{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T06:56:33Z","timestamp":1765608993437,"version":"3.37.3"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100005416","name":"Industry Partners Borregaard, Elkem, Yara, Hydro, and the Research Council of Norway through the Project \u201cToward Autonomy in Process Industries\u201d","doi-asserted-by":"publisher","award":["294544"],"award-info":[{"award-number":["294544"]}],"id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005416","name":"Project \u201cSafe Reinforcement Learning using Model Predictive Control\u201d","doi-asserted-by":"publisher","award":["300172"],"award-info":[{"award-number":["300172"]}],"id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3282842","type":"journal-article","created":{"date-parts":[[2023,6,5]],"date-time":"2023-06-05T17:56:26Z","timestamp":1685987786000},"page":"60724-60736","source":"Crossref","is-referenced-by-count":3,"title":["Variance-Based Exploration for Learning Model Predictive Control"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2488-2784","authenticated-orcid":false,"given":"Katrine","family":"Seel","sequence":"first","affiliation":[{"name":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6761-0856","authenticated-orcid":false,"given":"Alberto","family":"Bemporad","sequence":"additional","affiliation":[{"name":"IMT School for Advanced Studies, Lucca, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6054-2133","authenticated-orcid":false,"given":"S\u00e9bastien","family":"Gros","sequence":"additional","affiliation":[{"name":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5663-0795","authenticated-orcid":false,"given":"Jan Tommy","family":"Gravdahl","sequence":"additional","affiliation":[{"name":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5361"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2019.2949757"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.02.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2913768"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref8","first-page":"1","article-title":"Boltzmann exploration done right","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Cesa-Bianchi"},{"key":"ref9","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref10","first-page":"1","article-title":"Parameter space noise for exploration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Plappert"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2307\/2332286"},{"key":"ref14","first-page":"2377","article-title":"Generalization and exploration via randomized value functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Osband"},{"key":"ref15","first-page":"1","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Osband"},{"key":"ref16","first-page":"1","article-title":"Noisy networks for exploration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fortunato"},{"key":"ref17","article-title":"UCB exploration via Q-ensembles","author":"Chen","year":"2017","journal-title":"arXiv:1706.01502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCTIS51085.2021.00052"},{"key":"ref19","first-page":"1","article-title":"Plan online, learn offline: Efficient learning and exploration via model-based control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lowrey"},{"key":"ref20","first-page":"1","article-title":"Soft constraints and exact penalty functions in model predictive control","volume-title":"Proc. UKACC Int. Conf. Control","author":"Kerrigan"},{"key":"ref21","article-title":"Towards safe reinforcement learning using NMPC and policy gradients: Part I\u2014Stochastic case","author":"Gros","year":"2019","journal-title":"arXiv:1906.04057"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/OJCSYS.2022.3221063"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011255519438"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-020-00215-w"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/800186.810616"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1198\/TECH.2011.09154"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.01.028"},{"key":"ref29","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1017\/9781009089517"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10143647.pdf?arnumber=10143647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T09:00:31Z","timestamp":1709283631000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10143647\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3282842","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}