{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:24:00Z","timestamp":1780637040244,"version":"3.54.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Fund of China","doi-asserted-by":"publisher","award":["U1713208"],"award-info":[{"award-number":["U1713208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Fund of China","doi-asserted-by":"publisher","award":["61876084"],"award-info":[{"award-number":["61876084"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Fund of China","doi-asserted-by":"publisher","award":["62006119"],"award-info":[{"award-number":["62006119"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu","doi-asserted-by":"publisher","award":["BK20190444"],"award-info":[{"award-number":["BK20190444"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"\u201c111\u201d Program","award":["B13022"],"award-info":[{"award-number":["B13022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tnnls.2022.3203024","type":"journal-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T19:47:25Z","timestamp":1664308045000},"page":"5269-5279","source":"Crossref","is-referenced-by-count":27,"title":["Action Candidate Driven Clipped Double Q-Learning for Discrete and Continuous Action Tasks"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4536-5252","authenticated-orcid":false,"given":"Haobo","family":"Jiang","sequence":"first","affiliation":[{"name":"PCA Laboratory, the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, and the Jiangsu Key Laboratory of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4817-0618","authenticated-orcid":false,"given":"Guangyu","family":"Li","sequence":"additional","affiliation":[{"name":"PCA Laboratory, the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, and the Jiangsu Key Laboratory of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Xie","sequence":"additional","affiliation":[{"name":"PCA Laboratory, the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, and the Jiangsu Key Laboratory of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4800-832X","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"PCA Laboratory, the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, and the Jiangsu Key Laboratory of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"103","article-title":"Reinforcement learning: An introduction","volume":"21","author":"Thrun","year":"2000","journal-title":"AI Mag."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref3","volume-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref4","first-page":"1","article-title":"Rudder: Return decomposition for delayed rewards","volume-title":"Proc. NIPS","author":"Arjona-Medina"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.2200\/s00268ed1v01y201005aim009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3116063"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1995.478953"},{"key":"ref9","first-page":"1","article-title":"Issues in using function approximation for reinforcement learning","volume-title":"Proc. Connectionist Models Summer School","author":"Thrun"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390288"},{"issue":"11","key":"ref11","first-page":"2413","article-title":"Reinforcement learning in finite MDPs: PAC analysis","volume":"10","author":"Strehl","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","article-title":"Deep reinforcement learning and the deadly triad","volume-title":"arXiv:1812.02648","author":"van Hasselt","year":"2018"},{"key":"ref13","volume-title":"Insights in Reinforcement Learning","author":"van Hasselt","year":"2011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3106635"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143955"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref17","first-page":"3434","article-title":"Boosted fitted Q-iteration","volume-title":"Proc. ICML","author":"Tosatto"},{"key":"ref18","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"Ernst","year":"2005","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"ref19","first-page":"41","article-title":"Double delayed Q-learning","volume":"16","author":"Abed-Alguni","year":"2018","journal-title":"Int. J. Artif. Intell."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref21","article-title":"Deep attention recurrent Q-network","volume-title":"arXiv:1512.01693","author":"Sorokin","year":"2015"},{"key":"ref22","first-page":"486","article-title":"A theoretical analysis of deep Q-learning","volume-title":"Learning for Dynamics and Control","author":"Fan","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614994"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2912443"},{"key":"ref26","first-page":"1","article-title":"Revisiting the softmax Bellman operator: New benefits and new perspective","volume-title":"Proc. ICML","author":"Song"},{"key":"ref27","first-page":"1","article-title":"Estimating maximum expected value through Gaussian approximation","volume-title":"Proc. ICML","author":"D\u2019Eramo"},{"key":"ref28","article-title":"Deep reinforcement learning with weighted Q-learning","volume-title":"arXiv:2003.09280","author":"Cini","year":"2020"},{"key":"ref29","first-page":"176","article-title":"Averaged-DQN: Variance reduction and stabilization for deep reinforcement learning","volume-title":"Proc. ICML","author":"Anschel"},{"key":"ref30","first-page":"1","article-title":"Maxmin Q-learning: Controlling the estimation bias of Q-learning","volume-title":"Proc. ICLR","author":"Lan"},{"key":"ref31","first-page":"1","article-title":"Double Q-learning","volume-title":"Proc. NIPS","author":"Hasselt"},{"key":"ref32","article-title":"Estimating the maximum expected value: An analysis of (Nested) cross validation and the maximum sample average","volume-title":"arXiv:1302.7175","author":"van Hasselt","year":"2013"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/483"},{"key":"ref34","article-title":"Randomized ensembled double Q-learning: Learning fast without a model","volume-title":"arXiv:2101.05982","author":"Chen","year":"2021"},{"key":"ref35","first-page":"1","article-title":"Finite-time analysis for double Q-learning","volume-title":"Proc. NIPS","author":"Xiong"},{"key":"ref36","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. ICML","author":"Fujimoto"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16973"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref39","article-title":"MinAtar: An atari-inspired testbed for thorough and reproducible reinforcement learning experiments","volume-title":"arXiv:1903.03176","author":"Young","year":"2019"},{"key":"ref40","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. ICML","author":"Haarnoja"},{"key":"ref41","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. ICLR","author":"Lillicrap"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref43","article-title":"Openai baselines","author":"Dhariwal","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10492491\/09904590.pdf?arnumber=9904590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:42:20Z","timestamp":1712691740000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9904590\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":44,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3203024","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}