{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T09:15:18Z","timestamp":1768554918774,"version":"3.49.0"},"reference-count":23,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"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. Artif. Intell."],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1109\/tai.2021.3111142","type":"journal-article","created":{"date-parts":[[2021,9,13]],"date-time":"2021-09-13T17:21:35Z","timestamp":1631553695000},"page":"139-151","source":"Crossref","is-referenced-by-count":23,"title":["Deep Q-Learning: Theoretical Insights From an Asymptotic Analysis"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7547-8111","authenticated-orcid":false,"given":"Arunselvan","family":"Ramaswamy","sequence":"first","affiliation":[{"name":"Department of Computer Science, Paderborn University, Paderborn, Germany"}]},{"given":"Eyke","family":"H\u00fcllermeier","sequence":"additional","affiliation":[{"name":"Institute of Informatics, University of Munich, Munich, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref2","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","first-page":"486","article-title":"A theoretical analysis of deep Q-learning","author":"Yang"},{"key":"ref5","first-page":"8668","article-title":"Finite-sample analysis for SARSA with linear function approximation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zou","year":"2019"},{"key":"ref6","article-title":"Towards characterizing divergence in deep Q-learning","author":"Achiam"},{"key":"ref7","first-page":"1055","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":"ref8","first-page":"22327","article-title":"Agnostic $ Q$-learning with function approximation in deterministic systems: Near-optimal bounds on approximation error and sample complexity","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Du","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110623"},{"key":"ref10","first-page":"1283","article-title":"Provably efficient exploration in policy optimization","volume-title":"Int. Conf. Mach. Learn.","author":"Cai"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/379"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s12045-013-0136-x"},{"key":"ref13","volume-title":"Stochastic Approximation and Recursive Algorithms and Applications","volume":"35","author":"Kushner","year":"2003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511779398"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316962"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4848-0_10"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1142\/ASCAS"},{"key":"ref18","volume-title":"Artificial Neural Networks.","author":"Yegnanarayana","year":"2009"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3108492"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2005.06.005"},{"key":"ref21","volume-title":"Topology","author":"Munkres","year":"2000"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16684-6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/0315056"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/9741091\/09536409.pdf?arnumber=9536409","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:10:07Z","timestamp":1755911407000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9536409\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4]]},"references-count":23,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tai.2021.3111142","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4]]}}}