{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T17:36:22Z","timestamp":1762018582733,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032061058","type":"print"},{"value":"9783032061065","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-06106-5_11","type":"book-chapter","created":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T10:09:06Z","timestamp":1759399746000},"page":"179-197","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Efficient and\u00a0Generalized End-to-End Autonomous Driving System with\u00a0Latent Deep Reinforcement Learning and\u00a0Demonstrations"],"prefix":"10.1007","author":[{"given":"Zuojin","family":"Tang","sequence":"first","affiliation":[]},{"given":"Xiaoyu","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yongqiang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jianyu","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,3]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Bansal, M., Krizhevsky, A., Ogale, A.: ChauffeurNet: learning to drive by imitating the best and synthesizing the worst. arXiv preprint arXiv:1812.03079 (2018)","DOI":"10.15607\/RSS.2019.XV.031"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Bengtsson, T., Bickel, P., Li, B.: Curse-of-dimensionality revisited: collapse of the particle filter in very large scale systems. In: Probability and statistics: Essays in honor of David A. Freedman, vol.\u00a02, pp. 316\u2013335. Institute of Mathematical Statistics (2008)","DOI":"10.1214\/193940307000000518"},{"issue":"6","key":"11_CR3","doi-asserted-by":"publisher","first-page":"5068","DOI":"10.1109\/TITS.2020.3046646","volume":"23","author":"J Chen","year":"2021","unstructured":"Chen, J., Li, S.E., Tomizuka, M.: Interpretable end-to-end urban autonomous driving with latent deep reinforcement learning. IEEE Trans. Intell. Transp. Syst. 23(6), 5068\u20135078 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Wang, Z., Tomizuka, M.: Deep hierarchical reinforcement learning for autonomous driving with distinct behaviors. In: 2018 IEEE Intelligent Vehicles Symposium, pp. 1239\u20131244. IEEE (2018)","DOI":"10.1109\/IVS.2018.8500368"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Chen, J., Yuan, B., Tomizuka, M.: Deep imitation learning for autonomous driving in generic urban scenarios with enhanced safety. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 2884\u20132890. IEEE (2019)","DOI":"10.1109\/IROS40897.2019.8968225"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Yuan, B., Tomizuka, M.: Model-free deep reinforcement learning for urban autonomous driving. In: 2019 IEEE Intelligent Transportation Systems Conference, pp. 2765\u20132771. IEEE (2019)","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"11_CR7","unstructured":"Chen, X., Mu, Y.M., Luo, P., Li, S., Chen, J.: Flow-based recurrent belief state learning for POMDPs. In: International Conference on Machine Learning, pp. 3444\u20133468. PMLR (2022)"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Codevilla, F., M\u00fcller, M., L\u00f3pez, A., Koltun, V., Dosovitskiy, A.: End-to-end driving via conditional imitation learning. In: 2018 IEEE International Conference on Robotics and Automation, pp. 4693\u20134700. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"11_CR9","unstructured":"De\u00a0Cao, N., Aziz, W., Titov, I.: Block neural autoregressive flow. In: Uncertainty in Artificial Intelligence, pp. 1263\u20131273. PMLR (2020)"},{"key":"11_CR10","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. arXiv preprint arXiv:1605.08803 (2016)"},{"key":"11_CR11","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: an open urban driving simulator. In: Conference on Robot Learning, pp. 1\u201316. PMLR (2017)"},{"key":"11_CR12","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596. PMLR (2018)"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Gao, Z., et al.: Enhance sample efficiency and robustness of end-to-end urban autonomous driving via semantic masked world model. IEEE Trans. Intell. Transp. Syst. 25(10), 13067 \u201313079 (2024)","DOI":"10.1109\/TITS.2024.3400227"},{"issue":"4","key":"11_CR14","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1109\/TITS.2015.2498841","volume":"17","author":"D Gonz\u00e1lez","year":"2015","unstructured":"Gonz\u00e1lez, D., P\u00e9rez, J., Milan\u00e9s, V., Nashashibi, F.: A review of motion planning techniques for automated vehicles. IEEE Trans. Intell. Transp. Syst. 17(4), 1135\u20131145 (2015)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"11_CR15","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"11_CR16","unstructured":"Hafner, D., Lillicrap, T., Ba, J., Norouzi, M.: Dream to control: learning behaviors by latent imagination. arXiv preprint arXiv:1912.01603 (2019)"},{"key":"11_CR17","unstructured":"Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: International Conference on Machine Learning, pp. 2555\u20132565. PMLR (2019)"},{"key":"11_CR18","unstructured":"Huang, C.W., Krueger, D., Lacoste, A., Courville, A.: Neural autoregressive flows. In: International Conference on Machine Learning, pp. 2078\u20132087. PMLR (2018)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Z., Liu, H., Wu, J., Lv, C.: Conditional predictive behavior planning with inverse reinforcement learning for human-like autonomous driving. IEEE Trans. Intell. Transp. Syst. 24(7), 7244\u20137258 (2023)","DOI":"10.1109\/TITS.2023.3254579"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Huang, Z., Sheng, Z., Ma, C., Chen, S.: Human as AI mentor: enhanced human-in-the-loop reinforcement learning for safe and efficient autonomous driving. arXiv preprint arXiv:2401.03160 (2024)","DOI":"10.1016\/j.commtr.2024.100127"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Jordan, M.I., Ghahramani, Z., Jaakkola, T.S., Saul, L.K.: An Introduction to Variational Methods for Graphical Models. In: Learning in Graphical Models, pp. 105\u2013161 (1998)","DOI":"10.1007\/978-94-011-5014-9_5"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Kendall, A., et al.: Learning to drive in a day. In: 2019 International Conference on Robotics and Automation, pp. 8248\u20138254. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"11_CR23","first-page":"1179","volume":"33","author":"A Kumar","year":"2020","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative Q-learning for offline reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 1179\u20131191 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR24","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Liu, H., Huang, Z., Lv, C.: Improved deep reinforcement learning with expert demonstrations for urban autonomous driving. In: 2022 IEEE Intelligent Vehicles Symposium (IV), pp. 921\u2013928 (2021). https:\/\/api.semanticscholar.org\/CorpusID:231951804","DOI":"10.1109\/IV51971.2022.9827073"},{"key":"11_CR26","unstructured":"Liu, H., Huang, Z., Mo, X., Lv, C.: Augmenting reinforcement learning with transformer-based scene representation learning for decision-making of autonomous driving. arXiv preprint arXiv:2208.12263 (2022)"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Mero, L.L., Yi, D., Dianati, M., Mouzakitis, A.: A survey on imitation learning techniques for end-to-end autonomous vehicles. IEEE Trans. Intelligent Transp. Syst. 23, 14128\u201314147 (2022). https:\/\/api.semanticscholar.org\/CorpusID:246539766","DOI":"10.1109\/TITS.2022.3144867"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Mnih, V., et\u00a0al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"11_CR29","unstructured":"Murdoch, A., Schoeman, J.C., Jordaan, H.W.: Partial end-to-end reinforcement learning for robustness against modelling error in autonomous racing. arXiv preprint arXiv:2312.06406 (2023)"},{"key":"11_CR30","unstructured":"Nehme, G., Deo, T.Y.: Safe navigation: training autonomous vehicles using deep reinforcement learning in Carla. arXiv preprint arXiv:2311.10735 (2023)"},{"issue":"1","key":"11_CR31","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/TIV.2016.2578706","volume":"1","author":"B Paden","year":"2016","unstructured":"Paden, B., \u010c\u00e1p, M., Yong, S.Z., Yershov, D., Frazzoli, E.: A survey of motion planning and control techniques for self-driving urban vehicles. IEEE Trans. Intell. Veh. 1(1), 33\u201355 (2016)","journal-title":"IEEE Trans. Intell. Veh."},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Rajeswaran, A., et al.: Learning complex dexterous manipulation with deep reinforcement learning and demonstrations. arXiv preprint arXiv:1709.10087 (2017)","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"11_CR33","unstructured":"Rezende, D., Mohamed, S.: Variational inference with normalizing flows. In: International Conference on Machine Learning, pp. 1530\u20131538. PMLR (2015)"},{"key":"11_CR34","unstructured":"Silver, D., Veness, J.: Monte-Carlo planning in large POMDPs. Adv. Neural Info. Process. Syst. 23 (2010)"},{"key":"11_CR35","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (2018)"},{"key":"11_CR36","unstructured":"Tang, Z., Chen, X., Li, Y., Chen, J.: Efficient and generalized end-to-end autonomous driving system with latent deep reinforcement learning and demonstrations. arXiv preprint arXiv:2401.11792 (2024)"},{"key":"11_CR37","unstructured":"Tang, Z., Hu, B., Zhao, C., Ma, D., Pan, G., Liu, B.: How to build a pre-trained multimodal model for simultaneously chatting and decision-making? arXiv preprint arXiv:2410.15885 (2024)"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Theodorou, E., Buchli, J., Schaal, S.: Reinforcement learning of motor skills in high dimensions: a path integral approach. In: 2010 IEEE International Conference on Robotics and Automation, pp. 2397\u20132403. IEEE (2010)","DOI":"10.1109\/ROBOT.2010.5509336"},{"key":"11_CR39","unstructured":"Thrun, S.: Monte Carlo POMDPs. Adv. Neural Info. Process. Syst. 12 (1999)"},{"issue":"9","key":"11_CR40","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1002\/rob.20147","volume":"23","author":"S Thrun","year":"2006","unstructured":"Thrun, S., et al.: Stanley: the robot that won the DARPA grand challenge. J. field Robot. 23(9), 661\u2013692 (2006)","journal-title":"J. field Robot."},{"issue":"8","key":"11_CR41","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1002\/rob.20255","volume":"25","author":"C Urmson","year":"2008","unstructured":"Urmson, C., et al.: Autonomous driving in urban environments: boss and the urban challenge. J. field Robot. 25(8), 425\u2013466 (2008)","journal-title":"J. field Robot."},{"key":"11_CR42","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hoof, H., Hermans, T., Neumann, G., Peters, J.: Learning robot in-hand manipulation with tactile features. In: 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), pp. 121\u2013127. IEEE (2015)","DOI":"10.1109\/HUMANOIDS.2015.7363524"},{"key":"11_CR43","doi-asserted-by":"crossref","unstructured":"Wolf, P., et al.: Learning how to drive in a real world simulation with deep q-networks. In: 2017 IEEE Intelligent Vehicles Symposium, pp. 244\u2013250. IEEE (2017)","DOI":"10.1109\/IVS.2017.7995727"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Han, S., Wang, J., Miao, F.: Spatial-temporal-aware safe multi-agent reinforcement learning of connected autonomous vehicles in challenging scenarios. In: 2023 IEEE International Conference on Robotics and Automation, pp. 5574\u20135580. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161216"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Zhao, C., Zhou, Z., Liu, B.: On context distribution shift in task representation learning for online meta RL. In: International Conference on Intelligent Computing, pp. 614\u2013628. Springer (2023)","DOI":"10.1007\/978-981-99-4761-4_52"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, W., Cao, Z., Deng, N., Jiang, K., Yang, D.: Identify, estimate and bound the uncertainty of reinforcement learning for autonomous driving. IEEE Trans. Intell. Transp. Syst. 24(8), 7932\u20137942 (2023)","DOI":"10.1109\/TITS.2023.3266885"},{"key":"11_CR47","unstructured":"Zhou, Z., Hu, B., Zhao, C., Zhang, P., Liu, B.: Large language model as a policy teacher for training reinforcement learning agents. arXiv preprint arXiv:2311.13373 (2023)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06106-5_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T10:09:28Z","timestamp":1759399768000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06106-5_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"ISBN":["9783032061058","9783032061065"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06106-5_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]},"assertion":[{"value":"3 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}