{"id":"https://openalex.org/W2150147323","doi":null,"title":"The Asymptotic Convergence-Rate of Q-learning","display_name":"The Asymptotic Convergence-Rate of Q-learning","publication_year":1997,"publication_date":"1997-12-01","ids":{"openalex":"https://openalex.org/W2150147323","mag":"2150147323"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.554","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ualberta.ca/%7Eszepesva/papers/nips97.ps.pdf","raw_type":"text"},"volume":null,"type":"article","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/A5069856068","display_name":"Csaba Szepesv\u00e1ri","orcid":"https://orcid.org/0000-0002-9286-2892","observed_orcids":["https://orcid.org/0000-0002-9286-2892"]},"institutions":[{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Csaba Szepesv\u00e1ri","raw_affiliation_strings":["Research Group on Artificial Intelligence, J\u00f3zsef Attila University, Szeged, Hungary and Associative Computing, Inc., Budapest, Hungary#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-9286-2892","affiliations":[{"raw_affiliation_string":"Research Group on Artificial Intelligence, J\u00f3zsef Attila University, Szeged, Hungary and Associative Computing, Inc., Budapest, Hungary#TAB#","institution_ids":["https://openalex.org/I4210152167"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5069856068"],"corresponding_institution_ids":["https://openalex.org/I4210152167"],"apc_list":null,"apc_paid":null,"fwci":0.8791,"has_fulltext":false,"cited_by_count":116,"citation_normalized_percentile":{"value":0.74985657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"10","issue":null,"first_page":"1064","last_page":"1070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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":0.9955999851226807,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.00139999995008111,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0010000000474974513,"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/q-learning","display_name":"Q-learning","score":1.0},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.8169999718666077},{"id":"https://openalex.org/keywords/discounted-markov-decision-processes","display_name":"discounted Markov decision processes","score":0.9649999737739563},{"id":"https://openalex.org/keywords/asymptotic-convergence","display_name":"asymptotic convergence","score":0.6190000176429749},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.7379999756813049},{"id":"https://openalex.org/keywords/stationary-distribution","display_name":"stationary distribution","score":0.7630000114440918},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6589999794960022}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6610323786735535},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5481848120689392},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5374643802642822},{"id":"https://openalex.org/C6177178","wikidata":"https://www.wikidata.org/wiki/Q10998070","display_name":"Discounting","level":2,"score":0.4388554096221924},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.419898122549057},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3989188075065613},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3618004322052002},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33159878849983215},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.24856036901474},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1448400318622589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12220415472984314},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11704134941101074},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.07335564494132996},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.554","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ualberta.ca/%7Eszepesva/papers/nips97.ps.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.4792","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.4792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ualberta.ca/~szepesva/papers/nips97.ps.pdf","raw_type":"text"},{"id":"mag:2150147323","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/1383-the-asymptotic-convergence-rate-of-q-learning.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1548889916","https://openalex.org/W1576452626","https://openalex.org/W1605318140","https://openalex.org/W1626977535","https://openalex.org/W1991513691","https://openalex.org/W2066579401","https://openalex.org/W2101915445","https://openalex.org/W2119567691","https://openalex.org/W2125510930","https://openalex.org/W2147750403","https://openalex.org/W2165131254","https://openalex.org/W2798579099","https://openalex.org/W3011120880"],"related_works":["https://openalex.org/W7099405500","https://openalex.org/W7096416864","https://openalex.org/W32403112","https://openalex.org/W7100702781","https://openalex.org/W4251266081","https://openalex.org/W1557517019","https://openalex.org/W2949578685","https://openalex.org/W2118686230","https://openalex.org/W2973067663","https://openalex.org/W7097283377"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"show":[4],"that":[5,39,73],"for":[6],"discounted":[7],"MDPs":[8],"with":[9],"discount":[10],"factor>":[11],"1=2":[12,29],"the":[13,40,55,58,82,91],"asymptotic":[14],"rate":[15],"of":[16,18,57],"convergence":[17],"Q-learning":[19],"is":[20,54],"O(1=t":[21],"R(1":[22,25],"\ufffd))":[23],"if":[24],"\ufffd":[26],")":[27],"<":[28],"and":[30,60,78,84],"O":[31],"(":[32],"p":[33],"log":[34,35],"t=t)":[36],"otherwise":[37],"provided":[38,72],"state-action":[41,62,86],"pairs":[42],"are":[43],"sampled":[44],"from":[45],"a":[46],"xed":[47],"probability":[48],"distribution.":[49,93],"Here":[50],"R":[51],"=":[52],"pmin=pmax":[53],"ratio":[56],"minimum":[59,83],"maximum":[61,85],"occupation":[63,87],"frequencies.":[64],"The":[65],"results":[66],"extend":[67],"to":[68,90],"convergent":[69],"on-line":[70],"learning":[71],"pmin>":[74],"0,":[75],"where":[76],"pmin":[77],"pmax":[79],"now":[80],"become":[81],"frequencies":[88],"corresponding":[89],"stationary":[92],"1":[94]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}