{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T16:08:47Z","timestamp":1788624527300,"version":"build-2803163510"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Young Scientists Fund of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306063"],"award-info":[{"award-number":["62306063"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Scientists Fund of the Natural Science Foundation of Sichuan Province","award":["2024NSFSC1469"],"award-info":[{"award-number":["2024NSFSC1469"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62236007"],"award-info":[{"award-number":["62236007"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tnnls.2024.3424254","type":"journal-article","created":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T17:28:35Z","timestamp":1721150915000},"page":"8510-8524","source":"Crossref","is-referenced-by-count":5,"title":["Q-ADER: An Effective Q-Learning for Recommendation With Diminishing Action Space"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8949-4905","authenticated-orcid":false,"given":"Fan","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of Birth Defects and Related Diseases of Women and Children (Sichuan University), Ministry of Education, Section of Epidemiology and Population Health, Department of Obstetrics and Gynecology, West China Second University Hospital, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6114-3441","authenticated-orcid":false,"given":"Hong","family":"Qu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liyan","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Grid Sichuan Electric Power Company Marketing Service Center, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9257-126X","authenticated-orcid":false,"given":"Mingsheng","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5867-9322","authenticated-orcid":false,"given":"Zhang","family":"Yi","sequence":"additional","affiliation":[{"name":"School of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3141095"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301346"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3215596"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053633"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583467"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3280161"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330668"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570412"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3582900.3582905"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3209290"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.v35i.130584"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412044"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11798"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3296642"},{"key":"ref19","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331302"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110335"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371801"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371827"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/360"},{"key":"ref26","article-title":"Deep reinforcement learning for list-wise recommendations","author":"Zhao","year":"2017","journal-title":"arXiv:1801.00209"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546758"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.08.028"},{"key":"ref31","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref32","article-title":"Deep reinforcement learning in large discrete action spaces","author":"Dulac-Arnold","year":"2015","journal-title":"arXiv:1512.07679"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3353215"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3352397"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110289"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2024.3391268"},{"key":"ref37","first-page":"176","article-title":"Averaged-DQN: Variance reduction and stabilization for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Anschel"},{"key":"ref38","first-page":"1","article-title":"Maxmin Q-learning: Controlling the estimation bias of Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lan"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3203024"},{"key":"ref40","first-page":"5916","article-title":"Revisiting the softmax Bellman operator: New benefits and new perspective","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Song"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3317353"},{"key":"ref42","first-page":"243","article-title":"An alternative softmax operator for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Asadi"},{"key":"ref43","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Fujimoto"},{"key":"ref44","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref45","article-title":"Tight performance bounds on greedy policies based on imperfect value functions","author":"Williams","year":"1993"},{"key":"ref46","first-page":"1","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159656"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330984"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/10982361\/10599887.pdf?arnumber=10599887","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T17:57:13Z","timestamp":1746467833000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10599887\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":50,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3424254","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}