{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:04:32Z","timestamp":1740099872809,"version":"3.37.3"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,14]]},"DOI":"10.1109\/cdc42340.2020.9304242","type":"proceedings-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T07:27:32Z","timestamp":1610522852000},"page":"118-125","source":"Crossref","is-referenced-by-count":5,"title":["Adaptive Control for Linearizable Systems Using On-Policy Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Tyler","family":"Westenbroek","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Mazumdar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Fridovich-Keil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Valmik","family":"Prabhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claire J.","family":"Tomlin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. Shankar","family":"Sastry","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/027836498700600202"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref11"},{"journal-title":"Introduction to Reinforcement Learning","year":"1998","author":"sutton","key":"ref12"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"schulman","key":"ref13"},{"journal-title":"Stable Adaptive Systems","year":"2012","author":"narendra","key":"ref14"},{"article-title":"Technical Report: Adaptive Control for Linearizable Systems Using On-Policy Reinforcement Learning","year":"2020","author":"westenbroek","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/9.754811"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/9.995038"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.929402"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/72.485674"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717148"},{"key":"ref4","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/027836498700600303"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref6"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref5"},{"key":"ref8","volume":"48","author":"borkar","year":"2009","journal-title":"Stochastic Approximation A Dynamical Systems Viewpoint"},{"article-title":"Feedback Linearization for Unknown Systems via Reinforcement Learning","year":"2019","author":"westenbroek","key":"ref7"},{"key":"ref2","volume":"10","author":"sastry","year":"1999","journal-title":"Nonlinear Systems Analysis Stability and Control"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/9781108231596"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/9.40741"},{"key":"ref20","article-title":"Policy gradient in continuous time","author":"munos","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"article-title":"Deterministic policy gradient algorithms","year":"2014","author":"silver","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/9.1316"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1119\/1.16860"},{"key":"ref25","article-title":"Analysis and improvement of policy gradient estimation","author":"zhao","year":"2011","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2020 59th IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2020,12,14]]},"location":"Jeju, Korea (South)","end":{"date-parts":[[2020,12,18]]}},"container-title":["2020 59th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9303728\/9303729\/09304242.pdf?arnumber=9304242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:58:28Z","timestamp":1656345508000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9304242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/cdc42340.2020.9304242","relation":{},"subject":[],"published":{"date-parts":[[2020,12,14]]}}}