{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:08:53Z","timestamp":1740100133777,"version":"3.37.3"},"reference-count":29,"publisher":"IEEE","funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-13-1-0151"],"award-info":[{"award-number":["N00014-13-1-0151"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"AFOSR","doi-asserted-by":"publisher","award":["FA9550-18-1-0109"],"award-info":[{"award-number":["FA9550-18-1-0109"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"AFOSR","doi-asserted-by":"publisher","award":["FA9550-19-1-0169"],"award-info":[{"award-number":["FA9550-19-1-0169"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,25]]},"DOI":"10.23919\/acc50511.2021.9483047","type":"proceedings-article","created":{"date-parts":[[2021,7,28]],"date-time":"2021-07-28T20:29:16Z","timestamp":1627504156000},"page":"1973-1978","source":"Crossref","is-referenced-by-count":1,"title":["Cooperative Model-Based Reinforcement Learning for Approximate Optimal Tracking"],"prefix":"10.23919","author":[{"given":"Max L.","family":"Greene","sequence":"first","affiliation":[]},{"given":"Zachary I.","family":"Bell","sequence":"additional","affiliation":[]},{"given":"Scott A.","family":"Nivison","sequence":"additional","affiliation":[]},{"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[]},{"given":"Warren E.","family":"Dixon","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Optimal Control Theory An Introduction","year":"2004","author":"kirk","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1515\/9781400842643"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-78384-0","author":"kamalapurkar","year":"2018","journal-title":"Reinforcement learning for optimal feedback control A Lyapunov-based approach"},{"key":"ref13","volume":"17","author":"lewis","year":"2013","journal-title":"Reinforcement Learning and Approximate Dynamic Programming for Feedback Control"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2511658"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808102"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.2977927"},{"key":"ref17","first-page":"1100","article-title":"Simultaneously learning and advising in multiagent reinforcement learning","author":"da silva","year":"2017","journal-title":"Proc of the 16th Conf on Auton Agents and Multiagent Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967849"},{"key":"ref19","article-title":"Scaling up multiagent reinforcement learning for robotic systems: Learn an adaptive sparse communication graph","author":"sun","year":"2020","journal-title":"IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1090\/trans2\/042\/13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"journal-title":"Nonlinear Systems","year":"2002","author":"khalil","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2006.884959"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCS.1987.1086038"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.09.019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.10.039"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2013.848292"},{"key":"ref2","volume":"2","author":"bertsekas","year":"2007","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.08.004"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2970550"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.108922"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6566850"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898717563"},{"key":"ref23","volume":"48","author":"farrell","year":"2006","journal-title":"Adaptive Approximation Based Control Unifying Neural Fuzzy and Traditional Adaptive Approximation Approaches ser Adaptive and Learning Systems for Signal Processing Communications and Control Series"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.103"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-1253-3"}],"event":{"name":"2021 American Control Conference (ACC)","start":{"date-parts":[[2021,5,25]]},"location":"New Orleans, LA, USA","end":{"date-parts":[[2021,5,28]]}},"container-title":["2021 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9482409\/9482614\/09483047.pdf?arnumber=9483047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T10:52:06Z","timestamp":1633517526000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9483047\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,25]]},"references-count":29,"URL":"https:\/\/doi.org\/10.23919\/acc50511.2021.9483047","relation":{},"subject":[],"published":{"date-parts":[[2021,5,25]]}}}