{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T15:15:06Z","timestamp":1751555706989,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T00:00:00Z","timestamp":1697846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106172"],"award-info":[{"award-number":["62106172"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2022ZD0116402"],"award-info":[{"award-number":["2022ZD0116402"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,21]]},"DOI":"10.1145\/3583780.3615454","type":"proceedings-article","created":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T07:45:42Z","timestamp":1697874342000},"page":"4695-4701","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["A Hierarchical Imitation Learning-based Decision Framework for Autonomous Driving"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8371-2297","authenticated-orcid":false,"given":"Hebin","family":"Liang","sequence":"first","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2986-6022","authenticated-orcid":false,"given":"Zibin","family":"Dong","sequence":"additional","affiliation":[{"name":"Harbin Institution of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9375-6605","authenticated-orcid":false,"given":"Yi","family":"Ma","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3084-8366","authenticated-orcid":false,"given":"Xiaotian","family":"Hao","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5016-6549","authenticated-orcid":false,"given":"Yan","family":"Zheng","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0422-8235","authenticated-orcid":false,"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Davide Del Testa","author":"Bojarski Mariusz","year":"2016","unstructured":"Mariusz Bojarski , Davide Del Testa , Daniel Dworakowski, Bernhard Firner , Beat Flepp, Prasoon Goyal, Lawrence D. Jackel, Mathew Monfort, Urs Muller, Jiakai Zhang, Xin Zhang, Jake Zhao, and Karol Zieba. 2016 . End to End Learning for Self-Driving Cars . arxiv: 1604.07316 [cs.CV] Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski, Bernhard Firner, Beat Flepp, Prasoon Goyal, Lawrence D. Jackel, Mathew Monfort, Urs Muller, Jiakai Zhang, Xin Zhang, Jake Zhao, and Karol Zieba. 2016. End to End Learning for Self-Driving Cars. arxiv: 1604.07316 [cs.CV]"},{"key":"e_1_3_2_1_2_1","unstructured":"Mariusz Bojarski Philip Yeres Anna Choromanska Krzysztof Choromanski Bernhard Firner Lawrence Jackel and Urs Muller. 2017. Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car. arxiv: 1704.07911 [cs.CV]  Mariusz Bojarski Philip Yeres Anna Choromanska Krzysztof Choromanski Bernhard Firner Lawrence Jackel and Urs Muller. 2017. Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car. arxiv: 1704.07911 [cs.CV]"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"e_1_3_2_1_4_1","volume-title":"Predictive Fuzzy Markov Decision Strategy for Autonomous Driving in Highways. In 2018 IEEE Conference on Control Technology and Applications (CCTA). 1032--1039","author":"Coskun Serdar","year":"2018","unstructured":"Serdar Coskun and Reza Langari . 2018 . Predictive Fuzzy Markov Decision Strategy for Autonomous Driving in Highways. In 2018 IEEE Conference on Control Technology and Applications (CCTA). 1032--1039 . https:\/\/doi.org\/10.1109\/CCTA.2018.8511369 10.1109\/CCTA.2018.8511369 Serdar Coskun and Reza Langari. 2018. Predictive Fuzzy Markov Decision Strategy for Autonomous Driving in Highways. In 2018 IEEE Conference on Control Technology and Applications (CCTA). 1032--1039. https:\/\/doi.org\/10.1109\/CCTA.2018.8511369"},{"key":"e_1_3_2_1_5_1","volume-title":"UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning. arxiv: 2111.11097 [cs.RO]","author":"Diehl Christopher","year":"2022","unstructured":"Christopher Diehl , Timo Sievernich , Martin Kr\u00fcger , Frank Hoffmann , and Torsten Bertram . 2022 . UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning. arxiv: 2111.11097 [cs.RO] Christopher Diehl, Timo Sievernich, Martin Kr\u00fcger, Frank Hoffmann, and Torsten Bertram. 2022. UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning. arxiv: 2111.11097 [cs.RO]"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8814124"},{"key":"e_1_3_2_1_7_1","volume-title":"International conference on machine learning. PMLR","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja , Aurick Zhou , Pieter Abbeel , and Sergey Levine . 2018 . Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor . In International conference on machine learning. PMLR , 1861--1870. Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. PMLR, 1861--1870."},{"key":"e_1_3_2_1_8_1","volume-title":"Oh (Eds.)","volume":"35","author":"Hu Anthony","year":"2022","unstructured":"Anthony Hu , Gianluca Corrado , Nicolas Griffiths , Zachary Murez , Corina Gurau , Hudson Yeo , Alex Kendall , Roberto Cipolla , and Jamie Shotton . 2022 . Model-Based Imitation Learning for Urban Driving. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A . Oh (Eds.) , Vol. 35 . Curran Associates, Inc. , 20703--20716. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/827cb489449ea216e4a257c47e407d18-Paper-Conference.pdf Anthony Hu, Gianluca Corrado, Nicolas Griffiths, Zachary Murez, Corina Gurau, Hudson Yeo, Alex Kendall, Roberto Cipolla, and Jamie Shotton. 2022. Model-Based Imitation Learning for Urban Driving. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 20703--20716. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/827cb489449ea216e4a257c47e407d18-Paper-Conference.pdf"},{"key":"e_1_3_2_1_9_1","volume-title":"Learning Interaction-aware Motion Prediction Model for Decision-making in Autonomous Driving. arXiv preprint arXiv:2302.03939","author":"Huang Zhiyu","year":"2023","unstructured":"Zhiyu Huang , Haochen Liu , Jingda Wu , Wenhui Huang , and Chen Lv. 2023. Learning Interaction-aware Motion Prediction Model for Decision-making in Autonomous Driving. arXiv preprint arXiv:2302.03939 ( 2023 ). Zhiyu Huang, Haochen Liu, Jingda Wu, Wenhui Huang, and Chen Lv. 2023. Learning Interaction-aware Motion Prediction Model for Decision-making in Autonomous Driving. arXiv preprint arXiv:2302.03939 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Conservative Q-Learning for Offline Reinforcement Learning. arxiv","author":"Kumar Aviral","year":"2006","unstructured":"Aviral Kumar , Aurick Zhou , George Tucker , and Sergey Levine . 2020. Conservative Q-Learning for Offline Reinforcement Learning. arxiv : 2006 .04779 [cs.LG] Aviral Kumar, Aurick Zhou, George Tucker, and Sergey Levine. 2020. Conservative Q-Learning for Offline Reinforcement Learning. arxiv: 2006.04779 [cs.LG]"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A Rusu Joel Veness Marc G Bellemare Alex Graves Martin Riedmiller Andreas K Fidjeland Georg Ostrovski etal 2015. Human-level control through deep reinforcement learning. nature Vol. 518 7540 (2015) 529--533.  Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A Rusu Joel Veness Marc G Bellemare Alex Graves Martin Riedmiller Andreas K Fidjeland Georg Ostrovski et al. 2015. Human-level control through deep reinforcement learning. nature Vol. 518 7540 (2015) 529--533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_12_1","unstructured":"Tung Nguyen Qinqing Zheng and Aditya Grover. 2023. Reliable Conditioning of Behavioral Cloning for Offline Reinforcement Learning. arxiv: 2210.05158 [cs.LG]  Tung Nguyen Qinqing Zheng and Aditya Grover. 2023. Reliable Conditioning of Behavioral Cloning for Offline Reinforcement Learning. arxiv: 2210.05158 [cs.LG]"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2840530"},{"key":"e_1_3_2_1_14_1","volume-title":"Implicit Offline Reinforcement Learning via Supervised Learning. arXiv preprint arXiv:2210.12272","author":"Piche Alexandre","year":"2022","unstructured":"Alexandre Piche , Rafael Pardinas , David Vazquez , Igor Mordatch , and Chris Pal . 2022. Implicit Offline Reinforcement Learning via Supervised Learning. arXiv preprint arXiv:2210.12272 ( 2022 ). Alexandre Piche, Rafael Pardinas, David Vazquez, Igor Mordatch, and Chris Pal. 2022. Implicit Offline Reinforcement Learning via Supervised Learning. arXiv preprint arXiv:2210.12272 (2022)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569400"},{"key":"e_1_3_2_1_16_1","volume-title":"Competition: Driving SMARTS. arXiv preprint arXiv:2211.07545","author":"Rasouli Amir","year":"2022","unstructured":"Amir Rasouli , Randy Goebel , Matthew E Taylor , Iuliia Kotseruba , Soheil Alizadeh , Tianpei Yang , Montgomery Alban , Florian Shkurti , Yuzheng Zhuang , Adam Scibior , 2022 . NeurIPS 2022 Competition: Driving SMARTS. arXiv preprint arXiv:2211.07545 (2022). Amir Rasouli, Randy Goebel, Matthew E Taylor, Iuliia Kotseruba, Soheil Alizadeh, Tianpei Yang, Montgomery Alban, Florian Shkurti, Yuzheng Zhuang, Adam Scibior, et al. 2022. NeurIPS 2022 Competition: Driving SMARTS. arXiv preprint arXiv:2211.07545 (2022)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5120\/ijca2016908314"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of The 6th Conference on Robot Learning (Proceedings of Machine Learning Research","volume":"737","author":"Shao Hao","year":"2023","unstructured":"Hao Shao , Letian Wang , Ruobing Chen , Hongsheng Li , and Yu Liu . 2023 . Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer . In Proceedings of The 6th Conference on Robot Learning (Proceedings of Machine Learning Research , Vol. 205), Karen Liu, Dana Kulic, and Jeff Ichnowski (Eds.). PMLR, 726-- 737 . https:\/\/proceedings.mlr.press\/v205\/shao23a.html Hao Shao, Letian Wang, Ruobing Chen, Hongsheng Li, and Yu Liu. 2023. Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer. In Proceedings of The 6th Conference on Robot Learning (Proceedings of Machine Learning Research, Vol. 205), Karen Liu, Dana Kulic, and Jeff Ichnowski (Eds.). PMLR, 726--737. https:\/\/proceedings.mlr.press\/v205\/shao23a.html"},{"key":"e_1_3_2_1_19_1","unstructured":"Yuan Tian. 2022. SMARTS_VCR. https:\/\/github.com\/yuant95\/SMARTS_VCR.  Yuan Tian. 2022. SMARTS_VCR. https:\/\/github.com\/yuant95\/SMARTS_VCR."},{"key":"e_1_3_2_1_20_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention Is All You Need. arxiv: 1706.03762 [cs.CL]  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention Is All You Need. arxiv: 1706.03762 [cs.CL]"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317735"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.376"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5772\/51314"},{"key":"e_1_3_2_1_24_1","volume-title":"Smarts: Scalable multi-agent reinforcement learning training school for autonomous driving. arXiv preprint arXiv:2010.09776","author":"Zhou Ming","year":"2020","unstructured":"Ming Zhou , Jun Luo , Julian Villella , Yaodong Yang , David Rusu , Jiayu Miao , Weinan Zhang , Montgomery Alban , Iman Fadakar , Zheng Chen , 2020 . Smarts: Scalable multi-agent reinforcement learning training school for autonomous driving. arXiv preprint arXiv:2010.09776 (2020). Ming Zhou, Jun Luo, Julian Villella, Yaodong Yang, David Rusu, Jiayu Miao, Weinan Zhang, Montgomery Alban, Iman Fadakar, Zheng Chen, et al. 2020. Smarts: Scalable multi-agent reinforcement learning training school for autonomous driving. arXiv preprint arXiv:2010.09776 (2020)."}],"event":{"name":"CIKM '23: The 32nd ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Birmingham United Kingdom","acronym":"CIKM '23"},"container-title":["Proceedings of the 32nd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583780.3615454","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583780.3615454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:54Z","timestamp":1750178214000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583780.3615454"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,21]]},"references-count":24,"alternative-id":["10.1145\/3583780.3615454","10.1145\/3583780"],"URL":"https:\/\/doi.org\/10.1145\/3583780.3615454","relation":{},"subject":[],"published":{"date-parts":[[2023,10,21]]},"assertion":[{"value":"2023-10-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}