{"id":"https://openalex.org/W2071983464","doi":"https://doi.org/10.1137/s0363012997331639","title":"The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning","display_name":"The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W2071983464","doi":"https://doi.org/10.1137/s0363012997331639","mag":"2071983464"},"language":"en","primary_location":{"id":"doi:10.1137/s0363012997331639","is_oa":false,"landing_page_url":"https://doi.org/10.1137/s0363012997331639","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","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/A5018541798","display_name":"Vivek S. Borkar","orcid":"https://orcid.org/0000-0003-0756-5402"},"institutions":[{"id":"https://openalex.org/I11947397","display_name":"Tata Institute of Fundamental Research","ror":"https://ror.org/03ht1xw27","country_code":"IN","type":"education","lineage":["https://openalex.org/I11947397","https://openalex.org/I2799351866","https://openalex.org/I3149292468"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"V. S. Borkar","raw_affiliation_strings":["School of Technology and Computer Science, Tata Institute of Fundamental Research, Mum-bai 400005, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Technology and Computer Science, Tata Institute of Fundamental Research, Mum-bai 400005, India","institution_ids":["https://openalex.org/I11947397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047988825","display_name":"Sean Meyn","orcid":"https://orcid.org/0000-0002-8558-365X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. P. Meyn","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018541798"],"corresponding_institution_ids":["https://openalex.org/I11947397"],"apc_list":null,"apc_paid":null,"fwci":8.2501,"has_fulltext":false,"cited_by_count":528,"citation_normalized_percentile":{"value":0.97392463,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"38","issue":"2","first_page":"447","last_page":"469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10067","display_name":"Stochastic processes and financial applications","score":0.9912999868392944,"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"}},"topics":[{"id":"https://openalex.org/T10067","display_name":"Stochastic processes and financial applications","score":0.9912999868392944,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9836999773979187,"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":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/stochastic-approximation","display_name":"Stochastic approximation","score":0.8006043434143066},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.760525107383728},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6551353931427002},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6323978900909424},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5958942770957947},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5846181511878967},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5709951519966125},{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.45449841022491455},{"id":"https://openalex.org/keywords/exponential-stability","display_name":"Exponential stability","score":0.4492437541484833},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40419942140579224},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.384380578994751},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.20244815945625305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11059236526489258},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.08747479319572449},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.0676434338092804}],"concepts":[{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.8006043434143066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.760525107383728},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6551353931427002},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6323978900909424},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5958942770957947},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5846181511878967},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5709951519966125},{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.45449841022491455},{"id":"https://openalex.org/C167964875","wikidata":"https://www.wikidata.org/wiki/Q17011487","display_name":"Exponential stability","level":3,"score":0.4492437541484833},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40419942140579224},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.384380578994751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.20244815945625305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11059236526489258},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.08747479319572449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0676434338092804},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1137/s0363012997331639","is_oa":false,"landing_page_url":"https://doi.org/10.1137/s0363012997331639","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","raw_type":"journal-article"},{"id":"pmh:oai:eprints.iisc.ac.in:1737","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.219.6825","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.219.6825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://black.csl.uiuc.edu/~meyn/pages/ode.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.42.8952","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.42.8952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://black.csl.uiuc.edu/~meyn/pages/ode.PS","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310071","display_name":"Indian Institute of Science","ror":"https://ror.org/04dese585"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W649943522","https://openalex.org/W1568229137","https://openalex.org/W1576452626","https://openalex.org/W1595277102","https://openalex.org/W1973403707","https://openalex.org/W1988466436","https://openalex.org/W1995713768","https://openalex.org/W2011720124","https://openalex.org/W2028493795","https://openalex.org/W2065134213","https://openalex.org/W2080631849","https://openalex.org/W2082261506","https://openalex.org/W2094364653","https://openalex.org/W2102982586","https://openalex.org/W2147750403","https://openalex.org/W2154204727","https://openalex.org/W2165131254","https://openalex.org/W2531891978","https://openalex.org/W4231022371","https://openalex.org/W4302033506"],"related_works":["https://openalex.org/W2371448224","https://openalex.org/W3134495997","https://openalex.org/W2363680170","https://openalex.org/W2376428685","https://openalex.org/W4256082577","https://openalex.org/W625783435","https://openalex.org/W2048742619","https://openalex.org/W2384641672","https://openalex.org/W2742179975","https://openalex.org/W2032841357"],"abstract_inverted_index":{"It":[0,41],"is":[1,11,42],"shown":[2],"here":[3],"that":[4,44,66,91],"stability":[5,16],"of":[6,17,29,35,52,69,82],"the":[7,14,18,30,45,63,88,101],"stochastic":[8,71],"approximation":[9,72],"algorithm":[10],"implied":[12],"by":[13],"asymptotic":[15],"origin":[19],"for":[20,55,62,87,100],"an":[21],"associated":[22],"ODE.":[23],"This":[24],"in":[25],"turn":[26],"implies":[27],"convergence":[28],"algorithm.":[31],"Several":[32],"specific":[33],"classes":[34],"algorithms":[36,73,97],"are":[37,74,98],"considered":[38],"as":[39],"applications.":[40],"found":[43],"results":[46,54],"provide":[47],"(i)":[48],"a":[49,60,67,79,85],"simpler":[50],"derivation":[51],"known":[53],"reinforcement":[56],"learning":[57],"algorithms;":[58],"(ii)":[59],"proof":[61,86],"first":[64,89],"time":[65,90],"class":[68],"asynchronous":[70,92],"convergent":[75,99],"without":[76],"using":[77],"any":[78],"priori":[80],"assumption":[81],"stability;":[83],"(iii)":[84],"adaptive":[93],"critic":[94],"and":[95],"Q-learning":[96],"average":[102],"cost":[103],"optimal":[104],"control":[105],"problem.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":28},{"year":2021,"cited_by_count":60},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":42},{"year":2018,"cited_by_count":35},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":23},{"year":2012,"cited_by_count":21}],"updated_date":"2026-06-05T09:01:59.212387","created_date":"2025-10-10T00:00:00"}