{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:58:59Z","timestamp":1767085139391,"version":"3.37.3"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"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":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tac.2023.3250032","type":"journal-article","created":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T19:11:39Z","timestamp":1677525099000},"page":"7006-7013","source":"Crossref","is-referenced-by-count":7,"title":["A Generalized Stacked Reinforcement Learning Method for Sampled Systems"],"prefix":"10.1109","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6184-3293","authenticated-orcid":false,"given":"Pavel","family":"Osinenko","sequence":"first","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1091-7459","authenticated-orcid":false,"given":"Dmitrii","family":"Dobriborsci","sequence":"additional","affiliation":[{"name":"Deggendorf Institute of Technology, Cham, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8869-6422","authenticated-orcid":false,"given":"Grigory","family":"Yaremenko","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2936-6271","authenticated-orcid":false,"given":"Georgiy","family":"Malaniya","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Berner","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2012.6402735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2015.09.022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MIE.2015.2478920"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2625238"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.07.619"},{"key":"ref11","first-page":"909","article-title":"Safe model-based reinforcement learning with stability guarantees","volume":"2017","author":"Berkenkamp","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340823"},{"key":"ref13","first-page":"990","article-title":"Deep value model predictive control","volume-title":"Proc. Conf. Robot Learn.","author":"Hoeller","year":"2020"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2015.XI.012","article-title":"DeepMPC: Learning deep latent features for model predictive control","volume-title":"Proc. Robot., Sci. Syst.","author":"Lenz","year":"2015"},{"key":"ref15","first-page":"133","article-title":"Aggressive deep driving: Combining convolutional neural networks and model predictive control","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","volume":"78","author":"Drews","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref17","article-title":"Blending MPC & value function approximation for efficient reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bhardwaj","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1111\/j.1934-6093.1999.tb00002.x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.803"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2237"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/ECC51009.2020.9143704"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2018.8550545"},{"key":"ref23","first-page":"6096","article-title":"Making deep Q-learning methods robust to time discretization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tallec","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.09.610"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3112498"},{"volume-title":"Nonlinear Systems","year":"1996","author":"Khalil","key":"ref27"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10298015\/10054472.pdf?arnumber=10054472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T22:26:45Z","timestamp":1709418405000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10054472\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":27,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tac.2023.3250032","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"type":"print","value":"0018-9286"},{"type":"electronic","value":"1558-2523"},{"type":"electronic","value":"2334-3303"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}