{"id":"https://openalex.org/W2024074370","doi":"https://doi.org/10.3166/ria.20.275-310","title":"Apprentissage par renforcement dans le cadre des processus d\u00e9cisionnels de Markov factoris\u00e9s observables dans le d\u00e9sordre. Etude exp\u00e9rimentale du Q-Learning parall\u00e8le appliqu\u00e9 aux probl\u00e8mes du labyrinthe et du New York Driving","display_name":"Apprentissage par renforcement dans le cadre des processus d\u00e9cisionnels de Markov factoris\u00e9s observables dans le d\u00e9sordre. Etude exp\u00e9rimentale du Q-Learning parall\u00e8le appliqu\u00e9 aux probl\u00e8mes du labyrinthe et du New York Driving","publication_year":2006,"publication_date":"2006-06-01","ids":{"openalex":"https://openalex.org/W2024074370","doi":"https://doi.org/10.3166/ria.20.275-310","mag":"2024074370"},"language":"fr","primary_location":{"id":"doi:10.3166/ria.20.275-310","is_oa":false,"landing_page_url":"https://doi.org/10.3166/ria.20.275-310","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/A5086574604","display_name":"Guillaume J. Laurent","orcid":"https://orcid.org/0000-0003-3586-4696"},"institutions":[{"id":"https://openalex.org/I53262699","display_name":"\u00c9cole Nationale Sup\u00e9rieure de M\u00e9canique et des Microtechniques","ror":"https://ror.org/05813w841","country_code":"FR","type":"education","lineage":["https://openalex.org/I53262699"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Guillaume J. Laurent","raw_affiliation_strings":["Ecole Nationale Sup\u00e9rieure de M\u00e9canique et des Microtechniques"],"affiliations":[{"raw_affiliation_string":"Ecole Nationale Sup\u00e9rieure de M\u00e9canique et des Microtechniques","institution_ids":["https://openalex.org/I53262699"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055567959","display_name":"Emmanuel Piat","orcid":"https://orcid.org/0009-0008-5374-4181"},"institutions":[{"id":"https://openalex.org/I53262699","display_name":"\u00c9cole Nationale Sup\u00e9rieure de M\u00e9canique et des Microtechniques","ror":"https://ror.org/05813w841","country_code":"FR","type":"education","lineage":["https://openalex.org/I53262699"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Piat","raw_affiliation_strings":["Ecole Nationale Sup\u00e9rieure de M\u00e9canique et des Microtechniques"],"affiliations":[{"raw_affiliation_string":"Ecole Nationale Sup\u00e9rieure de M\u00e9canique et des Microtechniques","institution_ids":["https://openalex.org/I53262699"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086574604"],"corresponding_institution_ids":["https://openalex.org/I53262699"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09103856,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":"2-3","first_page":"275","last_page":"310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T12288","display_name":"Optimization and Search Problems","score":0.9794999957084656,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/markov-decision-process","display_name":"Markov decision process","score":0.6293402314186096},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6146558523178101},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5843360424041748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5625250339508057},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5369654893875122},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5142040252685547},{"id":"https://openalex.org/keywords/humanities","display_name":"Humanities","score":0.44370704889297485},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4173992872238159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33016806840896606},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2767021954059601},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27110788226127625},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.19114834070205688},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14851921796798706},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.13488057255744934},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08017924427986145},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07441839575767517}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6293402314186096},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6146558523178101},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5843360424041748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5625250339508057},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5369654893875122},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5142040252685547},{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.44370704889297485},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4173992872238159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33016806840896606},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2767021954059601},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27110788226127625},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.19114834070205688},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14851921796798706},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.13488057255744934},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08017924427986145},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07441839575767517},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3166/ria.20.275-310","is_oa":false,"landing_page_url":"https://doi.org/10.3166/ria.20.275-310","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":[{"id":"https://metadata.un.org/sdg/16","score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W27992807","https://openalex.org/W49038156","https://openalex.org/W1480676279","https://openalex.org/W1507087299","https://openalex.org/W1531886263","https://openalex.org/W1535640688","https://openalex.org/W1553023101","https://openalex.org/W1554015367","https://openalex.org/W1554120378","https://openalex.org/W1979071892","https://openalex.org/W1993740947","https://openalex.org/W1997477668","https://openalex.org/W2012036715","https://openalex.org/W2061504687","https://openalex.org/W2101767921","https://openalex.org/W2103626435","https://openalex.org/W2117341272","https://openalex.org/W2121517924","https://openalex.org/W2121682629","https://openalex.org/W2121863487","https://openalex.org/W2160371091","https://openalex.org/W2341171179","https://openalex.org/W2489939061","https://openalex.org/W2615268666","https://openalex.org/W3023407077","https://openalex.org/W3103882218"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W131709709","https://openalex.org/W2294884454","https://openalex.org/W3169161914"],"abstract_inverted_index":{"This":[0],"paper":[1,25],"presents":[2],"experimental":[3],"results":[4],"obtained":[5],"with":[6],"an":[7],"original":[8],"architecture":[9,51,68],"that":[10,66],"can":[11],"do":[12],"generic":[13,75],"learning":[14],"for":[15],"randomly":[16],"observable":[17],"factored":[18],"Markov":[19],"decision":[20],"process":[21],"(ROFMDP).":[22],"First,":[23],"the":[24,27,33,40,44,50,67,80,84],"describes":[26],"theoretical":[28],"framework":[29],"of":[30,35,79,83,87],"ROFMDP":[31],"and":[32,43,59,74],"working":[34],"this":[36],"algorithm,":[37],"in":[38,77],"particular":[39],"parallelization":[41],"principle":[42],"dynamic":[45],"reward":[46],"allocation":[47],"process.":[48],"Then,":[49],"is":[52],"applied":[53],"to":[54,70],"two":[55],"navigation":[56],"problems":[57],"(gridworld":[58],"New":[60],"York":[61],"Driving).":[62],"The":[63],"tests":[64],"show":[65],"allows":[69],"learn":[71],"a":[72],"good":[73],"policy":[76],"spite":[78],"large":[81],"dimensions":[82],"state":[85],"spaces":[86],"both":[88],"systems.":[89]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}