{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T23:49:34Z","timestamp":1784245774233,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819981830","type":"print"},{"value":"9789819981847","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8184-7_6","type":"book-chapter","created":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T07:02:41Z","timestamp":1700895761000},"page":"67-83","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["End-to-End Urban Autonomous Navigation with\u00a0Decision Hindsight"],"prefix":"10.1007","author":[{"given":"Qi","family":"Deng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangqing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qifu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaqian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rengang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,26]]},"reference":[{"issue":"8","key":"6_CR1","doi-asserted-by":"publisher","first-page":"12562","DOI":"10.1109\/TITS.2021.3115235","volume":"23","author":"M Ahmed","year":"2022","unstructured":"Ahmed, M., Abobakr, A., Lim, C.P., Nahavandi, S.: Policy-based reinforcement learning for training autonomous driving agents in urban areas with affordance learning. IEEE Trans. Intell. Transp. Syst. 23(8), 12562\u201312571 (2022). https:\/\/doi.org\/10.1109\/TITS.2021.3115235","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"6_CR2","doi-asserted-by":"publisher","unstructured":"Chen, D., Koltun, V., Kr\u00e4henb\u00fchl, P.: Learning to drive from a world on rails. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, 10\u201317 October 2021, pp. 15570\u201315579. IEEE (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01530","DOI":"10.1109\/ICCV48922.2021.01530"},{"issue":"6","key":"6_CR3","doi-asserted-by":"publisher","first-page":"5068","DOI":"10.1109\/TITS.2020.3046646","volume":"23","author":"J Chen","year":"2022","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 (2022). https:\/\/doi.org\/10.1109\/TITS.2020.3046646","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"6_CR4","doi-asserted-by":"publisher","unstructured":"Chen, J., Yuan, B., Tomizuka, M.: Model-free deep reinforcement learning for urban autonomous driving. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp. 2765\u20132771 (2019). https:\/\/doi.org\/10.1109\/ITSC.2019.8917306","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"6_CR5","unstructured":"Chen, L., et al.: Decision transformer: Reinforcement learning via sequence modeling. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol. 34, Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021(December), pp. 6\u201314, 2021. Virtual, pp. 15084\u201315097 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/7f489f642a0ddb10272b5c31057f0663-Abstract.html"},{"key":"6_CR6","doi-asserted-by":"publisher","unstructured":"Chen, M., Xiao, X., Zhang, W., Gao, X.: Efficient and stable information directed exploration for continuous reinforcement learning. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4023\u20134027 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746211","DOI":"10.1109\/ICASSP43922.2022.9746211"},{"key":"6_CR7","doi-asserted-by":"publisher","unstructured":"Chitta, K., Prakash, A., Geiger, A.: NEAT: neural attention fields for end-to-end autonomous driving. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, 10\u201317 October 2021, pp. 15773\u201315783. IEEE (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01550","DOI":"10.1109\/ICCV48922.2021.01550"},{"key":"6_CR8","doi-asserted-by":"publisher","unstructured":"Codevilla, F., Santana, E., L\u00f3pez, A.M., Gaidon, A.: Exploring the limitations of behavior cloning for autonomous driving. In: 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp. 9328\u20139337. IEEE (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00942","DOI":"10.1109\/ICCV.2019.00942"},{"key":"6_CR9","doi-asserted-by":"publisher","unstructured":"Deshpande, N., Vaufreydaz, D., Spalanzani, A.: Navigation in urban environments amongst pedestrians using multi-objective deep reinforcement learning. In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 923\u2013928 (2021). https:\/\/doi.org\/10.1109\/ITSC48978.2021.9564601","DOI":"10.1109\/ITSC48978.2021.9564601"},{"key":"6_CR10","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., L\u00f3pez, A.M., Koltun, V.: CARLA: an open urban driving simulator. In: 1st Annual Conference on Robot Learning, CoRL 2017, Mountain View, California, USA, 13\u201315 November 2017, Proceedings. Proceedings of Machine Learning Research, vol. 78, pp. 1\u201316. PMLR (2017). http:\/\/proceedings.mlr.press\/v78\/dosovitskiy17a.html"},{"key":"6_CR11","unstructured":"Fakoor, R., Chaudhari, P., Soatto, S., Smola, A.J.: Meta-q-learning. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, 26\u201330 April 2020. OpenReview.net (2020). https:\/\/openreview.net\/forum?id=SJeD3CEFPH"},{"issue":"12","key":"6_CR12","doi-asserted-by":"publisher","first-page":"5379","DOI":"10.1109\/TNNLS.2021.3109284","volume":"32","author":"C Huang","year":"2021","unstructured":"Huang, C., et al.: Deductive reinforcement learning for visual autonomous urban driving navigation. IEEE Trans. Neural Netw. Learn. Syst. 32(12), 5379\u20135391 (2021). https:\/\/doi.org\/10.1109\/TNNLS.2021.3109284","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"6_CR13","unstructured":"Janner, M., Li, Q., Levine, S.: Offline reinforcement learning as one big sequence modeling problem. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021(December), pp. 6\u201314, 2021. virtual, pp. 1273\u20131286 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/099fe6b0b444c23836c4a5d07346082b-Abstract.html"},{"issue":"3","key":"6_CR14","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1109\/TIV.2022.3149891","volume":"7","author":"E Kargar","year":"2022","unstructured":"Kargar, E., Kyrki, V.: Increasing the efficiency of policy learning for autonomous vehicles by multi-task representation learning. IEEE Trans. Intell. Veh. 7(3), 701\u2013710 (2022). https:\/\/doi.org\/10.1109\/TIV.2022.3149891","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"3","key":"6_CR15","doi-asserted-by":"publisher","first-page":"2921","DOI":"10.1109\/TVT.2022.3217299","volume":"72","author":"YH Khalil","year":"2023","unstructured":"Khalil, Y.H., Mouftah, H.T.: Exploiting multi-modal fusion for urban autonomous driving using latent deep reinforcement learning. IEEE Trans. Veh. Technol. 72(3), 2921\u20132935 (2023). https:\/\/doi.org\/10.1109\/TVT.2022.3217299","journal-title":"IEEE Trans. Veh. Technol."},{"key":"6_CR16","doi-asserted-by":"publisher","unstructured":"Li, W., Luo, H., Lin, Z., Zhang, C., Lu, Z., Ye, D.: A survey on transformers in reinforcement learning. CoRR abs\/2301.03044 (2023). https:\/\/doi.org\/10.48550\/arXiv.2301.03044","DOI":"10.48550\/arXiv.2301.03044"},{"key":"6_CR17","doi-asserted-by":"publisher","unstructured":"Liu, H., Huang, Z., Wu, J., Lv, C.: Improved deep reinforcement learning with expert demonstrations for urban autonomous driving. In: 2022 IEEE Intelligent Vehicles Symposium (IV), pp. 921\u2013928 (2022). https:\/\/doi.org\/10.1109\/IV51971.2022.9827073","DOI":"10.1109\/IV51971.2022.9827073"},{"key":"6_CR18","unstructured":"Loynd, R., Fernandez, R., Celikyilmaz, A., Swaminathan, A., Hausknecht, M.J.: Working memory graphs. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July 2020, Virtual Event. Proceedings of Machine Learning Research, vol. 119, pp. 6404\u20136414. PMLR (2020). http:\/\/proceedings.mlr.press\/v119\/loynd20a.html"},{"key":"6_CR19","unstructured":"Melo, L.C.: Transformers are meta-reinforcement learners. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesv\u00e1ri, C., Niu, G., Sabato, S. (eds.) International Conference on Machine Learning, ICML 2022, 17\u201323 July 2022, Baltimore, Maryland, USA. Proceedings of Machine Learning Research, vol. 162, pp. 15340\u201315359. PMLR (2022). https:\/\/proceedings.mlr.press\/v162\/melo22a.html"},{"key":"6_CR20","unstructured":"Parisotto, E., et al.: Stabilizing transformers for reinforcement learning. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July 2020, Virtual Event. Proceedings of Machine Learning Research, vol. 119, pp. 7487\u20137498. PMLR (2020). http:\/\/proceedings.mlr.press\/v119\/parisotto20a.html"},{"key":"6_CR21","doi-asserted-by":"publisher","unstructured":"Prakash, A., Chitta, K., Geiger, A.: Multi-modal fusion transformer for end-to-end autonomous driving. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, 19\u201325 June 2021, pp. 7077\u20137087. Computer Vision Foundation\/IEEE (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00700, https:\/\/openaccess.thecvf.com\/content\/CVPR2021\/html\/Prakash_Multi-Modal_Fusion_Transformer_for_End-to-End_Autonomous_Driving_CVPR_2021_paper.html","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"6_CR22","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M.I., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. In: Bengio, Y., LeCun, Y. (eds.) 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, 2\u20134 May 2016, Conference Track Proceedings (2016). http:\/\/arxiv.org\/abs\/1506.02438"},{"issue":"1","key":"6_CR23","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1146\/annurev-control-060117-105157","volume":"1","author":"W Schwarting","year":"2018","unstructured":"Schwarting, W., Alonso-Mora, J., Rus, D.: Planning and decision-making for autonomous vehicles. Ann. Rev. Control Robot. Autonom. Syst. 1(1), 187\u2013210 (2018). https:\/\/doi.org\/10.1146\/annurev-control-060117-105157","journal-title":"Ann. Rev. Control Robot. Autonom. Syst."},{"key":"6_CR24","unstructured":"Shao, H., Wang, L., Chen, R., Li, H., Liu, Y.: Safety-enhanced autonomous driving using interpretable sensor fusion transformer. In: Liu, K., Kulic, D., Ichnowski, J. (eds.) Conference on Robot Learning, CoRL 2022, 14\u201318 December 2022, Auckland, New Zealand. Proceedings of Machine Learning Research, vol. 205, pp. 726\u2013737. PMLR (2022). https:\/\/proceedings.mlr.press\/v205\/shao23a.html"},{"issue":"7782","key":"6_CR25","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019). https:\/\/doi.org\/10.1038\/s41586-019-1724-z","journal-title":"Nature"},{"issue":"3","key":"6_CR26","doi-asserted-by":"publisher","first-page":"2124","DOI":"10.1109\/TVT.2018.2890773","volume":"68","author":"C Wang","year":"2019","unstructured":"Wang, C., Wang, J., Shen, Y., Zhang, X.: Autonomous navigation of UAVs in large-scale complex environments: a deep reinforcement learning approach. IEEE Trans. Veh. Technol. 68(3), 2124\u20132136 (2019). https:\/\/doi.org\/10.1109\/TVT.2018.2890773","journal-title":"IEEE Trans. Veh. Technol."},{"key":"6_CR27","doi-asserted-by":"publisher","unstructured":"Wang, P., Chan, C.Y.: Formulation of deep reinforcement learning architecture toward autonomous driving for on-ramp merge. In: 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), pp. 1\u20136 (2017). https:\/\/doi.org\/10.1109\/ITSC.2017.8317735","DOI":"10.1109\/ITSC.2017.8317735"},{"key":"6_CR28","doi-asserted-by":"publisher","unstructured":"Wu, J., Huang, W., de Boer, N., Mo, Y., He, X., Lv, C.: Safe decision-making for lane-change of autonomous vehicles via human demonstration-aided reinforcement learning. In: 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), pp. 1228\u20131233 (2022). https:\/\/doi.org\/10.1109\/ITSC55140.2022.9921872","DOI":"10.1109\/ITSC55140.2022.9921872"},{"key":"6_CR29","unstructured":"Zambaldi, V.F., et al.: Deep reinforcement learning with relational inductive biases. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019. OpenReview.net (2019). https:\/\/openreview.net\/forum?id=HkxaFoC9KQ"},{"key":"6_CR30","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Liniger, A., Dai, D., Yu, F., Van Gool, L.: End-to-end urban driving by imitating a reinforcement learning coach. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15202\u201315212 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01494","DOI":"10.1109\/ICCV48922.2021.01494"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8184-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T06:03:19Z","timestamp":1711346599000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8184-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,26]]},"ISBN":["9789819981830","9789819981847"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8184-7_6","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,26]]},"assertion":[{"value":"26 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"650","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"51% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.14","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.46","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}