{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T12:25:32Z","timestamp":1756383932768,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"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":[[2021,7,11]]},"DOI":"10.1109\/iv48863.2021.9576031","type":"proceedings-article","created":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T20:59:16Z","timestamp":1635800356000},"page":"1213-1219","source":"Crossref","is-referenced-by-count":7,"title":["Speed Tracking Control Using Model-Based Reinforcement Learning in a Real Vehicle"],"prefix":"10.1109","author":[{"given":"Luca","family":"Puccetti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed","family":"Yasser","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Rathgeber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Becker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soren","family":"Hohmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Parameter space noise for exploration","author":"plappert","year":"0","journal-title":"6th Conference on Learning Representations (ICLR 2018)"},{"article-title":"Model-based reinforcement learning: A survey","year":"2020","author":"moerland","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ECC.2015.7330913"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-019-09426-y"},{"key":"ref15","article-title":"System Identification: Theory for the User","author":"ljung","year":"2012","journal-title":"ser Prentice Hall Information and System Sciences Series"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814865"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917113"},{"key":"ref19","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Machine Learning Research"},{"year":"2017","key":"ref4","article-title":"Automated driving at the bmw group"},{"year":"0","key":"ref27","article-title":"Ds1007 ppc processor board"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917113"},{"article-title":"Benchmarking model-based reinforcement learning","year":"2019","author":"wang","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAR49639.2020.9108051"},{"key":"ref8","article-title":"Control policy with autocorrelated noise in reinforcement learning for robotics","volume":"5","author":"wawrzy?ski","year":"2015","journal-title":"International Journal of Machine Learning and Computing L Huang Ed"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1970.1099363"},{"article-title":"Challenges of real-world reinforcement learning","year":"2019","author":"dulac-arnold","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78879-9"},{"key":"ref1","article-title":"Reinforcement Learning: An Introduction","author":"sutton","year":"2018","journal-title":"ser Adaptive Computation and Machine Learning"},{"journal-title":"Insights in reinforcement learning Formal analysis and empirical evaluation of temporal-difference learning Utrecht Universiteit Utrecht","year":"2011","author":"van hasselt","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487756"},{"key":"ref21","article-title":"When to trust your model: Model-based policy optimization","author":"janner","year":"0","journal-title":"Advances in Neural Information Processing Systems 2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0067700"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICSEE.2018.8646302"},{"journal-title":"AutoBox","year":"0","key":"ref26"},{"key":"ref25","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"0","journal-title":"Proceedings of the 30th International Conference on Machine Learning ser Proceedings of Machine Learning Research S Dasgupta and D McAllester Eds PMLR"}],"event":{"name":"2021 IEEE Intelligent Vehicles Symposium (IV)","start":{"date-parts":[[2021,7,11]]},"location":"Nagoya, Japan","end":{"date-parts":[[2021,7,17]]}},"container-title":["2021 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9575127\/9575130\/09576031.pdf?arnumber=9576031","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:47:53Z","timestamp":1652197673000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9576031\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iv48863.2021.9576031","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]}}}