{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:28:25Z","timestamp":1771468105775,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"CSIRHRDG, India","award":["09\/1022(0088)2019-EMR-I"],"award-info":[{"award-number":["09\/1022(0088)2019-EMR-I"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Control Syst. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lcsys.2025.3551265","type":"journal-article","created":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T17:48:18Z","timestamp":1741888098000},"page":"21-26","source":"Crossref","is-referenced-by-count":1,"title":["A Weighted Smooth Q-Learning Algorithm"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2435-9774","authenticated-orcid":false,"given":"V.","family":"Antony Vijesh","sequence":"first","affiliation":[{"name":"Department of Mathematics, Indian Institute of Technology Indore, Indore, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3356-7986","authenticated-orcid":false,"given":"S. R.","family":"Shreyas","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Indian Institute of Technology Indore, Indore, India"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"ref2","article-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/bf00993306"},{"key":"ref6","first-page":"2613","article-title":"Double Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Hasselt"},{"key":"ref7","first-page":"2411","article-title":"Speedy Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Azar"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17334"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/lcsys.2019.2921158"},{"key":"ref10","first-page":"6815","article-title":"The mean-squared error of double Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Weng"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2912443"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/s1573-4412(05)80020-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3112851"},{"key":"ref14","first-page":"243","article-title":"An alternative softmax operator for reinforcement learning","volume-title":"Proc. ICML","volume":"70","author":"Asadi"},{"key":"ref15","volume-title":"Unified ODE analysis of smooth Q-learning algorithms","author":"Lee","year":"2024"},{"key":"ref16","first-page":"1992","article-title":"Reinforcement learning with dynamic Boltzmann softmax updates","volume-title":"Proc. IJCAI","author":"Pan"},{"key":"ref17","volume-title":"Smoothed Q-learning","author":"Barber","year":"2023"},{"key":"ref18","first-page":"287","article-title":"Convergence results for single-step on-policy RL algorithms","volume-title":"Proc. Mach. Learn.","volume":"38","author":"Singh"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-93-86279-38-5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref21","first-page":"5916","article-title":"Revisiting the softmax Bellman operator: New benefits and new perspective","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Song"},{"key":"ref22","first-page":"1125","article-title":"SBEED: Convergent reinforcement learning with nonlinear function approximation","volume-title":"Proc. ICML","author":"Dai"},{"issue":"1","key":"ref23","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1287\/moor.2023.1370","article-title":"Neural temporal difference and Q-learning provably converge to global optima","volume":"49","author":"Cai","year":"2024","journal-title":"Math. Oper. Res."},{"key":"ref24","first-page":"1","article-title":"Adaptive temperature tuning for mellowmax in deep reinforcement learning","volume-title":"Proc. NeurIPS Workshop Deep Reinforcement Learn.","author":"Kim"},{"key":"ref25","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. ICML","volume":"70","author":"Haarnoja"},{"key":"ref26","first-page":"2772","article-title":"Bridging the gap between value and policy-based reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Nachum"},{"key":"ref27","first-page":"202","article-title":"Taming the noise in reinforcement learning via soft updates","volume-title":"Proc. 32nd Conf. Uncertainty Artif. Intell.","author":"Fox"},{"key":"ref28","volume-title":"Finite-time error analysis of soft Q-learning: Switching system approach","author":"Jeong","year":"2024"},{"key":"ref29","first-page":"3455","article-title":"Weighted double Q-learning","volume-title":"Proc. IJCAI","author":"Zhang"},{"key":"ref30","first-page":"1","article-title":"Maxmin Q-learning: Controlling the estimation bias of Q-learning","volume-title":"Proc. ICLR","author":"Lan"},{"issue":"4","key":"ref31","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1016\/j.sysconle.2005.08.011","article-title":"Boundedness of iterates in Q-learning","volume":"55","author":"Gosavi","year":"2006","journal-title":"Syst. Control Lett."},{"key":"ref32","first-page":"16628","article-title":"Finite-time analysis for double Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xiong"},{"key":"ref33","first-page":"15556","article-title":"A unified switching system perspective and convergence analysis of Q-learning algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lee"},{"key":"ref34","volume-title":"Convergence of batch asynchronous stochastic approximation with applications to reinforcement learning","author":"Karandikar","year":"2021"},{"key":"ref35","volume-title":"Neuro-Dynamic Programming","author":"Bertsekas","year":"1996"},{"key":"ref36","volume-title":"Insights in reinforcement learning","author":"Hasselt","year":"2011"},{"issue":"4","key":"ref37","doi-asserted-by":"crossref","first-page":"2311","DOI":"10.1093\/imanum\/draa038","article-title":"Accurately computing the log-sum-EXP and softmax functions","volume":"41","author":"Blanchard","year":"2021","journal-title":"IMA J. Numer. Anal."},{"key":"ref38","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"}],"container-title":["IEEE Control Systems Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782633\/10939047\/10925426.pdf?arnumber=10925426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T04:38:56Z","timestamp":1743223136000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10925426\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/lcsys.2025.3551265","relation":{},"ISSN":["2475-1456"],"issn-type":[{"value":"2475-1456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}