{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:53:23Z","timestamp":1784138003118,"version":"3.55.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"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":[[2022,6,8]]},"DOI":"10.23919\/acc53348.2022.9867687","type":"proceedings-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T16:24:10Z","timestamp":1662395050000},"page":"2691-2696","source":"Crossref","is-referenced-by-count":5,"title":["Reinforcement Learning Approach to Autonomous PID Tuning"],"prefix":"10.23919","author":[{"given":"Oguzhan","family":"Dogru","sequence":"first","affiliation":[{"name":"University of Alberta,Department of Chemical and Materials Engineering,Edmonton,AB,Canada,T6G 1H9"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kirubakaran","family":"Velswamy","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Chemical and Materials Engineering,Edmonton,AB,Canada,T6G 1H9"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fadi","family":"Ibrahim","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Chemical and Materials Engineering,Edmonton,AB,Canada,T6G 1H9"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqi","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Electrical and Electronics Engineering,Edmonton,AB,Canada,T6G 1H9"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arun Senthil","family":"Sundaramoorthy","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Chemical and Materials Engineering,Edmonton,AB,Canada,T6G 1H9"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biao","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Chemical and Materials Engineering,Edmonton,AB,Canada,T6G 1H9"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu","family":"Xu","sequence":"additional","affiliation":[{"name":"Emerson Electric Co.,Austin,TX,Canada,78681"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Nixon","sequence":"additional","affiliation":[{"name":"Emerson Electric Co.,Austin,TX,Canada,78681"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noel","family":"Bell","sequence":"additional","affiliation":[{"name":"Emerson Electric Co.,Austin,TX,Canada,78681"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","author":"bequette","year":"2003","journal-title":"Process Control Modeling Design and Simulation"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2019.03.027"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1145\/1772690.1772758","article-title":"A contextual-bandit approach to personalized news article recommendation","author":"li","year":"2010","journal-title":"Proceedings of the 19th International Conference on World Wide Web"},{"key":"ref13","article-title":"Reward constrained policy optimization","author":"tessler","year":"2018","journal-title":"arXiv preprint arXiv 1805 11074"},{"key":"ref14","author":"seborg","year":"2010","journal-title":"Process Dynamics and Control"},{"key":"ref15","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref16","article-title":"Reinforcement learning with constrained uncertain reward function through particle filtering","author":"dogru","year":"2021","journal-title":"IEEE Transactions on Industrial Electronics"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2021.04.027"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2021.06.004"},{"key":"ref3","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.129"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.09.173"},{"key":"ref8","article-title":"Control system design","author":"\u00e5str\u00f6m","year":"2002"},{"key":"ref7","volume":"7","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cep.2006.11.013"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1016\/j.jprocont.2004.01.002","article-title":"Revisiting the ziegler–nichols step response method for pid control","volume":"14","author":"\u00e5str\u00f6m","year":"2004","journal-title":"Journal of Process Control"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0959-1524(02)00062-8"}],"event":{"name":"2022 American Control Conference (ACC)","location":"Atlanta, GA, USA","start":{"date-parts":[[2022,6,8]]},"end":{"date-parts":[[2022,6,10]]}},"container-title":["2022 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9866948\/9867142\/09867687.pdf?arnumber=9867687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T16:38:54Z","timestamp":1664815134000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9867687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,8]]},"references-count":17,"URL":"https:\/\/doi.org\/10.23919\/acc53348.2022.9867687","relation":{},"subject":[],"published":{"date-parts":[[2022,6,8]]}}}