{"id":"https://openalex.org/W2036066046","doi":null,"title":"Classification structur\u00e9e pour l'apprentissage par renforcement inverse","display_name":"Classification structur\u00e9e pour l'apprentissage par renforcement inverse","publication_year":2012,"publication_date":"2012-05-23","ids":{"openalex":"https://openalex.org/W2036066046","mag":"2036066046"},"language":"fr","primary_location":{"id":"pmh:oai:HAL:hal-00701947v1","doi":null,"is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-00701947","pdf_url":"https://centralesupelec.hal.science/hal-00701947/document","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":"Conf\u00e9rence Francophone sur l'Apprentissage Automatique - CAp 2012, May 2012, Nancy, France. pp.1-16","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-00701947/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000665687","display_name":"Edouard Klein","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Klein, Edouard","raw_affiliation_strings":["ABC - Machine Learning and Computational Biology (France)","IMS : Information, Multimodalit\u00e9 & Signal (2 rue Edouard Belin - - 57070 METZ - France)","IMS : Information, Multimodalit\u00e9 & Signal","Machine Learning and Computational Biology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ABC - Machine Learning and Computational Biology (France)","institution_ids":[]},{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal (2 rue Edouard Belin - - 57070 METZ - France)","institution_ids":[]},{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal","institution_ids":[]},{"raw_affiliation_string":"Machine Learning and Computational Biology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051968502","display_name":"Bilal Piot","orcid":"https://orcid.org/0000-0003-3906-950X","observed_orcids":["https://orcid.org/0000-0003-3906-950X","https://orcid.org/0000-0002-6456-7183"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piot, Bilal","raw_affiliation_strings":["IMS : Information, Multimodalit\u00e9 & Signal (2 rue Edouard Belin - - 57070 METZ - France)","IMS : Information, Multimodalit\u00e9 & Signal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal (2 rue Edouard Belin - - 57070 METZ - France)","institution_ids":[]},{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal","institution_ids":[]}]},{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geist, Matthieu","raw_affiliation_strings":["IMS : Information, Multimodalit\u00e9 & Signal (2 rue Edouard Belin - - 57070 METZ - France)","IMS : Information, Multimodalit\u00e9 & Signal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal (2 rue Edouard Belin - - 57070 METZ - France)","institution_ids":[]},{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal","institution_ids":[]}]},{"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)","IMS : Information, Multimodalit\u00e9 & Signal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal (2 rue Edouard Belin - - 57070 METZ - France)","institution_ids":[]},{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.13527541,"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":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/inverse-reinforcement-learning","display_name":"inverse reinforcement learning","score":0.9819999933242798},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.8880000114440918},{"id":"https://openalex.org/keywords/reward-function-estimation","display_name":"reward function estimation","score":0.7360000014305115},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7540000081062317},{"id":"https://openalex.org/keywords/structured-classification","display_name":"structured classification","score":0.6970000267028809},{"id":"https://openalex.org/keywords/subgradient-descent","display_name":"subgradient descent","score":0.8510000109672546},{"id":"https://openalex.org/keywords/expert-trajectories","display_name":"expert trajectories","score":0.6359999775886536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4547911286354065}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-00701947v1","doi":null,"is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-00701947","pdf_url":"https://centralesupelec.hal.science/hal-00701947/document","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":"Conf\u00e9rence Francophone sur l'Apprentissage Automatique - CAp 2012, May 2012, Nancy, France. pp.1-16","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00701947v1","doi":null,"is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-00701947","pdf_url":"https://centralesupelec.hal.science/hal-00701947/document","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":"Conf\u00e9rence Francophone sur l'Apprentissage Automatique - CAp 2012, May 2012, Nancy, France. pp.1-16","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2036066046.pdf","grobid_xml":"https://content.openalex.org/works/W2036066046.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4301154800","https://openalex.org/W4293508306","https://openalex.org/W3156893302","https://openalex.org/W7017299356","https://openalex.org/W7143890883","https://openalex.org/W3087352516","https://openalex.org/W2559859970","https://openalex.org/W4392236016","https://openalex.org/W7043139432","https://openalex.org/W7151813940"],"abstract_inverted_index":{"Cette":[0],"contribution":[1,122],"traite":[2],"du":[3,35,58,146,179],"probl\u00e8me":[4,48,103,180],"de":[5,12,31,44,56,60,78,81,89,96,100,106,110,119,131,149,161],"l'apprentissage":[6,13,107],"par":[7,9,14,108],"imitation":[8],"le":[10,47,102],"biais":[11],"renforcement":[15],"inverse":[16],"(ARI).":[17],"Dans":[18],"ce":[19],"contexte,":[20],"un":[21,83,125,155],"expert":[22],"accomplit":[23],"une":[24,42,67,136,159,164],"t\u00e2che":[25],"qu'un":[26],"agent":[27],"artificiel":[28],"doit":[29],"essayer":[30],"reproduire.":[32],"L'ARI":[33],"part":[34,80],"postulat":[36],"que":[37,170],"l'expert":[38],"optimise":[39],"avec":[40],"succ\u00e8s":[41],"fonction":[43,53],"r\u00e9compense":[45],";":[46],"consiste":[49,123],"\u00e0":[50,54,115],"deviner":[51],"cette":[52],"partir":[55],"traces":[57],"comportement":[59],"l'expert.":[61,120],"Les":[62],"algorithmes":[63],"d'ARI":[64,128],"existants":[65],"n\u00e9cessitent":[66],"ou":[68,113],"plusieurs":[69],"des":[70,94],"conditions":[71],"suivantes":[72],"pour":[73,86],"fonctionner":[74],":":[75],"trajectoires":[76],"compl\u00e8tes":[77],"la":[79,92,98,116,144,177],"l'expert,":[82],"mod\u00e8le":[84],"g\u00e9n\u00e9ratif":[85],"les":[87],"estimations":[88],"type":[90],"Monte-Carlo,":[91],"connaissance":[93],"probabilit\u00e9s":[95],"transition,":[97],"capacit\u00e9":[99],"r\u00e9soudre":[101],"direct":[104],"(celui":[105],"renforcement)":[109],"mani\u00e8re":[111],"r\u00e9p\u00e9t\u00e9e":[112],"l'acc\u00e8s":[114],"strategie":[117],"compl\u00e8te":[118],"Notre":[121],"en":[124,168],"nouvel":[126],"algorithme":[127,156],"levant":[129],"l'ensemble":[130],"ces":[132],"contraintes.":[133],"En":[134],"utilisant":[135],"m\u00e9thode":[137],"supervis\u00e9e":[138],"dans":[139],"laquelle":[140],"nous":[141,153],"introduisons":[142],"implicitement":[143],"structure":[145],"processus":[147],"d\u00e9cisionnel":[148],"Markov":[150],"(PDM)":[151],"sous-jacent,":[152],"cr\u00e9ons":[154],"bas\u00e9":[157],"sur":[158],"descente":[160],"sous-gradient,":[162],"poss\u00e8dant":[163],"faible":[165],"complexit\u00e9":[166],"tant":[167],"\u00e9chantillons":[169],"calculatoire":[171],"et":[172],"surtout":[173],"ne":[174],"n\u00e9cessitant":[175],"pas":[176],"r\u00e9solution":[178],"direct.":[181]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}