{"id":"https://openalex.org/W4403277277","doi":"https://doi.org/10.1109/access.2024.3476564","title":"Finite-Time Analysis of Asynchronous Q-Learning Under Diminishing Step-Size From Control-Theoretic View","display_name":"Finite-Time Analysis of Asynchronous Q-Learning Under Diminishing Step-Size From Control-Theoretic View","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403277277","doi":"https://doi.org/10.1109/access.2024.3476564"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3476564","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3476564","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3476564","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006683710","display_name":"Han-Dong Lim","orcid":"https://orcid.org/0000-0002-1515-5836"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Han-Dong Lim","raw_affiliation_strings":["Department of Electrical Engineering, KAIST, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-1515-5836","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100654317","display_name":"Donghwan Lee","orcid":"https://orcid.org/0000-0002-4962-8478"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Donghwan Lee","raw_affiliation_strings":["Department of Electrical Engineering, KAIST, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-4962-8478","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2408,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64799418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"149916","last_page":"149939"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.963100016117096,"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/T10320","display_name":"Neural Networks and Applications","score":0.963100016117096,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9265000224113464,"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/T10323","display_name":"Analog and Mixed-Signal Circuit Design","score":0.9251999855041504,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/computer-science","display_name":"Computer science","score":0.661918580532074},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6459155678749084},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5004198551177979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2283150851726532},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1632823944091797}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.661918580532074},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6459155678749084},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5004198551177979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2283150851726532},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1632823944091797}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3476564","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3476564","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b0beddc06d8d4ee298c766cf54987ed5","is_oa":true,"landing_page_url":"https://doaj.org/article/b0beddc06d8d4ee298c766cf54987ed5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 149916-149939 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3476564","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3476564","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1552094772","https://openalex.org/W1865368880","https://openalex.org/W1941445455","https://openalex.org/W1977655452","https://openalex.org/W1990585910","https://openalex.org/W1992208280","https://openalex.org/W1994616650","https://openalex.org/W1999254175","https://openalex.org/W2025719457","https://openalex.org/W2038874684","https://openalex.org/W2062974796","https://openalex.org/W2071983464","https://openalex.org/W2118741873","https://openalex.org/W2145339207","https://openalex.org/W2150147323","https://openalex.org/W2493209382","https://openalex.org/W2605634350","https://openalex.org/W2885549115","https://openalex.org/W2963467914","https://openalex.org/W2963616027","https://openalex.org/W2989847975","https://openalex.org/W3041202696","https://openalex.org/W3123348991","https://openalex.org/W3146739461","https://openalex.org/W4233061323","https://openalex.org/W4233696721","https://openalex.org/W4243772471","https://openalex.org/W4382064684","https://openalex.org/W4390938885","https://openalex.org/W6677067356","https://openalex.org/W6677826109","https://openalex.org/W6754580366","https://openalex.org/W6757184387","https://openalex.org/W6763578770","https://openalex.org/W6771807793","https://openalex.org/W6773637655","https://openalex.org/W6774445294","https://openalex.org/W6775522024","https://openalex.org/W6779539656","https://openalex.org/W6784926121","https://openalex.org/W6785894376","https://openalex.org/W6789785855","https://openalex.org/W6790768012"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2116677773","https://openalex.org/W2155261584","https://openalex.org/W2584231425","https://openalex.org/W2150611273","https://openalex.org/W2390279801","https://openalex.org/W4207086172","https://openalex.org/W2358668433","https://openalex.org/W2042919702"],"abstract_inverted_index":{"Q-learning":[0,16,32,61,82,172],"has":[1,17,39],"long":[2,35],"been":[3,18],"one":[4],"of":[5,15,31,49,59,81,94,117,120],"the":[6,95,118,121,125,128,132,138,141],"most":[7,116],"popular":[8],"reinforcement":[9],"learning":[10],"algorithms,":[11],"and":[12,102,160],"theoretical":[13],"analysis":[14,30,58,98,142,152,166],"an":[19],"active":[20,44],"research":[21],"topic":[22],"for":[23,86,165],"decades.":[24],"Although":[25],"researches":[26],"on":[27,171],"asymptotic":[28],"convergence":[29,38],"have":[33],"a":[34,55,67,75],"tradition,":[36],"non-asymptotic":[37],"only":[40],"recently":[41],"come":[42],"under":[43,62],"study.":[45],"The":[46,150],"main":[47],"goal":[48],"this":[50],"paper":[51],"is":[52,110],"to":[53,112,136,167,177],"investigate":[54],"new":[56,162],"finite-time":[57],"asynchronous":[60],"Markovian":[63],"observation":[64],"models":[65],"via":[66,173],"control":[68],"system":[69,79,97],"viewpoint.":[70],"In":[71,127],"particular,":[72],"we":[73,130],"introduce":[74],"discrete-time":[76,178],"time-varying":[77],"switching":[78,96,179],"model":[80],"with":[83,99],"diminishing":[84,146],"step-sizes":[85,147],"our":[87,169],"analysis,":[88],"which":[89],"significantly":[90],"improves":[91],"recent":[92],"development":[93],"constant":[100],"step-sizes,":[101],"leads":[103],"to$\\mathcal":[104],"{O}(\\sqrt":[105],"{{\\log":[106],"k}/{k}})$convergence":[107],"rate":[108],"that":[109],"comparable":[111],"or":[113],"better":[114],"than":[115],"state":[119],"art":[122],"results":[123],"in":[124,140,148,154],"literature.":[126],"meanwhile,":[129],"consider":[131],"continuous-time":[133],"Lyapunov":[134],"equation":[135],"avoid":[137],"difficulty":[139],"posed":[143],"by":[144],"using":[145],"discrete-time.":[149],"proposed":[151],"brings":[153],"additional":[155],"insights,":[156],"covers":[157],"different":[158],"scenarios,":[159],"provides":[161],"simplified":[163],"templates":[164],"deepen":[168],"understanding":[170],"its":[174],"unique":[175],"connection":[176],"systems.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}