{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T17:40:27Z","timestamp":1732038027603,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.23919\/ecc.2018.8550545","type":"proceedings-article","created":{"date-parts":[[2018,12,8]],"date-time":"2018-12-08T00:50:06Z","timestamp":1544230206000},"page":"1349-1354","source":"Crossref","is-referenced-by-count":7,"title":["Constrained and Stabilizing Stacked Adaptive Dynamic Programming and a Comparison with Model Predictive Control"],"prefix":"10.23919","author":[{"given":"Lukas","family":"Beckenbach","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavel","family":"Osinenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Gohrt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Streif","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Learning from delayed rewards","author":"watkins","year":"1989","journal-title":"Ph D Dissertation Dept of Computer Science"},{"key":"ref32","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1007\/BF00115009"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1016\/j.automatica.2015.06.001"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-4757-2","article-title":"Adaptive Dynamic Programming for Control","author":"zhang","year":"2013","journal-title":"Communications and Control Engineering"},{"key":"ref34","article-title":"A Menu of Designs for Reinforcement Learning Over Time","author":"werbos","year":"1995","journal-title":"W T Miller III"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/9.863592"},{"key":"ref11","article-title":"Model predictive control and reinforcement learning as two complementary frameworks","volume":"6","author":"ernst","year":"2007","journal-title":"International Journal of Tomography & Statistics"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1016\/j.automatica.2006.08.026"},{"key":"ref13","first-page":"5071","article-title":"Relations between Model Predictive Control and Reinforce-ment Learning","author":"g\u00f6rges","year":"2017","journal-title":"IFAC 2017 World Congress"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.2514\/1.G001154"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1016\/j.asoc.2014.07.003"},{"key":"ref16","first-page":"102","article-title":"Contributions to the theory of optimal control","volume":"5","author":"kalman","year":"1960","journal-title":"Boletin Sociedad Matematica Mexicana"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1115\/1.3662604"},{"year":"1995","author":"krsti?","journal-title":"Nonlinear and Adaptive Control Design","key":"ref18"},{"key":"ref19","article-title":"Greedy Adaptive Critics for LQR Problems: Convergence proofs","author":"landelius","year":"1996","journal-title":"Technical report University of Skövde Sweden"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1016\/j.automatica.2012.06.075"},{"year":"1957","author":"bellman","journal-title":"Dynamic Programming","key":"ref4"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1002\/9780470182963"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1137\/0213054"},{"key":"ref6","article-title":"Neuro-Dynamic Programming","author":"bertsekas","year":"1996","journal-title":"Athena Scientific"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/9.751369"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.3166\/ejc.11.310-334"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1007\/BF00935009"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1214\/aoms\/1177700285"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TSMCB.2008.926614"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/9.701133"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1016\/j.sysconle.2008.12.002","article-title":"Adaptive model predictive control for constrained nonlinear systems","volume":"58","author":"adetola","year":"2009","journal-title":"Syst Control Lett"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/MCAS.2009.933854"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1016\/j.automatica.2014.10.128"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1109\/TNNLS.2013.2281663","article-title":"Policy Itereation Adaptive Dynamic Programming Algorithm for Discrete-Time Nonlinear Systems","volume":"25","author":"liu","year":"2014","journal-title":"IEEE T Neur Net Lear"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/9.262032"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/S0005-1098(99)00214-9","article-title":"Constrained model predictive control: Stability and optimality","volume":"36","author":"mayne","year":"2000","journal-title":"Automatica"},{"key":"ref26","first-page":"4218","article-title":"Stacked adaptive dynamic programming with unknown system model","author":"osinenko","year":"2017","journal-title":"IFAC 2017 World Congress"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"354","DOI":"10.3182\/20050703-6-CZ-1902.00280","article-title":"Learning-based Model Predictive Control For Markov Decision Processes","volume":"38","author":"negenborn","year":"2005","journal-title":"IFAC Proceedings Volumes"}],"event":{"name":"2018 17th European Control Conference (ECC)","start":{"date-parts":[[2018,6,12]]},"location":"Limassol","end":{"date-parts":[[2018,6,15]]}},"container-title":["2018 European Control Conference (ECC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8496738\/8550039\/08550545.pdf?arnumber=8550545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T22:52:22Z","timestamp":1598223142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8550545\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.23919\/ecc.2018.8550545","relation":{},"subject":[],"published":{"date-parts":[[2018,6]]}}}