{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T09:02:06Z","timestamp":1768899726705,"version":"3.49.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/cdc40024.2019.9029904","type":"proceedings-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T04:43:11Z","timestamp":1584074591000},"page":"6510-6517","source":"Crossref","is-referenced-by-count":10,"title":["Using Reinforcement Learning for Model-free Linear Quadratic Control with Process and Measurement Noises"],"prefix":"10.1109","author":[{"given":"Farnaz Adib","family":"Yaghmaie","sequence":"first","affiliation":[]},{"given":"Fredrik","family":"Gustafsson","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2012.2214134"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2550518"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.12.009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2317301"},{"key":"ref15","article-title":"Model-free linear quadratic control via reduction to expert prediction","author":"abbasi-yadkori","year":"2018"},{"key":"ref16","article-title":"On the sample complexity of the linear quadratic regulator","author":"dean","year":"2017"},{"key":"ref17","article-title":"Least-squares temporal difference learning for the linear quadratic regulator","author":"tu","year":"2017"},{"key":"ref18","article-title":"Online linear quadratic control","author":"cohen","year":"2018"},{"key":"ref19","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","author":"fazel","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref3","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.108549"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.4538"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.10.038"},{"key":"ref2","article-title":"Adaptive control","author":"astr?om","year":"2013","journal-title":"Courier Corporation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3413"},{"key":"ref1","volume":"222","author":"krstic","year":"1995","journal-title":"Nonlinear and Adaptive Control Design"},{"key":"ref20","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2009.2022097"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1971.1099755"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/0717073"},{"key":"ref23","article-title":"A tour of reinforcement learning: The view from continuous control","author":"recht","year":"2018","journal-title":"Annual Review of Control Robotics and Autonomous Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2007.04.004"}],"event":{"name":"2019 IEEE 58th Conference on Decision and Control (CDC)","location":"Nice, France","start":{"date-parts":[[2019,12,11]]},"end":{"date-parts":[[2019,12,13]]}},"container-title":["2019 IEEE 58th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8977134\/9028853\/09029904.pdf?arnumber=9029904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:22:14Z","timestamp":1658262134000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9029904\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/cdc40024.2019.9029904","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}