{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:19:39Z","timestamp":1775578779946,"version":"3.50.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["62120106003"],"award-info":[{"award-number":["62120106003"]}],"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":["62173301"],"award-info":[{"award-number":["62173301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2021C01151"],"award-info":[{"award-number":["2021C01151"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tii.2024.3523563","type":"journal-article","created":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T16:07:59Z","timestamp":1736525279000},"page":"3186-3195","source":"Crossref","is-referenced-by-count":1,"title":["Optimizing Weights to Fit Parametric Operation Policies for Generalized Working Conditions in Linear Systems Using Deep Reinforcement Learning"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2458-049X","authenticated-orcid":false,"given":"Ruiyu","family":"Qiu","sequence":"first","affiliation":[{"name":"State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanghui","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7873-9521","authenticated-orcid":false,"given":"Zuhua","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3016-4658","authenticated-orcid":false,"given":"Zhijiang","family":"Shao","sequence":"additional","affiliation":[{"name":"State Key Lab 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":"10.1016\/j.ces.2011.05.049"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2005.847331"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(78)90001-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-019-0774-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2014.2338273"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2951842"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3089143"},{"key":"ref8","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref12","volume-title":"Reinforcement Learning and Optimal Control","author":"Bertsekas","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3189725"},{"key":"ref14","first-page":"426","article-title":"Deep reinforcement learning: An overview","volume-title":"Proc. SAI Intell. Syst. Conf.","author":"Li","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2014.2333873"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3021024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2023.106686"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref19","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schulman","year":"2016"},{"key":"ref20","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-0578(07)60121-9"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106886"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2018.11.004"},{"key":"ref24","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2018.06.002"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/amp2.10113"},{"key":"ref27","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","author":"Zhang","year":"2020","journal-title":"in Proc. 34th Int. Conf. Neural Inf. Process. Syst."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2886407"},{"key":"ref29","volume-title":"A Softw. Package for Sequential Quadratic Program.","author":"Kraft","year":"1988"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-409-90136-8.40025-3"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9424\/10949153\/10836915.pdf?arnumber=10836915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T18:13:50Z","timestamp":1762539230000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10836915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":30,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tii.2024.3523563","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}