{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:15:49Z","timestamp":1774455349049,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003593","name":"National Council for Scientific and Technological Development - CNPq","doi-asserted-by":"publisher","award":["314121\/2021-8"],"award-info":[{"award-number":["314121\/2021-8"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892099","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Intelligent Robust Control for Second-Order Non-Linear Systems with Smart Gain Tuning based on Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Adalberto I. S.","family":"Oliveira","sequence":"first","affiliation":[{"name":"PUC-Rio,Dept. of Electrical Engineering,Rio de Janeiro RJ,Brazil"}]},{"given":"Antonio C.","family":"Leite","sequence":"additional","affiliation":[{"name":"Norwegian University of Life Sciences,Faculty of Science and Technology,As,Norway"}]},{"given":"Wouter","family":"Caarls","sequence":"additional","affiliation":[{"name":"PUC-Rio,Dept. of Electrical Engineering,Rio de Janeiro RJ,Brazil"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2018.04.042"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574713000623"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"5393","DOI":"10.3182\/20140824-6-ZA-1003.02511","article-title":"Nonlinear Disturbance Compensation and Reference Tracking via Reinforcement Learning with Fuzzy Approx-imators","volume":"47","author":"bayiz","year":"2014","journal-title":"IFAC Proceedings Volumes"},{"key":"ref13","author":"khalil","year":"2002","journal-title":"Nonlinear Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2008.0610"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2007.910740"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800106"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619843"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2417170"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2261"},{"key":"ref4","first-page":"1587","article-title":"Addressing Function Approxi-mation Error in Actor-critic Methods","author":"fujimoto","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref3","article-title":"Thinking While Moving: Deep Reinforcement Learning with Concurrent Control","author":"xiao","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967299"},{"key":"ref5","article-title":"Playing Atari with Deep Reinforcement Learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2009.2012452"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4893-0"},{"key":"ref2","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","first-page":"26","article-title":"Adaptive Tracking Control of Robotic Manipulators with Unknown Input Saturation using Backstep-ping Sliding Mode Technique","author":"chen","year":"2016","journal-title":"2016 Chinese Control and Decision Conference"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32552-1_15"},{"key":"ref20","author":"bruno","year":"2009","journal-title":"Robotics Modelling Planning and Control"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.05.097"},{"key":"ref21","first-page":"47","author":"davison","year":"2020","journal-title":"Robust Servomechanism Problem"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref23","first-page":"1008","article-title":"Actor-critic Algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref26","volume":"39","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"ref25","first-page":"387","article-title":"Deterministic Policy Gradient Algorithms","author":"silver","year":"2014","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","location":"Padua, Italy","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892099.pdf?arnumber=9892099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:58:47Z","timestamp":1667516327000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892099\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892099","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}