{"id":"https://openalex.org/W20823384","doi":null,"title":"A convergent reinforcement learning algorithm in the continuous case based on a finite difference method","display_name":"A convergent reinforcement learning algorithm in the continuous case based on a finite difference method","alternate_titles":[],"publication_year":1997,"publication_date":"1997-01-01","ids":{"openalex":"https://openalex.org/W20823384","mag":"20823384"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-02577311v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.inrae.fr/hal-02577311","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International joint conference on artifical intelligence, Nagoya, JPN, 23-29 August 1997, 1997, Japan. pp.826-831","raw_type":"info:eu-repo/semantics/conferenceObject"},"parent_works":[],"lineage":["https://openalex.org/W20823384"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5006533777","display_name":"R\u00e9mi Munos","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4402554077","display_name":"Laboratoire d'Ing\u00e9nierie des Syst\u00e8mes Complexes","ror":"https://ror.org/01dfzdy43","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210088668","https://openalex.org/I4402554077"]}],"countries":["FR"],"is_corresponding":true,"contributor_roles":[],"raw_author_name":"R\u00e9mi Munos","raw_affiliation_strings":["UR LISC - Laboratoire d'ing\u00e9nierie pour les syst\u00e8mes complexes (Clermont-Ferrand - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UR LISC - Laboratoire d'ing\u00e9nierie pour les syst\u00e8mes complexes (Clermont-Ferrand - France)","institution_ids":["https://openalex.org/I4402554077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5006533777"],"corresponding_institution_ids":["https://openalex.org/I4402554077"],"apc_list":null,"apc_paid":null,"fwci":1.5724,"has_fulltext":false,"cited_by_count":20,"reviewed_by_count":0,"citation_normalized_percentile":{"value":0.80491421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":86,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"826","last_page":"831"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5839999914169312,"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":0.5839999914169312,"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":0.4147999882698059,"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"}},{"id":"https://openalex.org/T10067","display_name":"Stochastic processes and financial applications","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6769999861717224},{"id":"https://openalex.org/keywords/optimal-control","display_name":"optimal control","score":0.7749999761581421},{"id":"https://openalex.org/keywords/continuous-state-spaces","display_name":"continuous state spaces","score":0.828000009059906},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.7950000166893005},{"id":"https://openalex.org/keywords/finite-difference-method","display_name":"finite difference method","score":0.8190000057220459},{"id":"https://openalex.org/keywords/hamilton-jacobi-bellman-equation","display_name":"Hamilton-Jacobi-Bellman equation","score":0.9990000128746033},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.6869999766349792},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.734000027179718},{"id":"https://openalex.org/keywords/markov-property","display_name":"Markov property","score":0.7770000100135803},{"id":"https://openalex.org/keywords/model-free-reinforcement-learning","display_name":"model-free reinforcement learning","score":0.8029999732971191},{"id":"https://openalex.org/keywords/discretization-error","display_name":"discretization error","score":0.597000002861023}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8434666395187378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.667338490486145},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5582079887390137},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47968578338623047},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4325811266899109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3067811131477356},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07967856526374817},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:HAL:hal-02577311v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.inrae.fr/hal-02577311","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International joint conference on artifical intelligence, Nagoya, JPN, 23-29 August 1997, 1997, Japan. pp.826-831","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:irsteadoc.irstea.fr:PUB00004338","doi":null,"is_oa":false,"landing_page_url":"https://irsteadoc.irstea.fr/cemoa/PUB00004338","pdf_url":null,"source":{"id":"https://openalex.org/S7407064358","display_name":"Cemadoc (Cemagref / IRSTEA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"3959","raw_type":"Communication \u00e0 un congr\u00e8s"},{"id":"mag:20823384","doi":null,"is_oa":false,"landing_page_url":"https://hal.inrae.fr/hal-02577311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"HAL (Le Centre pour la Communication Scientifique Directe)","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1144598269","display_name":"Cardiovascular Regenerative Medicine","funder_award_id":"P01HL108795","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G5397549010","display_name":"Pleiotropic Role of PAI-1 in Cardiovascular Aging","funder_award_id":"R01HL051387","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G8829731396","display_name":"SCCOR in Hemostatic and Thrombotic Diseases","funder_award_id":"P50HL081009","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"}],"funders":[{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1547105496","https://openalex.org/W1583902426","https://openalex.org/W1966195676","https://openalex.org/W2022384521","https://openalex.org/W2032316144","https://openalex.org/W2042112368","https://openalex.org/W2125074935","https://openalex.org/W2130746277","https://openalex.org/W2177195156","https://openalex.org/W4210791600"],"related_works":["https://openalex.org/W7096101611","https://openalex.org/W4300463344","https://openalex.org/W2166356462","https://openalex.org/W4312135885","https://openalex.org/W7100126691","https://openalex.org/W1583902426","https://openalex.org/W1564711114","https://openalex.org/W7098293622","https://openalex.org/W1501482654","https://openalex.org/W2113501460"],"abstract_inverted_index":{"In":[0,83],"this":[1,39],"paper,":[2],"we":[3,85,153],"propose":[4,131],"a":[5,28,44,94,100,119,138,144,155],"convergent":[6,139,228],"reinforcement":[7,157,163,272],"learning":[8,158],"algorithm":[9],"for":[10,15,70,126],"solving":[11],"optimal":[12,41,195],"control":[13],"problems":[14],"which":[16,35],"state":[17,116],"space":[18,117],"and":[19,80,165],"time":[20],"are":[21],"continuous":[22,49,128,175],"variables.":[23],"The":[24,107],"problem":[25],"of":[26,31,63,114,121,148,173],"computing":[27],"good":[29],"approximation":[30,147],"the":[32,48,61,72,112,115,122,134,149,170,174],"value":[33,73,135,171],"function,":[34],"is":[36,43,110],"essential":[37],"because":[38],"provides":[40],"control,":[42],"difficult":[45],"task":[46],"in":[47],"case.":[50],"Indeed,":[51],"as":[52,67],"it":[53],"has":[54],"been":[55],"pointed":[56],"out":[57],"by":[58],"several":[59],"authors,":[60],"use":[62],"parameterized":[64],"functions":[65],"such":[66],"neural":[68],"networks":[69],"approximating":[71],"function":[74,136,172],"may":[75,103],"produce":[76],"very":[77],"bad":[78],"results":[79],"even":[81,125],"diverge.":[82],"fact,":[84],"show":[86],"that":[87,111],"classical":[88],"algorithms,":[89],"like":[90],"Q-learning,":[91,216],"used":[92],"with":[93,137],"simple":[95],"look-up":[96],"table":[97],"built":[98],"on":[99,143],"rectangular":[101],"grid,":[102],"fail":[104],"to":[105,132,169],"converge.":[106],"main":[108],"reason":[109],"discretization":[113],"implies":[118],"loss":[120],"Markov":[123],"property":[124],"deterministic":[127],"processes.":[129],"We":[130],"approximate":[133],"numerical":[140],"scheme":[141],"based":[142],"finite":[145],"difference":[146,162,271],"Hamilton-Jacobi-Bellman":[150],"equation.":[151],"Then":[152],"present":[154],"model-free":[156],"algorithm,":[159],"called":[160],"\"Finite":[161,270],"learning\"":[164],"prove":[166],"its":[167],"convergence":[168,278],"problem.":[176],"/":[177],"Dans":[178],"cet":[179],"article":[180],"nous":[181],"proposons":[182,244],"un":[183,267],"algorithme":[184],"d'apprentissage":[185],"par":[186],"renforcement":[187],"convergent,":[188],"pour":[189,196],"r\u00e9soudre":[190],"des":[191,204,221,240],"probl\u00e8mes":[192],"de":[193,224,253,260,277],"contr\u00f4le":[194],"lesquels":[197],"l'espace":[198,225],"d'\u00e9tat":[199],"et":[200,274],"le":[201,215],"temps":[202],"sont":[203],"variables":[205],"continues.":[206],"Nous":[207,243],"montrons":[208],"que":[209],"les":[210,218,257],"algorithmes":[211],"habituellement":[212],"utilis\u00e9s,":[213],"comme":[214],"utilisant":[217],"propri\u00e9t\u00e9s":[219,258],"statistiques":[220],"successions":[222],"d'\u00e9tats":[223],"discr\u00e9tis\u00e9,":[226],"ne":[227],"pas.":[229],"La":[230],"principale":[231],"raison":[232],"en":[233,255,265],"est":[234,283],"la":[235,261,275,280],"perte":[236],"du":[237],"caract\u00e8re":[238],"Markovien":[239],"\u00e9tats":[241],"successifs.":[242],"ici":[245],"d'utiliser":[246],"une":[247],"m\u00e9thode":[248],"aux":[249],"diff\u00e9rences":[250],"finies,":[251],"permettant":[252],"prendre":[254],"consid\u00e9ration":[256],"g\u00e9om\u00e9triques":[259],"dynamique":[262],"d'\u00e9tat.":[263],"Il":[264],"r\u00e9sulte":[266],"algorithme,":[268],"appel\u00e9":[269],"learning\",":[273],"preuve":[276],"vers":[279],"solution":[281],"optimale":[282],"donn\u00e9e.":[284]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W20823384","counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-21T10:27:49.728292","created_date":"2016-06-24T00:00:00"}
