{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T04:52:00Z","timestamp":1777783920974,"version":"3.51.4"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ministry of Electronics and Information Technology, Government of India"},{"name":"5G Research and Building Next Gen Solutions for Indian Market"},{"DOI":"10.13039\/501100001852","name":"Indo-French Centre for the Promotion of Advanced Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001852","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Machine Learning for Network Analytics"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1109\/tac.2021.3108121","type":"journal-article","created":{"date-parts":[[2021,8,27]],"date-time":"2021-08-27T19:50:21Z","timestamp":1630093821000},"page":"3722-3729","source":"Crossref","is-referenced-by-count":23,"title":["Online Reinforcement Learning of Optimal Threshold Policies for Markov Decision Processes"],"prefix":"10.1109","volume":"67","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9955-9514","authenticated-orcid":false,"given":"Arghyadip","family":"Roy","sequence":"first","affiliation":[{"name":"Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana-Champaign, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0756-5402","authenticated-orcid":false,"given":"Vivek","family":"Borkar","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Indian Institute of Technology Bombay, Mumbai, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1608-3413","authenticated-orcid":false,"given":"Abhay","family":"Karandikar","sequence":"additional","affiliation":[{"name":"Director, Indian Institute of Technology Kanpur (on leave from Department of Electrical Engineering, IIT Bombay, Mumbai 400076, India), Kanpur, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5082-0179","authenticated-orcid":false,"given":"Prasanna","family":"Chaporkar","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Indian Institute of Technology Bombay, Mumbai, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3306309.3306321"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11134-009-9109-x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref5","volume-title":"Dynamic Programming","author":"Bellman","year":"1957"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"issue":"34","key":"ref7","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref8","first-page":"4863","article-title":"Is Q-learning provably efficient?","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Jin","year":"2018"},{"key":"ref9","first-page":"10170","article-title":"Model-free reinforcement learning in infinite-horizon average-reward Markov decision processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wei","year":"2020"},{"key":"ref10","article-title":"A model-free learning algorithm for infinite-horizon average-reward MDPs with near-optimal regret","author":"Jafarnia-Jahromi","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2008.080514"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2012.36"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.08.007"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_72229"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.925856"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1287\/opre.50.5.796.365"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1070.0240"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2012.2213850"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2027735"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2973125"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2926160"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2953089"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-93-86279-38-5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.2974216"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/NCC.2012.6176889"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019177307418"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11134-006-8307-z"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2009.08.070350"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00186-006-0137-6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2892983"},{"key":"ref31","volume-title":"Stochastic Modeling and the Theory of Queues","author":"Wolff","year":"1989"},{"key":"ref32","article-title":"Discrete event stochastic processes","volume-title":"Lecture Notes Eng. Curriculum","author":"Kumar","year":"2012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/9.905687"},{"key":"ref34","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Sutton","year":"2000"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.43.8.1093"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1561\/9781601980298"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3108121"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/INDIANCC.2018.8307959"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/S036301299731669X"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012999361974"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/9809927\/09524527.pdf?arnumber=9524527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:32:35Z","timestamp":1705015955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9524527\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":41,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tac.2021.3108121","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}