{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T15:03:19Z","timestamp":1788361399679,"version":"build-2803163510"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T00:00:00Z","timestamp":1695513600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T00:00:00Z","timestamp":1695513600000},"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":[[2023,9,24]]},"DOI":"10.1109\/itsc57777.2023.10422451","type":"proceedings-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T23:32:39Z","timestamp":1707867159000},"page":"894-901","source":"Crossref","is-referenced-by-count":4,"title":["Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control"],"prefix":"10.1109","author":[{"given":"Bernd","family":"Frauenknecht","sequence":"first","affiliation":[{"name":"Institute for Data Science in Mechanical Engineering (DSME), RWTH Aachen University,Aachen,Germany,52068"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Ehlgen","sequence":"additional","affiliation":[{"name":"AI Lab Friedrichshafen, ZF Friedrichshafen AG,Friedrichshafen,Germany,88045"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Trimpe","sequence":"additional","affiliation":[{"name":"Institute for Data Science in Mechanical Engineering (DSME), RWTH Aachen University,Aachen,Germany,52068"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2016.07.007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2017.10.012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3054625"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/OJITS.2022.3181510"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2962338"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2020.3008612"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref12","article-title":"Solving rubiks cube with a robot hand","author":"Akkaya","year":"2019","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2007.894653"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2012.2198886"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968225"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967299"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064284"},{"key":"ref19","article-title":"TC-Driver: Trajectory Conditioned Driving for Robust Autonomous Racing - A Reinforcement Learning Approach","author":"Ghignone","year":"2022","journal-title":"ArXiv"},{"key":"ref20","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"Haarnoja","year":"2018","journal-title":"Int. Conf. on Mach. Learn."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref22","article-title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","author":"Chen","year":"2021","journal-title":"Int. Conf. on Learn. Rep."},{"key":"ref23","article-title":"Deep Reinforce-ment Learning in a Handful of Trials using Probabilistic Dynamics Models","volume":"31","author":"Chua","year":"2018","journal-title":"Adv. in Neur. Inf. Proc. Sys."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487277"},{"key":"ref25","article-title":"When to trust your model: model-based policy optimization","author":"Janner","year":"2019","journal-title":"Int. Conf. on Neur. Inf. Proc. Sys. Curran Associates Inc."},{"key":"ref26","article-title":"CARLA: An Open Urban Driving Simulator","author":"Dosovitskiy","year":"2017","journal-title":"Conf. on Rob. Learn."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref28","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"Mnih","year":"2016","journal-title":"Int. Conf. on Mach. Learn."},{"key":"ref29","article-title":"Trust Region Policy Optimization","author":"Schulman","year":"2015","journal-title":"Int. Conf. on Mach. Learn."},{"key":"ref30","article-title":"Proximal Policy Optimization Algorithms","author":"Schulman","year":"2017","journal-title":"ArXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref32","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"Conf. on Rob. Learn."},{"key":"ref33","article-title":"Addressing Function Ap-proximation Error in Actor-Critic Methods","author":"Fujimoto","year":"2018","journal-title":"ArXiv"},{"key":"ref34","article-title":"Playing Atari with Deep Reinforce-ment Learning","author":"Mnih","year":"2013","journal-title":"arXiv"},{"key":"ref35","article-title":"Issues in using function approximation for reinforcement learning","author":"Thrun","year":"1993","journal-title":"Con. Mod. Sum. School"},{"key":"ref36","article-title":"Double Q-learning","volume":"23","author":"Hasselt","year":"2010","journal-title":"Adv. in Neur. Inf. Proc. Sys."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref38","article-title":"Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning","author":"Anschel","year":"2017","journal-title":"Int. Conf. on Mach. Learn. PMLR"},{"key":"ref39","article-title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-learning","author":"Lan","year":"2020","journal-title":"Arxiv"},{"key":"ref40","article-title":"SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning","author":"Lee","year":"2021","journal-title":"Int. Conf. on Mach. Learn."},{"key":"ref41","article-title":"Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World","author":"Smith","year":"2021","journal-title":"arXiv"},{"key":"ref42","article-title":"PILCO: a model-based and data-efficient approach to policy search","author":"Deisenroth","year":"2011","journal-title":"Int. Conf. on Mach. Learn."},{"key":"ref43","article-title":"Improving PILCO with Bayesian neural network dynamics models","author":"Gal","year":"2016","journal-title":"Int. Conf. on Mach. Learn."},{"key":"ref44","article-title":"Concrete dropout","author":"Gal","year":"2018","journal-title":"Adv. in Neur. Inf. Proc. Sys."},{"key":"ref45","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"Lakshminarayanan","year":"2017","journal-title":"Int. Conf. on Neur. Inf. Proc. Sys."},{"key":"ref46","article-title":"Guided Policy Search","author":"Levine","year":"2013","journal-title":"Int. Conf. on Mach. Learn."},{"key":"ref47","article-title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","author":"Feinberg","year":"2018","journal-title":"arXiv"},{"key":"ref48","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","author":"Buckman","year":"2018","journal-title":"Int. Conf. on Neur. Inf. Proc. Sys."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2865891"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-444-53859-8.00003-5"},{"key":"ref52","article-title":"Model-Ensemble Trust-Region Policy Optimization","author":"Kurutach","year":"2018","journal-title":"Arxiv"},{"key":"ref53","article-title":"Uncertainty-driven Imagination for Continuous Deep Reinforcement Learning","author":"Kalweit","year":"2017","journal-title":"Conf. on Rob. Learn."},{"key":"ref54","article-title":"Algorithmic Framework for Model-based Deep Reinforcement Learning with The-oretical Guarantees","author":"Luo","year":"2018","journal-title":"arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3311\/PPtr.18581"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562079"},{"key":"ref59","article-title":"OpenAI Gym","author":"Brockman","year":"2016","journal-title":"arXiv"},{"key":"ref60","first-page":"arXiv:2104.10159","article-title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","author":"Pineda","year":"2021","journal-title":"arXiv"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"event":{"name":"2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","location":"Bilbao, Spain","start":{"date-parts":[[2023,9,24]]},"end":{"date-parts":[[2023,9,28]]}},"container-title":["2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10420842\/10420843\/10422451.pdf?arnumber=10422451","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T11:49:16Z","timestamp":1709466556000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10422451\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,24]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/itsc57777.2023.10422451","relation":{},"subject":[],"published":{"date-parts":[[2023,9,24]]}}}