{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T19:19:15Z","timestamp":1779218355082,"version":"3.51.4"},"reference-count":45,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62450020"],"award-info":[{"award-number":["62450020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125306"],"award-info":[{"award-number":["62125306"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Natural Science Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["20242BAB27003"],"award-info":[{"award-number":["20242BAB27003"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011311","name":"State Key Laboratory of Industrial Control Technology","doi-asserted-by":"publisher","award":["ICT2024A06"],"award-info":[{"award-number":["ICT2024A06"]}],"id":[{"id":"10.13039\/501100011311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tsmc.2025.3539349","type":"journal-article","created":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T15:32:45Z","timestamp":1740065565000},"page":"3249-3260","source":"Crossref","is-referenced-by-count":1,"title":["Toward Universal Controller: Performance-Aware Self-Optimizing Reinforcement Learning for Discrete-Time Systems With Uncontrollable Factors"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1916-4809","authenticated-orcid":false,"given":"Jianfeng","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6883-1375","authenticated-orcid":false,"given":"Haoran","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0254-5763","authenticated-orcid":false,"given":"Chunhui","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3003224"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2022.06.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2021.04.023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109943"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3340726"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3177217"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3298336"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3208773"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2022.3191837"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106618"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2988208"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3006256"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2490072"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3251731"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2023.103028"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref20","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2023.105689"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3284397"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3284223"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.048"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref30","article-title":"A zero-shot adaptive quadcopter controller","author":"Zhang","year":"2022","journal-title":"arXiv:2209.09232"},{"key":"ref31","first-page":"1722","article-title":"In-hand object rotation via rapid motor adaptation","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Qi"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20730"},{"key":"ref33","first-page":"1","article-title":"Environment probing interaction policies","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref34","first-page":"5757","article-title":"Context-aware dynamics model for generalization in model-based reinforcement learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref35","volume-title":"Nonlinear Systems","author":"Khalil","year":"2002"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2417170"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2022.109274"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2015.05.003"},{"key":"ref39","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.05.049"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.02.015"},{"key":"ref42","first-page":"1","article-title":"A unified bellman optimality principle combining reward maximization and empowerment","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","volume":"32","author":"Leibfried"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2022.105302"},{"key":"ref44","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref45","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/10966470\/10896858.pdf?arnumber=10896858","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:50:49Z","timestamp":1776887449000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10896858\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":45,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3539349","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}