{"id":"https://openalex.org/W578577700","doi":null,"title":"Hierarchical and factored reinforcement learning","display_name":"Hierarchical and factored reinforcement learning","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W578577700","mag":"578577700"},"language":"en","primary_location":{"id":"pmh:hdl:10068/859496","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10068/859496","pdf_url":null,"source":{"id":"https://openalex.org/S4377196900","display_name":"OpenGrey (Institut de l'Information Scientifique et Technique)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1295345811","host_organization_name":"Institut de l'Information Scientifique et Technique","host_organization_lineage":["https://openalex.org/I1295345811"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"U - Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10068/859496","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Olga Kozlova","orcid":"https://orcid.org/0000-0002-5974-0228","observed_orcids":["https://orcid.org/0000-0002-5974-0228"]},"institutions":[{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Olga Kozlova","raw_affiliation_strings":["Institut des Syst\u00e8mes Intelligents et de Robotique"],"raw_orcid":"https://orcid.org/0000-0002-5974-0228","affiliations":[{"raw_affiliation_string":"Institut des Syst\u00e8mes Intelligents et de Robotique","institution_ids":["https://openalex.org/I4210150358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210150358"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10906","display_name":"AI-based Problem Solving and Planning","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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","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/hierarchical-reinforcement-learning","display_name":"hierarchical reinforcement learning","score":0.9649999737739563},{"id":"https://openalex.org/keywords/factored-markov-decision-processes","display_name":"factored Markov decision processes","score":0.9470000267028809},{"id":"https://openalex.org/keywords/options-framework","display_name":"options framework","score":0.7490000128746033},{"id":"https://openalex.org/keywords/hierarchical-decomposition","display_name":"hierarchical decomposition","score":0.5299999713897705},{"id":"https://openalex.org/keywords/industrial-simulation","display_name":"industrial simulation","score":0.460999995470047}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8509658575057983},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7031538486480713},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5774402022361755},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5758440494537354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5192461013793945},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4631836414337158},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44661444425582886},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43929511308670044},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4022926092147827},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3536834418773651},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34221789240837097},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33613908290863037},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.226054847240448},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.18108141422271729},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:hdl:10068/859496","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10068/859496","pdf_url":null,"source":{"id":"https://openalex.org/S4377196900","display_name":"OpenGrey (Institut de l'Information Scientifique et Technique)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1295345811","host_organization_name":"Institut de l'Information Scientifique et Technique","host_organization_lineage":["https://openalex.org/I1295345811"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"U - Thesis"},{"id":"pmh:oai:HAL:tel-00632968v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/tel-00632968v1","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":"Other [cs.OH]. Universit\u00e9 Pierre et Marie Curie - Paris VI, 2010. English. ⟨NNT : ⟩","raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"mag:578577700","doi":null,"is_oa":false,"landing_page_url":"https://tel.archives-ouvertes.fr/tel-00632968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:hdl:10068/859496","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10068/859496","pdf_url":null,"source":{"id":"https://openalex.org/S4377196900","display_name":"OpenGrey (Institut de l'Information Scientifique et Technique)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1295345811","host_organization_name":"Institut de l'Information Scientifique et Technique","host_organization_lineage":["https://openalex.org/I1295345811"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"U - Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W18175453","https://openalex.org/W32198084","https://openalex.org/W57282082","https://openalex.org/W125130877","https://openalex.org/W1218520990","https://openalex.org/W1488730473","https://openalex.org/W1490954610","https://openalex.org/W1491961724","https://openalex.org/W1503515926","https://openalex.org/W1520883790","https://openalex.org/W1530444831","https://openalex.org/W1537180453","https://openalex.org/W1557310611","https://openalex.org/W1562487267","https://openalex.org/W1564393562","https://openalex.org/W1585861384","https://openalex.org/W1586980550","https://openalex.org/W1598052524","https://openalex.org/W1640358294","https://openalex.org/W1650504995","https://openalex.org/W1678414046","https://openalex.org/W1895872655","https://openalex.org/W1966028617","https://openalex.org/W1977137834","https://openalex.org/W1980035368","https://openalex.org/W1997477668","https://openalex.org/W2009533501","https://openalex.org/W2020294948","https://openalex.org/W2048226872","https://openalex.org/W2089561656","https://openalex.org/W2090170171","https://openalex.org/W2097381042","https://openalex.org/W2098432798","https://openalex.org/W2106216496","https://openalex.org/W2107726111","https://openalex.org/W2109910161","https://openalex.org/W2110415190","https://openalex.org/W2119567691","https://openalex.org/W2120406836","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2125055259","https://openalex.org/W2131660762","https://openalex.org/W2138186376","https://openalex.org/W2139139112","https://openalex.org/W2139612737","https://openalex.org/W2141714215","https://openalex.org/W2143435603","https://openalex.org/W2144744117","https://openalex.org/W2149706766","https://openalex.org/W2153668164","https://openalex.org/W2153947321","https://openalex.org/W2154051144","https://openalex.org/W2158548602","https://openalex.org/W2159420891","https://openalex.org/W2160371091","https://openalex.org/W2167650507","https://openalex.org/W2170400507","https://openalex.org/W2180809782","https://openalex.org/W2341171179","https://openalex.org/W2406325222","https://openalex.org/W2963614772","https://openalex.org/W3015571647"],"related_works":["https://openalex.org/W4392445223","https://openalex.org/W7152595087","https://openalex.org/W2311063981","https://openalex.org/W7020976845","https://openalex.org/W4298683466","https://openalex.org/W7097092764","https://openalex.org/W651862707","https://openalex.org/W3035644125","https://openalex.org/W7056863049","https://openalex.org/W7130299693"],"abstract_inverted_index":{"Les":[0],"m\u00e9thodes":[1],"d'apprentissage":[2],"par":[3,41],"renforcement":[4,42],"factoris\u00e9":[5],"et":[6,21,44,91,108,185,192],"hi\u00e9rarchique":[7],"(HFRL)":[8],"sont":[9],"bas\u00e9es":[10],"sur":[11,99,147,177,197],"le":[12,45,145,190],"formalisme":[13,46],"des":[14,47,100,154],"processus":[15],"de":[16,33,53,55,65,74,86,96,119,125,132,134,150,159,195,205],"d\u00e9cision":[17,56],"markoviens":[18],"factoris\u00e9es":[19],"(FMDP)":[20],"les":[22,37,51,58,81,94,182,193],"MDP":[23,133],"hi\u00e9rarchiques":[24],"(HMDP).":[25],"Dans":[26,70],"cette":[27,75,120],"th\u00e8se,":[28,76],"nous":[29,77,92,188],"proposons":[30],"une":[31],"m\u00e9thode":[32],"HFRL":[34],"qui":[35,164],"utilise":[36],"approches":[38],"d":[39],"apprentissage":[40],"indirect":[43],"options":[48],"pour":[49,129],"r\u00e9soudre":[50],"probl\u00e8mes":[52,82,101,183],"prise":[54],"dans":[57,104],"environnements":[59],"dynamiques":[60],"sans":[61],"connaissance":[62],"a":[63],"priori":[64],"la":[66,71,105,123,130,138,148,151,160,206],"structure":[67,139,161],"du":[68,162,203],"probl\u00e8me.":[69],"premi\u00e8re":[72],"contribution":[73,118],"montrons":[78],"comment":[79],"mod\u00e9liser":[80],"o\u00f9":[83],"certaines":[84],"combinaisons":[85],"variables":[87],"n":[88],"existent":[89],"pas":[90],"d\u00e9montrons":[93],"performances":[95],"nos":[97],"algorithmes":[98],"jouet":[102,200],"classiques":[103],"litt\u00e9rature,":[106],"MAZE6":[107],"BLOCKSWORLD,":[109],"en":[110,169],"comparaison":[111],"avec":[112,171],"l":[113,172],"approche":[114],"standard.":[115],"La":[116],"deuxi\u00e8me":[117],"th\u00e8se":[121],"est":[122,140,165],"proposition":[124],"TeXDYNA,":[126],"un":[127,198],"algorithme":[128],"r\u00e9solution":[131],"grande":[135],"taille":[136],"dont":[137],"inconnue.":[141],"TeXDYNA":[142,176,196],"d\u00e9compose":[143],"hi\u00e9rarchiquement":[144],"FMDP":[146],"base":[149],"d\u00e9couverte":[152],"automatique":[153],"sous-t\u00e2ches":[155],"directement":[156],"\u00e0":[157,180],"partir":[158],"probl\u00e8me":[163,199],"elle":[166],"m\u00eame":[167],"apprise":[168],"interaction":[170],"environnement.":[173],"Nous":[174],"\u00e9valuons":[175],"deux":[178],"benchmarks,":[179],"savoir":[181],"TAXI":[184],"LIGHTBOX.":[186],"Finalement,":[187],"estimons":[189],"potentiel":[191],"limitations":[194],"plus":[201],"repr\u00e9sentatif":[202],"domaine":[204],"simulation":[207],"industrielle.":[208]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}