{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:15:33Z","timestamp":1774455333766,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T00:00:00Z","timestamp":1696982400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T00:00:00Z","timestamp":1696982400000},"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":[],"published-print":{"date-parts":[[2023,10,11]]},"DOI":"10.1109\/icstcc59206.2023.10308475","type":"proceedings-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T18:49:18Z","timestamp":1699642158000},"page":"349-355","source":"Crossref","is-referenced-by-count":1,"title":["Learning-Based Model Predictive Control Using Double Q-Learning"],"prefix":"10.1109","author":[{"given":"Hoomaan","family":"MoradiMaryamnegari","sequence":"first","affiliation":[{"name":"Free University of Bozen-Bolzano,Faculty of Engineering,Bolzano,Italy"}]},{"given":"Marco","family":"Frego","sequence":"additional","affiliation":[{"name":"Free University of Bozen-Bolzano,Faculty of Engineering,Bolzano,Italy"}]},{"given":"Angelika","family":"Peer","sequence":"additional","affiliation":[{"name":"Free University of Bozen-Bolzano,Faculty of Engineering,Bolzano,Italy"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9482765"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2913768"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483100"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3228922"},{"key":"ref6","first-page":"01","article-title":"Sarsa-based Model Predictive Control with Improved Performance and Computational Complexity","volume-title":"2022 IEEE 5th International Conference on Industrial CyberPhysical Systems (ICPS)","author":"Lu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2022.107727"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"81177","DOI":"10.1109\/ACCESS.2022.3195530","article-title":"Model Predictive Control-Based Reinforcement Learning Using Expected Sarsa","volume":"10","author":"MoradiMaryamnegari","year":"2022","journal-title":"IEEE Access"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CoDIT58514.2023.10284335"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683750"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA48906.2021.9659202"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683333"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483016"},{"key":"ref14","volume-title":"Blending MPC and value function approximation for efficient reinforcement learning","author":"Bhardwaj","year":"2020"},{"key":"ref15","first-page":"8130","article-title":"Combining system identification with reinforcement learning-based MPC","volume":"53","author":"Martinsen","year":"2020","journal-title":"IFACPapersOnLine"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2021.105024"},{"key":"ref17","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref18","article-title":"Double Q-learning","volume":"23","author":"Hasselt","year":"2010","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/aic.17658"},{"key":"ref20","first-page":"2094","article-title":"Deep Reinforcement Learning with Double Q-learning","volume-title":"30th AAAI Conference on Artificial Intelligence, AAAI 2016","author":"van Hasselt"},{"key":"ref21","volume-title":"Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?","author":"Nachum","year":"2019"},{"key":"ref22","volume-title":"A Survey of Exploration Methods in Reinforcement Learning","author":"Amin","year":"2021"}],"event":{"name":"2023 27th International Conference on System Theory, Control and Computing (ICSTCC)","location":"Timisoara, Romania","start":{"date-parts":[[2023,10,11]]},"end":{"date-parts":[[2023,10,13]]}},"container-title":["2023 27th International Conference on System Theory, Control and Computing (ICSTCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10305866\/10308427\/10308475.pdf?arnumber=10308475","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T13:27:37Z","timestamp":1709386057000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10308475\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,11]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icstcc59206.2023.10308475","relation":{},"subject":[],"published":{"date-parts":[[2023,10,11]]}}}