{"id":"https://openalex.org/W2000316603","doi":"https://doi.org/10.3166/ria.17.559-589","title":"Apprentissage par renforcement pour les processus d\u00e9cisionnels de Markov partiellement observ\u00e9s Apprendre une extension s\u00e9lective du pass\u00e9","display_name":"Apprentissage par renforcement pour les processus d\u00e9cisionnels de Markov partiellement observ\u00e9s Apprendre une extension s\u00e9lective du pass\u00e9","publication_year":2003,"publication_date":"2003-08-01","ids":{"openalex":"https://openalex.org/W2000316603","doi":"https://doi.org/10.3166/ria.17.559-589","mag":"2000316603"},"language":"fr","primary_location":{"id":"doi:10.3166/ria.17.559-589","is_oa":false,"landing_page_url":"https://doi.org/10.3166/ria.17.559-589","pdf_url":null,"source":{"id":"https://openalex.org/S4210205895","display_name":"Revue d intelligence artificielle","issn_l":"0992-499X","issn":["0992-499X","1958-5748"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310312982","host_organization_name":"International Information and Engineering Technology Association","host_organization_lineage":["https://openalex.org/P4310312982"],"host_organization_lineage_names":["International Information and Engineering Technology Association"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Revue d'intelligence artificielle","raw_type":"journal-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/A5048051326","display_name":"Alain Dutech","orcid":"https://orcid.org/0000-0001-7549-7988"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alain Dutech","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5008275995","display_name":"Manuel Samuelides","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuel Samuelides","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048051326"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9137,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80094317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"17","issue":"4","first_page":"559","last_page":"589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9721999764442444,"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":0.9721999764442444,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9301000237464905,"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/philosophy","display_name":"Philosophy","score":0.36002856492996216},{"id":"https://openalex.org/keywords/humanities","display_name":"Humanities","score":0.33103758096694946}],"concepts":[{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.36002856492996216},{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.33103758096694946}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3166/ria.17.559-589","is_oa":false,"landing_page_url":"https://doi.org/10.3166/ria.17.559-589","pdf_url":null,"source":{"id":"https://openalex.org/S4210205895","display_name":"Revue d intelligence artificielle","issn_l":"0992-499X","issn":["0992-499X","1958-5748"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310312982","host_organization_name":"International Information and Engineering Technology Association","host_organization_lineage":["https://openalex.org/P4310312982"],"host_organization_lineage_names":["International Information and Engineering Technology Association"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Revue d'intelligence artificielle","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W93312527","https://openalex.org/W2603296253","https://openalex.org/W1589203209","https://openalex.org/W2557454913","https://openalex.org/W828925460","https://openalex.org/W11365241","https://openalex.org/W1013667899","https://openalex.org/W2559405764"],"abstract_inverted_index":{"Nous":[0,48,71],"presentons":[1],"un":[2,41],"nouvel":[3],"algorithme":[4],"qui":[5,37,44],"contribue":[6],"a":[7],"etendre":[8],"le":[9],"formalisme":[10],"de":[11,25,29,39,62,75],"l'Apprentissage":[12],"par":[13],"Renforcement":[14],"(RL)":[15],"aux":[16],"Processus":[17],"Decisionnels":[18],"Markoviens":[19],"Partiellement":[20],"Observes":[21],"(POMDP).":[22],"L'idee":[23],"principale":[24],"notre":[26],"methode":[27],"est":[28,45],"construire":[30],"une":[31,65],"extension":[32],"d'etat,":[33],"appelee":[34],"observable":[35],"exhaustif,":[36],"permet":[38],"definir":[40],"nouveau":[42,53],"processus":[43],"alors":[46],"markovien.":[47],"demontrons":[49],"que":[50],"resoudre":[51],"ce":[52,76],"processus,":[54],"auquel":[55],"on":[56],"peut":[57],"appliquer":[58],"les":[59],"techniques":[60],"classiques":[61],"RL,":[63],"apporte":[64],"solution":[66],"optimale":[67],"au":[68],"POMDP":[69],"original.":[70],"appliquons":[72],"l'algorithme":[73],"deduit":[74],"resultat":[77],"sur":[78],"plusieurs":[79],"exemples":[80],"pour":[81],"en":[82],"tester":[83],"la":[84,87],"validite":[85],"et":[86],"robustesse.":[88]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}