{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T01:52:59Z","timestamp":1771033979781,"version":"3.50.1"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ministry of Science and Technology of the Republic of China","award":["108-2511-H-143 -001"],"award-info":[{"award-number":["108-2511-H-143 -001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1109\/tii.2020.2986501","type":"journal-article","created":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T19:56:30Z","timestamp":1587412590000},"page":"2116-2123","source":"Crossref","is-referenced-by-count":32,"title":["Cognitive Optimal-Setting Control of AIoT Industrial Applications With Deep Reinforcement Learning"],"prefix":"10.1109","volume":"17","author":[{"given":"Ying-Hsun","family":"Lai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tung-Cheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7138-0272","authenticated-orcid":false,"given":"Chin-Feng","family":"Lai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7986-4244","authenticated-orcid":false,"given":"Laurence Tianruo","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3488-4679","authenticated-orcid":false,"given":"Xiaokang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2613","article-title":"Double q-learning","author":"hasselt","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","first-page":"2094","article-title":"Deep reinforcement learning with double qlearning","author":"van hasselt","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(96)00385-2"},{"key":"ref13","first-page":"303","author":"rubinstein","year":"2001","journal-title":"Combinatorial Optimization"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/089976604773135104"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF00419934"},{"key":"ref18","first-page":"543","article-title":"A method for solving the convex programming problem with convergence rate $O\\bigl (\\frac{1}{k^2}\\bigr)$","volume":"269","author":"nesterov","year":"1983","journal-title":"Dokl Akad Nauk SSSR"},{"key":"ref19","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref28","first-page":"203","article-title":"Adaptive $\\epsilon$-greedy exploration in reinforcement learning based on value differences","author":"tokic","year":"0","journal-title":"Proc 33rd Annu German Conf Adv Artif Intell (AI)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2898174"},{"key":"ref27","first-page":"1","article-title":"Distributed prioritized experience replay","author":"horgan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2018.06.017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.05.056"},{"key":"ref29","first-page":"2817","article-title":"Cold-start reinforcement learning with softmax policy gradient","author":"ding","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2953289"},{"key":"ref8","first-page":"1476","article-title":"Increasing the action gap: New operators for reinforcement learning","author":"bellemare","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref7","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref9","article-title":"Reinforcement learning through gradient descent","author":"baird","year":"1999"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref20","first-page":"26","article-title":"Lecture 6.5—RmsProp: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Netw Mach Learn"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref21","article-title":"Adadelta: An adaptive learning rate method","author":"zeiler","year":"0"},{"key":"ref24","first-page":"2613","article-title":"Double q-learning","author":"hasselt","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"1","article-title":"On the convergence of adam and beyond","author":"reddi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","article-title":"Prioritized experience replay","author":"schaul","year":"0"},{"key":"ref25","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/9281052\/09072609.pdf?arnumber=9072609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:52:44Z","timestamp":1652194364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9072609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":29,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tii.2020.2986501","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3]]}}}