{"id":"https://openalex.org/W4403586047","doi":"https://doi.org/10.1137/25m1769806","title":"Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning","display_name":"Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W4403586047","doi":"https://doi.org/10.1137/25m1769806"},"language":"en","primary_location":{"id":"doi:10.1137/25m1769806","is_oa":false,"landing_page_url":"https://doi.org/10.1137/25m1769806","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.03915","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014937312","display_name":"Huizhen Yu","orcid":"https://orcid.org/0000-0002-3673-0094"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Huizhen Yu","raw_affiliation_strings":["Corresponding author. Department of Computing Science, University of Alberta, Edmonton, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3673-0094","affiliations":[{"raw_affiliation_string":"Corresponding author. Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671214","display_name":"Yi Wan","orcid":"https://orcid.org/0000-0003-3325-1386"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yi Wan","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108498344","display_name":"Richard Sutton","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Richard S. Sutton","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":8.8388,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9391345,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"64","issue":"3","first_page":"1456","last_page":"1481"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.8233000040054321,"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"}},"topics":[{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.8233000040054321,"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/T10524","display_name":"Traffic control and management","score":0.7231000065803528,"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":0.8520293235778809},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.683735728263855},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6482491493225098},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5193520784378052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42781010270118713},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34254664182662964},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.26454442739486694},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24718886613845825},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.15433654189109802},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.05118641257286072}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8520293235778809},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.683735728263855},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6482491493225098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5193520784378052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42781010270118713},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34254664182662964},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26454442739486694},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24718886613845825},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.15433654189109802},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.05118641257286072}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1137/25m1769806","is_oa":false,"landing_page_url":"https://doi.org/10.1137/25m1769806","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:arXiv.org:2409.03915","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.03915","pdf_url":"https://arxiv.org/pdf/2409.03915","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2409.03915","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2409.03915","pdf_url":"https://arxiv.org/pdf/2409.03915","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.03915","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.03915","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.03915","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.03915","pdf_url":"https://arxiv.org/pdf/2409.03915","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3801747459","display_name":null,"funder_award_id":"DGECR-2024-00312","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G5290545508","display_name":null,"funder_award_id":"RGPIN-2024-04939","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320314212","display_name":"Alberta Machine Intelligence Institute","ror":null},{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2154204727","https://openalex.org/W2150123286","https://openalex.org/W1967049706","https://openalex.org/W1491706803","https://openalex.org/W1991667331","https://openalex.org/W1971048324","https://openalex.org/W2080631849","https://openalex.org/W2069738649","https://openalex.org/W4391410851","https://openalex.org/W2071983464","https://openalex.org/W2102982586","https://openalex.org/W1983817419","https://openalex.org/W162901799","https://openalex.org/W2334782222","https://openalex.org/W3087787603","https://openalex.org/W2049847128","https://openalex.org/W2128857696","https://openalex.org/W2111971348","https://openalex.org/W2147750403","https://openalex.org/W2025025900","https://openalex.org/W2081374871","https://openalex.org/W2161950876"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W2116677773","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291"],"abstract_inverted_index":{"This":[0],"paper":[1,99],"investigates":[2],"the":[3,54,60],"stability":[4,28],"and":[5,33,74,94,105],"convergence":[6,47,55],"properties":[7,62],"of":[8,31,63,72,85],"asynchronous":[9,50,64],"stochastic":[10],"approximation":[11],"(SA)":[12],"algorithms,":[13],"with":[14],"a":[15,27,68,79,83,97],"focus":[16],"on":[17,67],"extensions":[18],"relevant":[19],"to":[20,35],"average-reward":[21,103],"reinforcement":[22,89],"learning.":[23],"We":[24],"first":[25],"extend":[26],"proof":[29],"method":[30],"Borkar":[32],"Meyn":[34],"accommodate":[36],"more":[37],"general":[38],"noise":[39],"conditions":[40],"than":[41],"previously":[42],"considered,":[43],"thereby":[44],"yielding":[45],"broader":[46],"guarantees":[48],"for":[49,82,101],"SA.":[51],"To":[52],"sharpen":[53],"analysis,":[56],"we":[57],"further":[58],"examine":[59],"shadowing":[61],"SA,":[65],"building":[66],"dynamical":[69],"systems":[70],"approach":[71],"Hirsch":[73],"Bena\u00efm.":[75],"These":[76],"results":[77],"provide":[78],"theoretical":[80],"foundation":[81],"class":[84],"relative":[86],"value":[87],"iteration-based":[88],"learning":[90],"algorithms":[91],"--":[92,100],"developed":[93],"analyzed":[95],"in":[96],"companion":[98],"solving":[102],"Markov":[104],"semi-Markov":[106],"decision":[107],"processes.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2024-10-21T00:00:00"}