{"id":"https://openalex.org/W2147750403","doi":"https://doi.org/10.1007/bf00993306","title":"Asynchronous Stochastic Approximation and Q-Learning","display_name":"Asynchronous Stochastic Approximation and Q-Learning","publication_year":1994,"publication_date":"1994-09-01","ids":{"openalex":"https://openalex.org/W2147750403","doi":"https://doi.org/10.1007/bf00993306","mag":"2147750403"},"language":"en","primary_location":{"id":"doi:10.1007/bf00993306","doi":"https://doi.org/10.1007/bf00993306","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00993306","pdf_url":"https://link.springer.com/content/pdf/10.1007%2FBF00993306.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007%2FBF00993306.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108523422","display_name":"John N. Tsitsiklis","orcid":"https://orcid.org/0000-0003-2658-8239","observed_orcids":["https://orcid.org/0000-0003-2658-8239"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John N. Tsitsiklis","raw_affiliation_strings":["Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, 02139, Cambridge, MA","Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, 02139"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, 02139, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, 02139","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108523422"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":{"value":3290,"currency":"USD","value_usd":3290},"apc_paid":null,"fwci":12.5255,"has_fulltext":true,"cited_by_count":854,"citation_normalized_percentile":{"value":0.988895,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"16","issue":"3","first_page":"185","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9932000041007996,"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":0.9932000041007996,"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":0.003800000064074993,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.8370000123977661},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.8479999899864197},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.718999981880188},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8379999995231628},{"id":"https://openalex.org/keywords/asynchronous-algorithms","display_name":"asynchronous algorithms","score":0.546999990940094}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7294235825538635},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7040852308273315},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6878458261489868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6500030755996704},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5950178503990173},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5119615793228149},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5058807730674744},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4646188020706177},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.45884808897972107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4355711340904236},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41511625051498413},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.411819189786911},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3350558876991272},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29427024722099304},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07591590285301208},{"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/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/bf00993306","doi":"https://doi.org/10.1007/bf00993306","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00993306","pdf_url":"https://link.springer.com/content/pdf/10.1007%2FBF00993306.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"doi:10.1023/a:1022689125041","doi":"https://doi.org/10.1023/a:1022689125041","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1022689125041","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1022689125041.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/bf00993306","doi":"https://doi.org/10.1007/bf00993306","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00993306","pdf_url":"https://link.springer.com/content/pdf/10.1007%2FBF00993306.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2010061944","display_name":"Intelligent Feedback Systems","funder_award_id":"9216531","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2147750403.pdf","grobid_xml":"https://content.openalex.org/works/W2147750403.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1603765807","https://openalex.org/W1963747782","https://openalex.org/W1990005421","https://openalex.org/W2059287472","https://openalex.org/W2077274021","https://openalex.org/W2081287319","https://openalex.org/W2100677568","https://openalex.org/W2119380668","https://openalex.org/W2135677363","https://openalex.org/W2154834860","https://openalex.org/W2158091072","https://openalex.org/W2235056388","https://openalex.org/W2341072966","https://openalex.org/W3011120880","https://openalex.org/W4395684075"],"related_works":["https://openalex.org/W3173526354","https://openalex.org/W3190031629","https://openalex.org/W3003165689","https://openalex.org/W2071983464","https://openalex.org/W2993442395","https://openalex.org/W7214813640","https://openalex.org/W2151661095","https://openalex.org/W2419084655","https://openalex.org/W2150123286","https://openalex.org/W4404650081"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":40},{"year":2025,"cited_by_count":54},{"year":2024,"cited_by_count":48},{"year":2023,"cited_by_count":44},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":78},{"year":2020,"cited_by_count":58},{"year":2019,"cited_by_count":53},{"year":2018,"cited_by_count":39},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":33},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":22}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}