-8233","observed_orcids":["https://orcid.org/0009-0002-7888-8233"]},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099","https://openalex.org/I277688954","https://openalex.org/I4210107720"]},{"id":"https://openalex.org/I1288283403","display_name":"Georgia Tech-Europe","ror":"https://ror.org/02m5dy175","country_code":"FR","type":"education","lineage":["https://openalex.org/I1288283403"]},{"id":"https://openalex.org/I4210089931","display_name":"Georgia Tech-CNRS Laboratory","ror":"https://ror.org/00avmbz91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I130701444","https://openalex.org/I4210089931","https://openalex.org/I4210095849","https://openalex.org/I4405256580"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["Georgia Tech Lorraine [Metz]","SUPELEC-Campus Metz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech Lorraine [Metz]","institution_ids":["https://openalex.org/I1288283403","https://openalex.org/I4210089931"]},{"raw_affiliation_string":"SUPELEC-Campus Metz","institution_ids":["https://openalex.org/I102475099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031626252","display_name":"Senthilkumar Chandramohan","orcid":"https://orcid.org/0000-0002-8909-5485","observed_orcids":["https://orcid.org/0000-0002-8909-5485"]},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099","https://openalex.org/I277688954","https://openalex.org/I4210107720"]},{"id":"https://openalex.org/I1288283403","display_name":"Georgia Tech-Europe","ror":"https://ror.org/02m5dy175","country_code":"FR","type":"education","lineage":["https://openalex.org/I1288283403"]},{"id":"https://openalex.org/I4210089931","display_name":"Georgia Tech-CNRS Laboratory","ror":"https://ror.org/00avmbz91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I130701444","https://openalex.org/I4210089931","https://openalex.org/I4210095849","https://openalex.org/I4405256580"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Senthilkumar Ch","raw_affiliation_strings":["Georgia Tech Lorraine [Metz]","SUPELEC-Campus Metz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech Lorraine [Metz]","institution_ids":["https://openalex.org/I1288283403","https://openalex.org/I4210089931"]},{"raw_affiliation_string":"SUPELEC-Campus Metz","institution_ids":["https://openalex.org/I102475099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1173,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89281631,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1878","last_page":"1883"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9961000084877014,"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/T12031","display_name":"Speech and dialogue systems","score":0.9961000084877014,"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":0.0032999999821186066,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":9.999999747378752e-05,"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/dialogue-policy-learning","display_name":"dialogue policy learning","score":0.7910000085830688},{"id":"https://openalex.org/keywords/off-policy-learning","display_name":"off-policy learning","score":0.902999997138977},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.875},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.9950000047683716},{"id":"https://openalex.org/keywords/cross-domain-transfer","display_name":"cross-domain transfer","score":0.6629999876022339}],"concepts":[{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.8106637001037598},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.675512969493866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6377114057540894},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.5514065027236938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4614637494087219},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10613742470741272},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:HAL:hal-00618252v1","doi":null,"is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-00618252","pdf_url":"https://centralesupelec.hal.science/hal-00618252v1/file/IJCAI_2011_OPMGSC.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"IJCAI 2011, Jul 2011, Barcelona, Spain. pp.1878-1883","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.7558","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.7558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.metz.supelec.fr//metz/personnel/pietquin/pdf/IJCAI_2011_OPMGSC.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00618252v1","doi":null,"is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-00618252","pdf_url":"https://centralesupelec.hal.science/hal-00618252v1/file/IJCAI_2011_OPMGSC.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"IJCAI 2011, Jul 2011, Barcelona, Spain. pp.1878-1883","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5889215709","display_name":"Computational  Learning in  Adaptive Systems for  Spoken  Conversation","funder_award_id":"216594","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4298306847.pdf","grobid_xml":"https://content.openalex.org/works/W4298306847.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7100622596","https://openalex.org/W7100692260","https://openalex.org/W4299126605","https://openalex.org/W7098585361","https://openalex.org/W2964044380","https://openalex.org/W3133451788","https://openalex.org/W2040123554","https://openalex.org/W2577837170","https://openalex.org/W2950805960","https://openalex.org/W2012712913"],"abstract_inverted_index":{"Designing":[0],"dialog":[1,28,43],"policies":[2],"for":[3,25,42],"voice-enabled":[4],"interfaces":[5],"is":[6,11,22,33,58,94,131,145],"a":[7,125,137,159],"tailoring":[8],"job":[9,21],"that":[10,106,130],"most":[12],"often":[13],"left":[14],"to":[15,74,86,147],"natural":[16],"language":[17],"processing":[18],"experts.":[19],"This":[20,93],"generally":[23],"redone":[24],"every":[26],"new":[27],"task":[29],"because":[30],"cross-domain":[31],"transfer":[32],"not":[34,108],"possible.":[35],"For":[36],"this":[37,68,135],"reason,":[38],"machine":[39],"learning":[40,56,132,143],"methods":[41,72],"policy":[44,83,97,151],"optimization":[45],"have":[46],"been":[47],"investigated":[48],"during":[49],"the":[50,62,65,82],"last":[51],"15":[52],"years.":[53],"Especially,":[54],"reinforcement":[55,142],"(RL)":[57],"now":[59],"part":[60],"of":[61,64,155],"state":[63],"art":[66],"in":[67,81,103],"domain.":[69],"Standard":[70],"RL":[71],"require":[73],"test":[75],"more":[76],"or":[77,91],"less":[78],"random":[79],"changes":[80],"on":[84,96],"users":[85],"assess":[87],"them":[88],"as":[89],"improvements":[90],"degradations.":[92],"called":[95],"learning.":[98],"Nevertheless,":[99],"it":[100],"can":[101],"result":[102],"system":[104],"behaviors":[105],"are":[107],"acceptable":[109,128],"by":[110,120,124],"users.":[111],"Learning":[112],"algorithms":[113],"should":[114],"ideally":[115],"infer":[116],"an":[117,149],"optimal":[118,150],"strategy":[119],"observing":[121],"interactions":[122],"generated":[123,157],"non-optimal":[126],"but":[127],"strategy,":[129],"off-policy.":[133],"In":[134],"contribution,":[136],"sample-efficient,":[138],"online":[139],"and":[140],"off-policy":[141],"algorithm":[144],"proposed":[146],"learn":[148],"from":[152],"few":[153],"hundreds":[154],"dialogues":[156],"with":[158],"very":[160],"simple":[161],"handcrafted":[162],"policy.":[163],"1":[164]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}