{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:16:05Z","timestamp":1774455365957,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T00:00:00Z","timestamp":1686614400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T00:00:00Z","timestamp":1686614400000},"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":[[2023,6,13]]},"DOI":"10.23919\/ecc57647.2023.10178182","type":"proceedings-article","created":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T14:00:50Z","timestamp":1690898450000},"page":"1-6","source":"Crossref","is-referenced-by-count":7,"title":["Design of Reinforcement Learning based PI controller for nonlinear Multivariable System"],"prefix":"10.23919","author":[{"given":"P","family":"Kranthi Kumar","sequence":"first","affiliation":[{"name":"Indian Institute of Technology,Department of Artificial Intelligence,Hyderabad,India"}]},{"given":"Ketan P","family":"Detroja","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Department of Artificial Intelligence,Hyderabad,India"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814958"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2018.01.014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/87.845876"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC49329.2020.9163990"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCA52192.2021.9666405"},{"key":"ref20","author":"sutton","year":"2018","journal-title":"Reinforcement learning An introduction Second edition"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106886"},{"key":"ref22","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"99","author":"sutton","year":"1999","journal-title":"NIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S1006-1266(07)60009-1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2020.02.017"},{"key":"ref2","article-title":"On-line q-learning using connectionist systems","author":"rummery","year":"1994","journal-title":"Technical Report CUED\/F-INFENG\/TR 156 Cambridge University Engineering Department"},{"key":"ref1","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref17","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"ArXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3025194"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1999.832889"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147706"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1109\/TCST.2005.847331","article-title":"Pid control system analysis, design, and technology","volume":"13","author":"ang","year":"2005","journal-title":"IEEE Transactions on Control Systems Technology"},{"key":"ref7","article-title":"Proximal Policy Optimization Algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(91)90052-4"},{"key":"ref4","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"ICML"},{"key":"ref3","article-title":"Playing atari with deep reinforcement learning","volume":"12","author":"mnih","year":"2013","journal-title":"NIPS"},{"key":"ref6","first-page":"1889","article-title":"Trust Region Policy Optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"ICLRE"}],"event":{"name":"2023 European Control Conference (ECC)","location":"Bucharest, Romania","start":{"date-parts":[[2023,6,13]]},"end":{"date-parts":[[2023,6,16]]}},"container-title":["2023 European Control Conference (ECC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10178092\/10178115\/10178182.pdf?arnumber=10178182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T13:40:34Z","timestamp":1692625234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10178182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,13]]},"references-count":23,"URL":"https:\/\/doi.org\/10.23919\/ecc57647.2023.10178182","relation":{},"subject":[],"published":{"date-parts":[[2023,6,13]]}}}