{"id":"https://openalex.org/W2130746277","doi":"https://doi.org/10.1007/bfb0026710","title":"A general convergence method for Reinforcement Learning in the continuous case","display_name":"A general convergence method for Reinforcement Learning in the continuous case","publication_year":1998,"publication_date":"1998-01-01","ids":{"openalex":"https://openalex.org/W2130746277","doi":"https://doi.org/10.1007/bfb0026710","mag":"2130746277"},"language":"en","primary_location":{"id":"doi:10.1007/bfb0026710","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bfb0026710","pdf_url":"https://link.springer.com/content/pdf/10.1007%2FBFb0026710.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007%2FBFb0026710.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006533777","display_name":"R\u00e9mi Munos","orcid":null},"institutions":[{"id":"https://openalex.org/I1312486979","display_name":"Local Initiatives Support Corporation","ror":"https://ror.org/04r5g1376","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1312486979"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"R\u00e9mi Munos","raw_affiliation_strings":["CEMAGREF, LISC, Parc de Tourvoie, BP 121, 92185, Antony Cedex, France","CEMAGREF, LISC, Parc de Tourvoie, Antony, France#TAB#"],"affiliations":[{"raw_affiliation_string":"CEMAGREF, LISC, Parc de Tourvoie, BP 121, 92185, Antony Cedex, France","institution_ids":["https://openalex.org/I1312486979"]},{"raw_affiliation_string":"CEMAGREF, LISC, Parc de Tourvoie, Antony, France#TAB#","institution_ids":["https://openalex.org/I1312486979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5006533777"],"corresponding_institution_ids":["https://openalex.org/I1312486979"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.815,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73065622,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"394","last_page":"405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958000183105469,"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":0.9958000183105469,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9650999903678894,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8792557716369629},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.7644258737564087},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7238839864730835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6923558712005615},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.6765236854553223},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6590086221694946},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6414489150047302},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6407001614570618},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.56666100025177},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5021460056304932},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.44195687770843506},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3748718500137329},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3249567151069641},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3160267770290375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24707797169685364},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.06512206792831421}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8792557716369629},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7644258737564087},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7238839864730835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6923558712005615},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.6765236854553223},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6590086221694946},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6414489150047302},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6407001614570618},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.56666100025177},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5021460056304932},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.44195687770843506},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3748718500137329},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3249567151069641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3160267770290375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24707797169685364},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.06512206792831421},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/bfb0026710","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bfb0026710","pdf_url":"https://link.springer.com/content/pdf/10.1007%2FBFb0026710.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-02577306v1","is_oa":false,"landing_page_url":"https://hal.inrae.fr/hal-02577306","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"European conference on machine learning, Chemnitz, DEU, 21-24 avril 1998, 1998, Germany. pp.12","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.1007/bfb0026710","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bfb0026710","pdf_url":"https://link.springer.com/content/pdf/10.1007%2FBFb0026710.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2130746277.pdf","grobid_xml":"https://content.openalex.org/works/W2130746277.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W20823384","https://openalex.org/W1505284970","https://openalex.org/W1558902221","https://openalex.org/W1583902426","https://openalex.org/W1964377184","https://openalex.org/W2009533501","https://openalex.org/W2067981016","https://openalex.org/W2166356462","https://openalex.org/W2177195156","https://openalex.org/W4302367620"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W4389475841","https://openalex.org/W2152670157","https://openalex.org/W2903299703","https://openalex.org/W4281791088","https://openalex.org/W2117282672","https://openalex.org/W4385342861","https://openalex.org/W1574958246","https://openalex.org/W2807018115"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}