{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T02:12:35Z","timestamp":1783044755244,"version":"3.54.6"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100007455","name":"Skolkovo Institute of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007455","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3112498","type":"journal-article","created":{"date-parts":[[2021,9,13]],"date-time":"2021-09-13T20:53:42Z","timestamp":1631566422000},"page":"127611-127618","source":"Crossref","is-referenced-by-count":9,"title":["Effects of Sampling and Prediction Horizon in Reinforcement Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6184-3293","authenticated-orcid":false,"given":"Pavel","family":"Osinenko","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1091-7459","authenticated-orcid":false,"given":"Dmitrii","family":"Dobriborsci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3182\/20100901-3-IT-2016.00301"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-39983-4_10"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ECC.2014.6862498"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2010.5674939"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT.2018.8352196"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3182\/20120823-5-NL-3013.00037"},{"key":"ref37","article-title":"Adaptive discretization for model-based reinforcement learning","author":"sinclair","year":"2020","journal-title":"arXiv 2007 00717"},{"key":"ref36","first-page":"6096","article-title":"Making deep Q-learning methods robust to time discretization","volume":"97","author":"tallec","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2015.07.073"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-83581-0_21"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3182\/20140824-6-ZA-1003.01093"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.858679"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-0578(07)60121-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref20","first-page":"1","article-title":"Dream to control: Learning behaviors by latent imagination","author":"hafner","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref22","first-page":"8289","article-title":"Differentiable MPC for end-to-end planning and control","volume":"31","author":"amos","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","first-page":"3875","article-title":"Bootstrap latent-predictive representations for multitask reinforcement learning","author":"guo","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","first-page":"1","article-title":"Infinite-horizon differentiable model predictive control","author":"east","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref23","first-page":"990","article-title":"Deep value model predictive control","volume":"100","author":"hoeller","year":"2020","journal-title":"Proc Conf Robot Learn"},{"key":"ref26","first-page":"211","article-title":"Practical reinforcement learning for MPC: Learning from sparse objectives in under an hour on a real robot","volume":"120","author":"karnchanachari","year":"2020","journal-title":"Proc 2nd Conf Learn Dyn Control"},{"key":"ref25","first-page":"8020","article-title":"Learning human objectives by evaluating hypothetical behavior","author":"reddy","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3182\/20120823-5-NL-3013.00030"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.128"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2006.878720"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2018.8550545"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.803"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.927799"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/9.751369"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(98)00073-9"},{"key":"ref10","first-page":"14887","article-title":"Online optimal control with linear dynamics and predictions: Algorithms and regret analysis","author":"li","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2514\/1.14511"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264382"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2008.2008349"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1109\/TCST.2011.2124461","article-title":"Model predictive control for the operation of building cooling systems","volume":"20","author":"ma","year":"2012","journal-title":"IEEE Trans Control Syst Technol"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0967-0661(02)00186-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2012.6402735"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2011.12.004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2015.09.022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009634810396"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3166\/ejc.11.310-334"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1201\/9781351006620-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref6","first-page":"8353","article-title":"Provably global convergence of actor-critic: A case for linear quadratic regulator with ergodic cost","author":"yang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"8514","article-title":"Finite-time analysis of approximate policy iteration for the linear quadratic regulator","author":"krauth","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","article-title":"Information theoretic regret bounds for online nonlinear control","author":"kakade","year":"2020","journal-title":"arXiv 2006 12466"},{"key":"ref7","first-page":"7521","article-title":"Structured policy iteration for linear quadratic regulator","author":"park","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/S0065-2377(01)26003-7","article-title":"Model predictive controllers: A critical synthesis of theory and industrial needs","author":"nikolaou","year":"2001","journal-title":"Advances in Chemical Engineering"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5650951"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399599"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1111\/j.1934-6093.1999.tb00002.x"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/S0167-6911(99)00073-0","article-title":"Sufficient conditions for stabilization of sampled-data nonlinear systems via discrete-time approximations","volume":"38","author":"ne\u0161i?","year":"1999","journal-title":"Syst Control Lett"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)37954-5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.14736\/kyb-2017-4-0578"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.na.2005.03.086"},{"key":"ref43","first-page":"1","article-title":"Practical stabilization of the extended nonholonomic double integrator","author":"pascoal","year":"2002","journal-title":"Proc 10th Medit Conf Control Autom"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09536718.pdf?arnumber=9536718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:36Z","timestamp":1639770936000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9536718\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3112498","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}