{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T21:09:28Z","timestamp":1774991368436,"version":"3.50.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tac.2025.3631342","type":"journal-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:52:03Z","timestamp":1762800723000},"page":"2482-2495","source":"Crossref","is-referenced-by-count":0,"title":["Does DQN Learn?"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7323-2975","authenticated-orcid":false,"given":"Aditya","family":"Gopalan","sequence":"first","affiliation":[{"name":"Department of Electrical Communication Engineering, Indian Institute of Science (IISc), Bengaluru, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5066-6589","authenticated-orcid":false,"given":"Gugan","family":"Thoppe","sequence":"additional","affiliation":[{"name":"Computer Science and Automation Department, Indian Institute of Science (IISc), Bengaluru, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref3","article-title":"Chattering in SARSA (lambda)-a CMU learning lab internal report","author":"Gordon","year":"1996"},{"key":"ref4","first-page":"996","article-title":"Reinforcement learning with function approximation converges to a region","volume-title":"Proc. 14th Int. Conf. Neural Inf. Process. Syst.","author":"Gordon","year":"2000"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1004641123405"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-1005-3"},{"key":"ref7","article-title":"Understanding the pathologies of approximate policy evaluation when combined with greedification in reinforcement learning","author":"Young","year":"2020"},{"issue":"318","key":"ref8","first-page":"1","article-title":"Empirical design in reinforcement learning","volume":"25","author":"Patterson","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49097-3_2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483244"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0096509"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-81-951961-1-1"},{"key":"ref13","first-page":"19412","article-title":"A new convergent variant of Q-learning with linear function approximation","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Carvalho","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390240"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110623"},{"key":"ref16","first-page":"8668","article-title":"Finite-sample analysis for SARSA with linear function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zou","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-69512-4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/0-306-48332-7_333"},{"key":"ref19","first-page":"41613","article-title":"On the convergence of SARSA with linear function approximation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2023"},{"key":"ref20","first-page":"2537","article-title":"The phenomenon of policy churn","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schaul","year":"2022"},{"key":"ref21","first-page":"486","article-title":"A theoretical analysis of deep Q-learning","volume-title":"2nd Annu. Conf. Learn. Dyn. Control","author":"Fan","year":"2020"},{"key":"ref22","first-page":"10555","article-title":"A finite-time analysis of Q-learning with neural network function approximation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2020"},{"key":"ref23","first-page":"15556","article-title":"A unified switching system perspective and convergence analysis of Q-learning algorithms","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Lee","year":"2020"},{"key":"ref24","first-page":"719","article-title":"Toward off-policy learning control with function approximation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Maei","year":"2010"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10626-015-0216-z"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-76928-4_10"},{"key":"ref27","first-page":"1167","article-title":"Classes of multiagent Q-learning dynamics with epsilon-greedy exploration","volume-title":"Proc. 27th Int. Conf. Mach. Learn.","author":"Wunder","year":"2010"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3580507.3597726"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2008.919306"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-015-7793-9"},{"key":"ref31","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2005.08.011"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012904439301"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9\/11458056\/11236998.pdf?arnumber=11236998","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T19:55:07Z","timestamp":1774986907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11236998\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":34,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tac.2025.3631342","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":[[2026,4]]}}}