{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T05:27:19Z","timestamp":1782451639615,"version":"3.54.5"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"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":["61988101"],"award-info":[{"award-number":["61988101"]}],"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":["61525302"],"award-info":[{"award-number":["61525302"]}],"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":["61590922"],"award-info":[{"award-number":["61590922"]}],"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":["61773068"],"award-info":[{"award-number":["61773068"]}],"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":["61733005"],"award-info":[{"award-number":["61733005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013290","name":"National Key Research and Development Program of China Stem Cell and Translational Research","doi-asserted-by":"publisher","award":["2018YFB1701104"],"award-info":[{"award-number":["2018YFB1701104"]}],"id":[{"id":"10.13039\/501100013290","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Xingliao Plan of Liaoning Province","award":["XLYC1808001"],"award-info":[{"award-number":["XLYC1808001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1109\/tii.2020.3005207","type":"journal-article","created":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T22:16:29Z","timestamp":1593468989000},"page":"2727-2736","source":"Crossref","is-referenced-by-count":26,"title":["Reinforcement Learning Based Decision Making of Operational Indices in Process Industry Under Changing Environment"],"prefix":"10.1109","volume":"17","author":[{"given":"Chao","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3735-0672","authenticated-orcid":false,"given":"Jinliang","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6701-6598","authenticated-orcid":false,"given":"Jiyuan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015789"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2475419"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2903098"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref16","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2785794"},{"key":"ref18","article-title":"Attention, learn to solve routing problems!","author":"wouter","year":"0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3724\/SP.J.1004.2009.00641"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2016.2516973"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2785351"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2478\/v10006-010-0035-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2017.10.038"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2902790"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3182\/20050703-6-CZ-1902.00280"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2018.2865593"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2010.05.002"},{"key":"ref9","first-page":"263","article-title":"Approximate dynamic programming strategies and their applicability for process control: A review and future directions","volume":"2","author":"lee","year":"2004","journal-title":"Int J Control Autom Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2308576"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2102362"},{"key":"ref21","first-page":"140","article-title":"Integrated automation system for hematite ores processing and its applications","volume":"39","author":"chai","year":"2006","journal-title":"Meas Control"},{"key":"ref24","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2015.08.015"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/9319768\/09127490.pdf?arnumber=9127490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:52:32Z","timestamp":1652194352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9127490\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":24,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tii.2020.3005207","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]}}}