{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T17:52:28Z","timestamp":1771523548009,"version":"3.50.1"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2020R1C1C1003461"],"award-info":[{"award-number":["NRF-2020R1C1C1003461"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007053","name":"Korea Institute of Energy Technology Evaluation and Planning","doi-asserted-by":"publisher","award":["20213030160250"],"award-info":[{"award-number":["20213030160250"]}],"id":[{"id":"10.13039\/501100007053","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2022,11]]},"DOI":"10.1109\/tii.2022.3159570","type":"journal-article","created":{"date-parts":[[2022,3,16]],"date-time":"2022-03-16T19:45:20Z","timestamp":1647459920000},"page":"7494-7503","source":"Crossref","is-referenced-by-count":15,"title":["DIP-QL: A Novel Reinforcement Learning Method for Constrained Industrial Systems"],"prefix":"10.1109","volume":"18","author":[{"given":"Hyungjun","family":"Park","sequence":"first","affiliation":[{"name":"Department of Industrial and Management Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daiki","family":"Min","sequence":"additional","affiliation":[{"name":"School of Business, Ewha Womans University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jong-hyun","family":"Ryu","sequence":"additional","affiliation":[{"name":"College of Business Management, Hongik University, Sejong, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3208-060X","authenticated-orcid":false,"given":"Dong Gu","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Industrial and Management Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2963072"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2975232"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2019.2919364"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1003814"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2016.2569525"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2881540"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2014.09.027"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2013.2280645"},{"key":"ref28","article-title":"Delayed Q-update: A novel credit assignment technique for deriving an optimal operation policy of the grid-connected microgrid","author":"park","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2801880"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2230197"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2896618"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2514358"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/en12061124"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2933502"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2924025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2974037"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2013.05.060"},{"key":"ref9","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/41.170966"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460547"},{"key":"ref22","first-page":"610","article-title":"Resource constrained deep reinforcement learning","author":"bhatia","year":"0","journal-title":"Proc 29th Int Conf Automated Plan Scheduling"},{"key":"ref21","article-title":"Safe exploration in continuous action spaces","author":"dalal","year":"2018"},{"key":"ref24","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":"ref23","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"2137","article-title":"Provably efficient reinforcement learning with linear function approximation","author":"jin","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/0309028"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/9895125\/09736610.pdf?arnumber=9736610","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:34:00Z","timestamp":1667514840000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9736610\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":29,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tii.2022.3159570","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11]]}}}