{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T06:28:11Z","timestamp":1766557691523,"version":"3.44.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government through Ministry of Science and ICT","award":["NRF-2022R1A2C2004457"],"award-info":[{"award-number":["NRF-2022R1A2C2004457"]}]},{"name":"Brain Korea 21 FOUR"},{"DOI":"10.13039\/501100003725","name":"Ministry of Education of Korea and the National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3600504","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:18:24Z","timestamp":1755627504000},"page":"20280-20295","source":"Crossref","is-referenced-by-count":2,"title":["Autonomous PID Tuning: Two-Phase Reinforcement Learning Through Adversarial Imitation Learning Under Imperfect Demonstrations"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8113-3034","authenticated-orcid":false,"given":"Gon","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Industrial and Management Engineering, Korea University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1928-9417","authenticated-orcid":false,"given":"Kyuchang","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Software, Jeju National University, Jeju, South Korea"}]},{"given":"Yunseon","family":"Byun","sequence":"additional","affiliation":[{"name":"Department of Industrial and Management Engineering, Korea University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7088-1478","authenticated-orcid":false,"given":"Jun-Geol","family":"Baek","sequence":"additional","affiliation":[{"name":"Department of Industrial and Management Engineering, Korea University, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2005.847331"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s40435-023-01368-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3524303"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3217209"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2023.100900"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-021-00431-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.59247\/csol.v1i2.41"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2022.107760"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/tee.23430"},{"key":"ref10","article-title":"Deep reinforcement learning for process control: A primer for beginners","author":"Spielberg","year":"2020","journal-title":"arXiv:2004.05490"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9993026"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1049\/trit.2018.1007"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.06.066"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-023-07934-2"},{"key":"ref15","article-title":"Stability-preserving automatic tuning of PID control with reinforcement learning","author":"Lakhani","year":"2021","journal-title":"arXiv:2112.15187"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5662"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2021.105046"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.03.063"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3174625"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref21","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref23","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2023.108393"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyai.2023.100255"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cirpj.2022.11.003"},{"key":"ref29","article-title":"Learning to be safe: Deep RL with a safety critic","author":"Srinivasan","year":"2020","journal-title":"arXiv:2010.14603"},{"key":"ref30","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Fujimoto"},{"key":"ref31","article-title":"Learning sparse rewarded tasks from sub-optimal demonstrations","author":"Zhu","year":"2020","journal-title":"arXiv:2004.00530"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3395626"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160939"},{"key":"ref36","first-page":"34556","article-title":"Jump-start reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Uchendu"},{"key":"ref37","first-page":"1071","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Ho"},{"key":"ref38","article-title":"Autotuning PID control using actor-critic deep reinforcement learning","author":"van Veldhuizen","year":"2022","journal-title":"arXiv:2212.00013"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2022.e09399"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref42","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3293508"},{"key":"ref44","first-page":"1787","article-title":"Better exploration with optimistic actor critic","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ciosek"},{"key":"ref45","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref46","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref47","article-title":"Trust region policy optimization","author":"Schulman","year":"2015","journal-title":"arXiv:1502.05477"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119192"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-023-0616-z"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/11130359.pdf?arnumber=11130359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T04:30:10Z","timestamp":1756441810000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11130359\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3600504","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"type":"print","value":"1545-5955"},{"type":"electronic","value":"1558-3783"}],"subject":[],"published":{"date-parts":[[2025]]}}}