{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:21:19Z","timestamp":1730204479033,"version":"3.28.0"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T00:00:00Z","timestamp":1678233600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T00:00:00Z","timestamp":1678233600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,3,8]]},"DOI":"10.1109\/ccwc57344.2023.10099286","type":"proceedings-article","created":{"date-parts":[[2023,4,18]],"date-time":"2023-04-18T13:28:01Z","timestamp":1681824481000},"page":"0093-0101","source":"Crossref","is-referenced-by-count":0,"title":["Process Proportional-Integral PI Control with Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Teckchai","family":"Tiong","sequence":"first","affiliation":[{"name":"Curtin University Malaysia,Electrical and Computer Engineering,Miri Sarawak,Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ismail","family":"Saad","sequence":"additional","affiliation":[{"name":"University Malaysia Sabah,Electrical and Electronics Engineering,Kota Kinabalu,Sabah,Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenneth Tze Kin","family":"Teo","sequence":"additional","affiliation":[{"name":"University Malaysia Sabah,Electrical and Electronics Engineering,Kota Kinabalu,Sabah,Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Herwansyah","family":"Bin Lago","sequence":"additional","affiliation":[{"name":"University Malaysia Sabah,Electrical and Electronics Engineering,Kota Kinabalu,Sabah,Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2021","journal-title":"Reinforcement Learning","key":"ref13"},{"key":"ref35","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"year":"0","journal-title":"Machine Learning What it is and why it matters","key":"ref12"},{"key":"ref34","first-page":"903","article-title":"Practical reinforcement learning in continuous spaces","author":"smart","year":"2000","journal-title":"In Proceedings of the 17th International Conference on Machine Learning"},{"key":"ref15","article-title":"Introduction to Reinforcement Learning (Coding SARSA)","author":"adesh","year":"2018","journal-title":"Dynamic Programming and Optimal Control Athena Scientific"},{"key":"ref37","article-title":"Deterministic policy gradient algorithms","author":"david","year":"2014","journal-title":"International Conference on Machine Learning"},{"year":"1998","author":"sutton","journal-title":"Reinforcement Learning An Introduction","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1016\/j.compchemeng.2020.106886"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/TNNLS.2012.2227339"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/72.914523"},{"key":"ref11","volume":"2013","author":"tulsyan","year":"2013","journal-title":"In Bayesian Identification of Non-Linear State-SpaceModels Part I Input Design Dynamics and Control of Process Systems"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1163\/156855300741852"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1021\/acs.iecr.8b02738"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1016\/j.automatica.2012.05.049"},{"key":"ref2","first-page":"274286","article-title":"Status of Flue Gas Desulphurisation (FGD) systemsfrom coal-fired power plants: Overview of the physic-chemical controlprocesses of wet limestone FGDs","volume":"144","author":"c\u00f3rdoba","year":"0","journal-title":"Fuel2015"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1039\/C4CP04211E"},{"year":"0","author":"lillicrap","journal-title":"Continuous control with deep reinforcement learning","key":"ref17"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1016\/S0967-0661(99)00141-0"},{"year":"0","journal-title":"Reinforcement Learning With (Deep) Q-Learning Explained","key":"ref16"},{"key":"ref38","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"ArXiv Preprint"},{"year":"0","journal-title":"TD3 Learning To Run With AI Learn to build one of themost powerful… — by Donal Byrne — Towards Data Science","key":"ref19"},{"year":"0","journal-title":"Twin Delayed DDPG — Spinning Up documentation","key":"ref18"},{"key":"ref24","first-page":"143","article-title":"Neuro-dynamic programming method for MPC1","volume":"34","author":"lee","year":"0","journal-title":"IFAC Proceedings"},{"year":"0","journal-title":"Twin-Delayed Deep Deterministic Policy Gradient Agents-MATLAB Simulink","key":"ref46"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1016\/j.jprocont.2005.04.010"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1109\/rICT-ICeVT.2013.6741546"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1007\/BF02705417"},{"year":"0","journal-title":"arXiv Vanity","article-title":"Practical Deep Reinforcement Learning Approach for Stock Trading","key":"ref48"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1002\/rnc.822"},{"year":"0","journal-title":"Introduction to Reinforcement Learning for Beginners","key":"ref47"},{"year":"2020","author":"jordi","journal-title":"A gentle introduction to Deep Reinforcement Learning","key":"ref20"},{"key":"ref42","article-title":"Reinforcement learning adaptive PID controller for an under-actuated robot arm","volume":"7","author":"adel","year":"2015","journal-title":"International Journal of Integrated Engineering"},{"key":"ref41","article-title":"Adaptive PID controller based on reinforcement learning for wind turbine control","volume":"27","author":"sedighizadeh","year":"0","journal-title":"Proceedings of World Academy of Science Engineering and Technology"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1016\/j.compchemeng.2006.05.043"},{"year":"2010","author":"lena","journal-title":"Dynamic tuning of PI-controllers based on model-free reinforcement learning methods","key":"ref44"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ADCONIP.2017.7983780"},{"year":"0","author":"gurel","journal-title":"Q-Learning for Adaptive PID Control of a Line Follower Mobile Robot","key":"ref43"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1016\/S0098-1354(98)00301-9"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1016\/j.automatica.2005.02.006"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1109\/TSMCB.2008.926614","article-title":"Discrete-time nonlinear HJB solution using approximate dynamic programming: convergence proof","volume":"38","author":"a","year":"2008","journal-title":"IEEE Transactions on Systems Man and Cybernetics Part B"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1002\/bit.26605"},{"key":"ref7","first-page":"126","article-title":"Machine-learning for biopharma ceutical batch process monitoring with limited data","volume":"51","author":"tulsyan","year":"2018","journal-title":"IFACPapersOnLine"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1016\/j.jprocont.2019.03.002"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1016\/j.jprocont.2019.05.007"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1007\/s11081-020-09506-x"},{"key":"ref6","article-title":"Optimum settings for automatic controllers","volume":"42","author":"ziegler","year":"1995","journal-title":"INTECH"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.1016\/S0967-0661(01)00062-4","article-title":"The future of PID control","volume":"9","author":"\u00e5str\u00f6m","year":"2001","journal-title":"Control Eng Pract"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1016\/S1006-1266(07)60009-1"}],"event":{"name":"2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC)","start":{"date-parts":[[2023,3,8]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2023,3,11]]}},"container-title":["2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10099037\/10098906\/10099286.pdf?arnumber=10099286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T14:27:26Z","timestamp":1683556046000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10099286\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,8]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/ccwc57344.2023.10099286","relation":{},"subject":[],"published":{"date-parts":[[2023,3,8]]}}}