{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T17:14:15Z","timestamp":1740158055935,"version":"3.37.3"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T00:00:00Z","timestamp":1568764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T00:00:00Z","timestamp":1568764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 61603382","No. 61573353"],"award-info":[{"award-number":["No. 61603382","No. 61573353"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 61533017"],"award-info":[{"award-number":["No. 61533017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Ambient Intell Human Comput"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s12652-019-01503-y","type":"journal-article","created":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T18:06:51Z","timestamp":1568830011000},"page":"15673-15685","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Vision-based control in the open racing car simulator with deep and reinforcement learning"],"prefix":"10.1007","volume":"14","author":[{"given":"Yuanheng","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,18]]},"reference":[{"key":"1503_CR1","volume-title":"Reinforcement learning and dynamic programming using function approximators","author":"L Busoniu","year":"2010","unstructured":"Busoniu L, Babuska R, Schutter BD, Ernst D (2010) Reinforcement learning and dynamic programming using function approximators, 1st edn. CRC Press, Inc., Boca Raton","edition":"1"},{"key":"1503_CR2","doi-asserted-by":"crossref","unstructured":"Butz MV, L\u00f6nneker TD (2009). Optimized sensory-motor couplings plus strategy extensions for the TORCS car racing challenge. In: 2009 IEEE Symposium on Computational Intelligence and Games, pp 317\u2013324","DOI":"10.1109\/CIG.2009.5286458"},{"key":"1503_CR3","doi-asserted-by":"crossref","unstructured":"Cardamone L, Loiacono D, Lanzi PL (2009a) Learning drivers for TORCS through imitation using supervised methods. In: 2009 IEEE Symposium on Computational Intelligence and Games, pp 148\u2013155","DOI":"10.1109\/CIG.2009.5286480"},{"key":"1503_CR4","doi-asserted-by":"crossref","unstructured":"Cardamone L, Loiacono D, Lanzi PL (2009b) On-line neuroevolution applied to the open racing car simulator. In: 2009 IEEE Congress on Evolutionary Computation, pp 2622\u20132629","DOI":"10.1109\/CEC.2009.4983271"},{"key":"1503_CR5","doi-asserted-by":"crossref","unstructured":"Chen C, Seff A, Kornhauser A, Xiao J (2015) Deepdriving: learning affordance for direct perception in autonomous driving. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp 2722\u20132730","DOI":"10.1109\/ICCV.2015.312"},{"key":"1503_CR6","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1016\/j.ins.2017.08.035","volume":"432","author":"Y Chen","year":"2018","unstructured":"Chen Y, Zhao D, Lv L, Zhang Q (2018) Multi-task learning for dangerous object detection in autonomous driving. Inf Sci 432:559\u2013571","journal-title":"Inf Sci"},{"issue":"4","key":"1503_CR7","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1109\/TCDS.2016.2543839","volume":"8","author":"F Cruz","year":"2016","unstructured":"Cruz F, Magg S, Weber C, Wermter S (2016) Training agents with interactive reinforcement learning and contextual affordances. IEEE Trans Cognit Dev Syst 8(4):271\u2013284","journal-title":"IEEE Trans Cognit Dev Syst"},{"key":"1503_CR8","unstructured":"Deisenroth M, Rasmussen CE (2011) PILCO: A model-based and data-efficient approach to policy search. In: Getoor L, Scheffer T (eds) Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp 465\u2013472, New York, NY, USA"},{"key":"1503_CR9","volume-title":"Efficient reinforcement learning using Gaussian processes","author":"MP Deisenroth","year":"2010","unstructured":"Deisenroth MP (2010) Efficient reinforcement learning using Gaussian processes. KIT Scientific Publishing, Karlsruhe"},{"issue":"1","key":"1503_CR10","doi-asserted-by":"publisher","first-page":"4920","DOI":"10.1016\/j.ifacol.2017.08.747","volume":"50","author":"D G\u00f6rges","year":"2017","unstructured":"G\u00f6rges D (2017) Relations between model predictive control and reinforcement learning. IFAC-PapersOnLine 50(1):4920\u20134928 20th IFAC World Congress","journal-title":"IFAC-PapersOnLine"},{"issue":"2","key":"1503_CR11","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1002\/rob.20276","volume":"26","author":"R Hadsell","year":"2009","unstructured":"Hadsell R, Sermanet P, Ben J, Erkan A, Scoffier M, Kavukcuoglu K, Muller U, LeCun Y (2009) Learning long-range vision for autonomous off-road driving. J Field Robot 26(2):120\u2013144","journal-title":"J Field Robot"},{"key":"1503_CR12","unstructured":"Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov R (2012) Improving neural networks by preventing co-adaptation of feature detectors. CoRR, arXiv:1207.0580"},{"key":"1503_CR13","unstructured":"Huval B, Wang T, Tandon S, Kiske J, Song W, Pazhayampallil J, Andriluka M, Rajpurkar P, Migimatsu T, Cheng-Yue R, Mujica F, Coates A, Ng AY (2015) An empirical evaluation of deep learning on highway driving. CoRR, arXiv:1504.01716"},{"key":"1503_CR14","doi-asserted-by":"crossref","unstructured":"Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: Convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on Multimedia, pp 675\u2013678. ACM","DOI":"10.1145\/2647868.2654889"},{"key":"1503_CR15","unstructured":"Konda VR, Tsitsiklis JN (2000) Actor-critic algorithms. In: Advances in Neural Information Processing Systems, pp 1008\u20131014"},{"key":"1503_CR16","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Pereira F, Burges C, Bottou L, Weinberger K (eds), Advances in Neural Information Processing Systems 25, pp 1097\u20131105. Curran Associates, Inc"},{"issue":"7553","key":"1503_CR17","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Lecun","year":"2015","unstructured":"Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"1503_CR18","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. CoRR, arXiv:1509.02971"},{"key":"1503_CR19","doi-asserted-by":"crossref","unstructured":"Loiacono D, Togelius J, Lanzi PL, Kinnaird-Heether L, Lucas SM, Simmerson M, Perez D, Reynolds RG, Saez Y (2008) The WCCI 2008 simulated car racing competition. In: 2008 IEEE Symposium On Computational Intelligence and Games, pp 119\u2013126","DOI":"10.1109\/CIG.2008.5035630"},{"issue":"2","key":"1503_CR20","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/TCIAIG.2010.2050590","volume":"2","author":"D Loiacono","year":"2010","unstructured":"Loiacono D, Lanzi PL, Togelius J, Onieva E, Pelta DA, Butz MV, L\u00f6nneker TD, Cardamone L, Perez D, S\u00e1ez Y, Preuss M, Quadflieg J (2010a) The 2009 simulated car racing championship. IEEE Trans Comput Intell AI Games 2(2):131\u2013147","journal-title":"IEEE Trans Comput Intell AI Games"},{"key":"1503_CR21","doi-asserted-by":"crossref","unstructured":"Loiacono D, Prete A, Lanzi PL, Cardamone L (2010b) Learning to overtake in TORCS using simple reinforcement learning. In: IEEE Congress on Evolutionary Computation, pp 1\u20138","DOI":"10.1109\/CEC.2010.5586191"},{"issue":"3","key":"1503_CR22","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1109\/TAMD.2015.2494460","volume":"8","author":"VC Meola","year":"2016","unstructured":"Meola VC, Caligiore D, Sperati V, Zollo L, Ciancio AL, Taffoni F, Guglielmelli E, Baldassarre G (2016) Interplay of rhythmic and discrete manipulation movements during development: a policy-search reinforcement-learning robot model. IEEE Trans Cognit Dev Syst 8(3):152\u2013170","journal-title":"IEEE Trans Cognit Dev Syst"},{"key":"1503_CR23","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller MA (2013) Playing Atari with deep reinforcement learning. CoRR, arXiv:1312.5602"},{"issue":"7540","key":"1503_CR24","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"1503_CR25","unstructured":"Mnih V, Badia AP, Mirza M, Graves A, Lillicrap TP, Harley T, Silver D, Kavukcuoglu K (2016) Asynchronous methods for deep reinforcement learning. CoRR, arXiv:1602.01783"},{"key":"1503_CR26","doi-asserted-by":"crossref","unstructured":"Mun\u0300oz J, Gutierrez G, Sanchis A (2009) Controller for TORCS created by imitation. In: 2009 IEEE Symposium on Computational Intelligence and Games, pp 271\u2013278","DOI":"10.1109\/CIG.2009.5286464"},{"key":"1503_CR27","doi-asserted-by":"crossref","unstructured":"Mun\u0300oz J, Gutierrez G, Sanchis A (2010) A human-like TORCS controller for the simulated car racing championship. In: Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games, pp 473\u2013480","DOI":"10.1109\/ITW.2010.5593318"},{"issue":"3","key":"1503_CR28","doi-asserted-by":"publisher","first-page":"579","DOI":"10.2478\/amcs-2014-0042","volume":"24","author":"C Pawe\u0142","year":"2014","unstructured":"Pawe\u0142 C, \u0141ukasz P (2014) Imitation learning of car driving skills with decision trees and random forests. Int J Appl Math Comput Sci 24(3):579\u2013597","journal-title":"Int J Appl Math Comput Sci"},{"key":"1503_CR29","doi-asserted-by":"crossref","unstructured":"Riedmiller M (2005) Neural fitted Q iteration\u2013first experiences with a data efficient neural reinforcement learning method. In: Proceedings of 16th European Conference on Machine Learning, pp 317\u2013328, Porto, Portugal","DOI":"10.1007\/11564096_32"},{"issue":"2","key":"1503_CR30","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/TAMD.2015.2496248","volume":"8","author":"O Sigaud","year":"2016","unstructured":"Sigaud O, Droniou A (2016) Towards deep developmental learning. IEEE Trans Cognit Dev Syst 8(2):99\u2013114","journal-title":"IEEE Trans Cognit Dev Syst"},{"key":"1503_CR31","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, Cambridge"},{"issue":"3\u20134","key":"1503_CR32","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"C Watkins","year":"1992","unstructured":"Watkins C, Dayan P (1992) Q-learning. Mach Learn 8(3\u20134):279\u2013292","journal-title":"Mach Learn"},{"key":"1503_CR33","unstructured":"Wymann B, Dimitrakakisy C, Sumnery A, Guionneauz C (2015) TORCS: the open racing car simulator"},{"issue":"2","key":"1503_CR34","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1109\/TNNLS.2014.2371046","volume":"26","author":"D Zhao","year":"2015","unstructured":"Zhao D, Zhu Y (2015) MEC-a near-optimal online reinforcement learning algorithm for continuous deterministic systems. IEEE Trans Neural Netw Learn Syst 26(2):346\u2013356","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"1503_CR35","doi-asserted-by":"crossref","unstructured":"Zhao D, Zhu Y, Lv L, Chen Y, Zhang Q (2016) Convolutional fitted Q iteration for vision-based control problems. In: 2016 International Joint Conference on Neural Networks (IJCNN), pp 4539\u20134544","DOI":"10.1109\/IJCNN.2016.7727794"},{"key":"1503_CR36","doi-asserted-by":"crossref","unstructured":"Zhao D, Chen Y, Lv L (2017a) Deep reinforcement learning with visual attention for vehicle classification. IEEE Trans Cognit Dev Syst (in press)","DOI":"10.1109\/TCDS.2016.2614675"},{"issue":"2","key":"1503_CR37","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/MCI.2017.2670463","volume":"12","author":"D Zhao","year":"2017","unstructured":"Zhao D, Xia Z, Zhang Q (2017b) Model-free optimal control based intelligent cruise control with hardware-in-the-loop demonstration. IEEE Comput Intell Mag 12(2):56\u201369","journal-title":"IEEE Comput Intell Mag"},{"issue":"4","key":"1503_CR38","doi-asserted-by":"publisher","first-page":"1772","DOI":"10.1109\/TCST.2018.2811376","volume":"27","author":"Y Zhu","year":"2019","unstructured":"Zhu Y, Zhao D, Zhong Z (2019a) Adaptive optimal control of heterogeneous CACC system with uncertain dynamics. IEEE Trans Control Syst Technol 27(4):1772\u20131779","journal-title":"IEEE Trans Control Syst Technol"},{"issue":"4","key":"1503_CR39","doi-asserted-by":"publisher","first-page":"4235","DOI":"10.1109\/TSG.2018.2854300","volume":"10","author":"Y Zhu","year":"2019","unstructured":"Zhu Y, Zhao D, Li X, Wang D (2019b) Control-limited adaptive dynamic programming for multi-battery energy storage systems. IEEE Trans Smart Grid 10(4):4235\u20134244","journal-title":"IEEE Trans Smart Grid"}],"container-title":["Journal of Ambient Intelligence and Humanized Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-019-01503-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12652-019-01503-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-019-01503-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T11:22:54Z","timestamp":1703676174000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12652-019-01503-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,18]]},"references-count":39,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["1503"],"URL":"https:\/\/doi.org\/10.1007\/s12652-019-01503-y","relation":{},"ISSN":["1868-5137","1868-5145"],"issn-type":[{"type":"print","value":"1868-5137"},{"type":"electronic","value":"1868-5145"}],"subject":[],"published":{"date-parts":[[2019,9,18]]},"assertion":[{"value":"27 December 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}