{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T02:27:16Z","timestamp":1730341636392,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"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":[[2023,5,31]]},"DOI":"10.23919\/acc55779.2023.10156038","type":"proceedings-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T17:48:03Z","timestamp":1688406483000},"page":"84-91","source":"Crossref","is-referenced-by-count":1,"title":["Robust nonlinear set-point control with reinforcement learning"],"prefix":"10.23919","author":[{"given":"Ruoqi","family":"Zhang","sequence":"first","affiliation":[{"name":"Uppsala University,Division of Systems and Control,Department of Information Technology,Uppsala,Sweden,SE-751 05"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Per","family":"Mattsson","sequence":"additional","affiliation":[{"name":"Uppsala University,Division of Systems and Control,Department of Information Technology,Uppsala,Sweden,SE-751 05"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Torbj\u00f6rn","family":"Wigren","sequence":"additional","affiliation":[{"name":"Uppsala University,Division of Systems and Control,Department of Information Technology,Uppsala,Sweden,SE-751 05"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2005.08.017"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref12"},{"article-title":"Epopt: Learning robust neural network policies using model ensembles","year":"2016","author":"rajeswaran","key":"ref15"},{"article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","year":"2018","author":"plappert","key":"ref14"},{"article-title":"ElegantRL: Massively parallel framework for cloud-native deep reinforcement learning","year":"2021","author":"liu","key":"ref31"},{"key":"ref30","article-title":"What matters in on-policy reinforcement learning? A large-scale empirical study","author":"andrychowicz","year":"2021","journal-title":"ICLR 2021 The Ninth International Conference on Learning Representations"},{"article-title":"Challenges of real-world reinforcement learning","year":"2019","author":"dulac-arnold","key":"ref11"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2006.10.009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1201\/9781315274737"},{"journal-title":"Tuning and Control Loop Performance","year":"1983","author":"mcmillan","key":"ref2"},{"key":"ref1","volume":"70","author":"\u00e5str\u00f6m","year":"1970","journal-title":"Introduction to Stochastic Control Theory"},{"article-title":"Residual policy learning","year":"2018","author":"silver","key":"ref17"},{"key":"ref16","article-title":"Reinforcement learning in robust markov decision processes","volume":"26","author":"lim","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Aiding reinforcement learning for set point control","author":"zhang","year":"0","journal-title":"IFAC-PapersOnLine 2023 22nd IFAC World Congress"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref24","volume":"461","author":"\u00e5str\u00f6m","year":"2006","journal-title":"Advanced PID control ISA-The Instrumentation Systems and Automation Society Research Triangle Park"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1016\/0005-1098(84)90014-1","article-title":"Automatic tuning of simple regulators with specifications on phase and amplitude margins","volume":"20","author":"\u00e5str\u00f6m","year":"1984","journal-title":"Automatica"},{"key":"ref26","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"article-title":"Transfer learning in deep reinforcement learning: A survey","year":"2020","author":"zhu","key":"ref25"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.129"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2020.108053"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2020.02.017"},{"journal-title":"Adaptive Control","year":"2013","author":"\u00e5str\u00f6m","key":"ref28"},{"key":"ref27","article-title":"Model-ensemble trust-region policy optimization","author":"kurutach","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref29","article-title":"Recursive identification based on the nonlinear Wiener model","author":"wigren","year":"1990","journal-title":"Ph D Dissertation"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"journal-title":"Constrained Control and Estimation An Optimisation Approach","year":"2005","author":"de dona","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1115\/1.4019264"},{"journal-title":"Nonlinear and Adaptive Control Design","year":"1995","author":"krstic","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/OJIA.2020.3020184"}],"event":{"name":"2023 American Control Conference (ACC)","start":{"date-parts":[[2023,5,31]]},"location":"San Diego, CA, USA","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10155646\/10155787\/10156038.pdf?arnumber=10156038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:40:48Z","timestamp":1692639648000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10156038\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,31]]},"references-count":33,"URL":"https:\/\/doi.org\/10.23919\/acc55779.2023.10156038","relation":{},"subject":[],"published":{"date-parts":[[2023,5,31]]}}}