{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T12:52:16Z","timestamp":1782391936077,"version":"3.54.5"},"reference-count":33,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"3","funder":[{"DOI":"10.13039\/100013373","name":"Alberta Machine Intelligence Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013373","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2024-04939"],"award-info":[{"award-number":["RGPIN-2024-04939"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["DGECR-2024-00312"],"award-info":[{"award-number":["DGECR-2024-00312"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Control Optim."],"published-print":{"date-parts":[[2026,6,30]]},"DOI":"10.1137\/25m1769806","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T07:15:51Z","timestamp":1779261351000},"page":"1456-1481","source":"Crossref","is-referenced-by-count":1,"title":["Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning"],"prefix":"10.1137","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3673-0094","authenticated-orcid":true,"given":"Huizhen","family":"Yu","sequence":"first","affiliation":[{"name":"Corresponding author. Department of Computing Science, University of Alberta, Edmonton, Canada."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wan","sequence":"additional","affiliation":[{"name":"Department of Computing Science, University of Alberta, Edmonton, Canada."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard S.","family":"Sutton","sequence":"additional","affiliation":[{"name":"Department of Computing Science, University of Alberta, Edmonton, Canada."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2026,5,20]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012999361974"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012998346621"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012993253534"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0096509"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF02218617"},{"key":"ref6","volume-title":"Neural-Dynamic Programming","author":"Bertsekas D. P.","year":"1996"},{"key":"ref7","volume-title":"Stability Theory of Dynamical Systems","author":"Bhatia N. P.","year":"2002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2011.04.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012995282784"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012998345913"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8277-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/81.563625"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0396(75)90065-0"},{"key":"ref15","doi-asserted-by":"crossref","unstructured":"C. C. Conley, Isolated Invariant Sets and the Morse Index, CBMS Regional Conference Series in Mathematics 38, AMS, Providence, RI, 1978.","DOI":"10.1090\/cbms\/038"},{"key":"ref16","volume-title":"Martingale Limit Theory and Its Application","author":"Hall P.","year":"1980"},{"key":"ref17","series-title":"Lecture Notes in Pure Appl. Math. 152","first-page":"87","volume-title":"Differential Equations, Dynamical Systems and Control Science","author":"Hirsch M. W.","year":"1994"},{"key":"ref18","volume-title":"Stochastic Approximation and Recursive Algorithms and Applications","author":"Kushner H. J.","year":"2003","edition":"2"},{"key":"ref19","volume-title":"Discrete Parameter Martingales","author":"Neveu J.","year":"1975"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3026269"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(71)90094-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2.4.360"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/moor.3.4.308"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022689125041"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0601-9"},{"key":"ref27","first-page":"22758","volume-title":"Neural Inform. Proc. Syst.","author":"Wan Y.","year":"2021"},{"key":"ref28","first-page":"10653","volume":"139","author":"Wan Y.","year":"2021","journal-title":"Proc. Mach. Learn. Res. (PMLR)"},{"key":"ref29","unstructured":"Y. Wan, H. Yu, and R. S. Sutton, On Convergence of Average-Reward Q-learning in Weakly Communicating Markov Decision Processes, preprint, arXiv:2408.16262, 2024."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(63)90017-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1120.0562"},{"key":"ref32","unstructured":"H. Yu, Y. Wan, and R. S. Sutton,\n                      Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning\n                      , preprint, arXiv:2409.03915, 2025, (extended report version of this paper)."},{"key":"ref33","unstructured":"H. Yu, Y. Wan, and R. S. Sutton, Average-Reward Reinforcement Learning in Semi-Markov Decision Processes via Relative Value Iteration, preprint, arXiv:2512.06218, 2025."}],"container-title":["SIAM Journal on Control and Optimization"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T07:16:07Z","timestamp":1779261367000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/25M1769806"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,20]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1137\/25M1769806"],"URL":"https:\/\/doi.org\/10.1137\/25m1769806","relation":{},"ISSN":["0363-0129","1095-7138"],"issn-type":[{"value":"0363-0129","type":"print"},{"value":"1095-7138","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,20]]}}}