{"id":"https://openalex.org/W31677673","doi":null,"title":"Apprentissage off-policy appliqu\u00e9 \u00e0 un syst\u00e8me de dialogue bas\u00e9 sur les PDMPO","display_name":"Apprentissage off-policy appliqu\u00e9 \u00e0 un syst\u00e8me de dialogue bas\u00e9 sur les PDMPO","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W31677673","mag":"31677673"},"language":"fr","primary_location":{"id":"pmh:oai:HAL:hal-00656496v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-00656496","pdf_url":"https://hal.science/hal-00656496v1/file/rfia2012_submission_40.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":"RFIA 2012 (Reconnaissance des Formes et Intelligence Artificielle), Jan 2012, Lyon, France. pp.978-2-9539515-2-3","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://hal.science/hal-00656496v1/file/rfia2012_submission_40.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072253501","display_name":"Lucie Daubigney","orcid":null,"observed_orcids":[]},"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":"Daubigney, Lucie","raw_affiliation_strings":["Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)","SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)","institution_ids":["https://openalex.org/I1288283403","https://openalex.org/I4210089931"]},{"raw_affiliation_string":"SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)","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":"Geist, Matthieu","raw_affiliation_strings":["Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)","SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech Lorraine [Metz] (Metz Technop\u00f4le 2-3 rue Marconi 57070 METZ - France)","institution_ids":["https://openalex.org/I1288283403","https://openalex.org/I4210089931"]},{"raw_affiliation_string":"SUPELEC-Campus Metz (2 rue Edouard Belin 57070 Metz - France)","institution_ids":["https://openalex.org/I102475099"]}]},{"author_position":"last","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pietquin, Olivier","raw_affiliation_strings":["IMS : Information, Multimodalit\u00e9 & Signal (2 rue Edouard Belin - - 57070 METZ - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal (2 rue Edouard Belin - - 57070 METZ - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00621902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4982999861240387,"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":0.4982999861240387,"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/T12031","display_name":"Speech and dialogue systems","score":0.49799999594688416,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.00039999998989515007,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/off-policy-learning","display_name":"off-policy learning","score":0.8489999771118164},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6169999837875366},{"id":"https://openalex.org/keywords/dialogue-systems","display_name":"dialogue systems","score":0.7699999809265137},{"id":"https://openalex.org/keywords/policy-optimization","display_name":"policy optimization","score":0.4230000078678131},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.5899999737739563},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.7350000143051147},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"multilayer perceptron","score":0.9549999833106995},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.4050000011920929}],"concepts":[{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.8376970887184143},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.5891557335853577},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.3941715955734253}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:HAL:hal-00656496v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-00656496","pdf_url":"https://hal.science/hal-00656496v1/file/rfia2012_submission_40.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":"RFIA 2012 (Reconnaissance des Formes et Intelligence Artificielle), Jan 2012, Lyon, France. pp.978-2-9539515-2-3","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-00656997v1","doi":null,"is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-00656997","pdf_url":null,"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":"Actes du 18\u00e8me congr\u00e8s francophone sur la Reconnaissance de Formes et l'Intelligence Artificielle (RFIA 2012), 2012, pp.1-8","raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00656496v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-00656496","pdf_url":"https://hal.science/hal-00656496v1/file/rfia2012_submission_40.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":"RFIA 2012 (Reconnaissance des Formes et Intelligence Artificielle), Jan 2012, Lyon, France. pp.978-2-9539515-2-3","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337753","display_name":"Interreg","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W31677673.pdf","grobid_xml":"https://content.openalex.org/works/W31677673.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W52170320","https://openalex.org/W196536594","https://openalex.org/W1211946649","https://openalex.org/W1778387566","https://openalex.org/W2021151961","https://openalex.org/W2040123554","https://openalex.org/W2106547558","https://openalex.org/W2107961737","https://openalex.org/W2115101920","https://openalex.org/W2116154161","https://openalex.org/W2121863487","https://openalex.org/W2124352385","https://openalex.org/W2132997613","https://openalex.org/W2134466368","https://openalex.org/W2151814822","https://openalex.org/W2156974606","https://openalex.org/W2158984235","https://openalex.org/W2163068732"],"related_works":["https://openalex.org/W4299126605","https://openalex.org/W2740233242","https://openalex.org/W7098585361","https://openalex.org/W7144103591","https://openalex.org/W7147145485","https://openalex.org/W4392217357","https://openalex.org/W2620768183","https://openalex.org/W2888863225","https://openalex.org/W3159144418","https://openalex.org/W7148943555"],"abstract_inverted_index":{"L'apprentissage":[0],"par":[1,34,92],"renforcement":[2],"(AR)":[3],"fait":[4],"maintenant":[5],"partie":[6],"de":[7,9,14,16,18,28,43,56,70,78,124,138,141,147],"l'\u00e9tat":[8],"l'art":[10],"dans":[11,51],"le":[12],"domaine":[13],"l'optimisation":[15],"syst\u00e8mes":[17,27,150],"dialogues":[19],"vocaux.":[20],"La":[21],"plupart":[22],"des":[23,39,45,68,149],"m\u00e9thodes":[24],"appliqu\u00e9es":[25],"aux":[26,76],"dialogue":[29],"bas\u00e9es":[30],"sur":[31,115],"l'AR,":[32],"comme":[33],"exemple":[35],"celles":[36],"qui":[37],"utilisent":[38],"processus":[40],"gaussiens,":[41],"requi\u00e8rent":[42],"tester":[44],"changements":[46],"plus":[47],"ou":[48],"moins":[49],"al\u00e9atoires":[50],"la":[52,71,85,125,139],"politique.":[53],"Cette":[54],"mani\u00e8re":[55],"proc\u00e9der":[57],"est":[58,128],"appel\u00e9e":[59],"apprentissage":[60],"\"":[61,106],"on-policy":[62],"\".":[63,108],"N\u00e9anmoins,":[64],"celle-ci":[65],"peut":[66],"induire":[67],"comportements":[69],"part":[72],"du":[73],"syst\u00e8me":[74],"incoh\u00e9rents":[75],"yeux":[77],"l'utilisateur.":[79],"Les":[80],"algorithmes":[81],"devraient":[82],"id\u00e9alement":[83],"trouver":[84],"politique":[86,94,126],"optimale":[87,127],"d'apr\u00e8s":[88],"l'observation":[89],"d'interactions":[90],"g\u00e9n\u00e9r\u00e9es":[91],"une":[93,134],"sous-optimale":[95],"mais":[96],"proposant":[97],"un":[98,112],"comportement":[99],"coh\u00e9rent":[100],"a":[101],"l'utilisateur":[102],":":[103],"c'est":[104],"l'apprentissage":[105,119],"off-policy":[107,120],"Dans":[109],"cette":[110],"contribution,":[111],"algorithme":[113,131],"efficace":[114],"les":[116],"\u00e9chantillons":[117],"permettant":[118],"et":[121],"en":[122],"ligne":[123],"propos\u00e9.":[129],"Cet":[130],"combin\u00e9,":[132],"\u00e0":[133,151],"repr\u00e9sentation":[135],"compacte,":[136],"non-lin\u00e9aire":[137],"fonction":[140],"valeur":[142],"(un":[143],"perceptron":[144],"multi-couche)":[145],"permet":[146],"g\u00e9rer":[148],"grande":[152],"\u00e9chelle":[153]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}
