{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:04:26Z","timestamp":1740099866053,"version":"3.37.3"},"reference-count":37,"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\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000781","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\/cdc42340.2020.9304315","type":"proceedings-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T07:27:32Z","timestamp":1610522852000},"page":"2455-2462","source":"Crossref","is-referenced-by-count":0,"title":["Constrained Optimal Tracking Control of Unknown Systems: A Multi-Step Linear Programming Approach"],"prefix":"10.1109","author":[{"given":"Alexandros","family":"Tanzanakis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Lygeros","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2358227"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.05.011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2317301"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2751018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2623859"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/0471459100"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2585520"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2384016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-4080-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2018.7511249"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/9781118453988.ch17"},{"key":"ref13","article-title":"Abstract dynamic programming","author":"bertsekas","year":"2018","journal-title":"Athena Scientific"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-018-9990-5"},{"key":"ref15","article-title":"Lambda-policy iteration with randomization for contractive models with infinite policies: Well-posedness and convergence (Extended Version)","author":"li","year":"2019","journal-title":"arXiv 1912 08504"},{"key":"ref16","article-title":"Multiple-step greedy policies in online and approximate reinforcement learning","author":"efroni","year":"2018","journal-title":"Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref17","article-title":"Beyond the one-step greedy approach in renforcement learning","author":"efroni","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6706982"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2772162"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029405"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2906423"},{"journal-title":"Athena Scientific","year":"1996","author":"bertsekas","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref29","article-title":"Data-driven control of unknown systems: A linear programming approach","author":"tanzanakis","year":"2020","journal-title":"arXiv 2003 00779"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/9781118029176"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2503980"},{"key":"ref7","first-page":"2959","article-title":"On actor-critic algorithms","volume":"20","author":"konda","year":"2010","journal-title":"SIAM Journal on Optimization"},{"journal-title":"Ph D thesis","year":"1989","author":"watkins","key":"ref2"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MCS.2012.2214134","article-title":"Reinforcement learning and feedback control: Using natural decision methods to design optimal adaptive controllers","volume":"32","author":"lewis","year":"2012","journal-title":"IEEE Control Systems Magazine"},{"year":"2012","author":"lewis","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2015.08.007"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2597763"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.09.043"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1998.694659"},{"key":"ref23","article-title":"Model-free H? optimal tracking control of constrained nonlinear systems via an iterative adaptive learning algorithm","author":"hou","year":"2019","journal-title":"IEEE Transactions on Systems Man and Cybernetic"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/11664550_13"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3152"}],"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\/09304315.pdf?arnumber=9304315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:58:27Z","timestamp":1656345507000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9304315\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,14]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/cdc42340.2020.9304315","relation":{},"subject":[],"published":{"date-parts":[[2020,12,14]]}}}