{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:53:45Z","timestamp":1761598425509,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,11,19]],"date-time":"2021-11-19T00:00:00Z","timestamp":1637280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,11,19]]},"DOI":"10.1145\/3505688.3505693","type":"proceedings-article","created":{"date-parts":[[2022,4,9]],"date-time":"2022-04-09T16:07:04Z","timestamp":1649520424000},"page":"26-32","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Benchmarking Lane-changing Decision-making for Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Junjie","family":"Wang","sequence":"first","affiliation":[{"name":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation,Chinese Academy of Sciences, China and College of Artificial Intelligence, University of Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qichao","family":"Zhang","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation,Chinese Academy of Sciences, China and College of Artificial Intelligence, University of Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation,Chinese Academy of Sciences, China and College of Artificial Intelligence, University of Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,4,9]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"159","volume-title":"Elements of a European roadmap on smart systems for automated driving.\" Road Vehicle Automation 2","author":"Meyer G.","year":"2015","unstructured":"G. Meyer , J. Dokic , and B. M\u00fcller . \" Elements of a European roadmap on smart systems for automated driving.\" Road Vehicle Automation 2 . Springer , 2015 , pp. 153\u2013 159 . G. Meyer, J. Dokic, and B. M\u00fcller. \"Elements of a European roadmap on smart systems for automated driving.\" Road Vehicle Automation 2. Springer, 2015, pp. 153\u2013159."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2016.09.010"},{"key":"e_1_3_2_1_3_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R. S.","year":"2018","unstructured":"R. S. Sutton and A. G. Barto . Reinforcement Learning: An Introduction . MIT press , 2018 . R. S. Sutton and A. G. Barto. Reinforcement Learning: An Introduction. MIT press, 2018."},{"issue":"6","key":"e_1_3_2_1_4_1","first-page":"701","article-title":"Review of deep reinforcement learning and discussions on the development of computer Go","volume":"33","author":"Zhao D.","year":"2016","unstructured":"D. Zhao , K. Shao , Y. Zhu , D. Li , Y. Chen , H. Wang , D.-R. Liu , T. Zhou , and C.-H. Wang . \u201c Review of deep reinforcement learning and discussions on the development of computer Go .\u201d Control Theory and Applications. vol. 33 , no. 6 , pp. 701 \u2013 717 , 2016 . D. Zhao, K. Shao, Y. Zhu, D. Li, Y. Chen, H. Wang, D.-R. Liu,T. Zhou, and C.-H. Wang. \u201cReview of deep reinforcement learning and discussions on the development of computer Go.\u201d Control Theory and Applications. vol. 33, no. 6, pp. 701\u2013717, 2016.","journal-title":"Control Theory and Applications."},{"key":"e_1_3_2_1_5_1","volume-title":"Social attention for autonomous decision-making in dense traffic.\" arXiv preprint arXiv:1911.12250","author":"Leurent E.","year":"2019","unstructured":"E. Leurent and J. Mercat . \" Social attention for autonomous decision-making in dense traffic.\" arXiv preprint arXiv:1911.12250 , 2019 . E. Leurent and J. Mercat. \"Social attention for autonomous decision-making in dense traffic.\" arXiv preprint arXiv:1911.12250, 2019."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2019.2901089"},{"key":"e_1_3_2_1_7_1","volume-title":"IEEE","author":"Li D.","year":"2019","unstructured":"D. Li , D. Zhao , and Q. Zhang . \" Reinforcement learning based lane change decision-making with imaginary sampling.\" 2019 IEEE Symposium Series on Computational Intelligence . IEEE , 2019 . D. Li, D. Zhao, and Q. Zhang. \"Reinforcement learning based lane change decision-making with imaginary sampling.\" 2019 IEEE Symposium Series on Computational Intelligence. IEEE, 2019."},{"key":"e_1_3_2_1_8_1","volume-title":"PMLR","author":"Dosovitskiy A.","year":"2017","unstructured":"A. Dosovitskiy , G. Ros , F. Codevilla , A. Lopez , and V. Koltun . \" CARLA: An open urban driving simulator.\" Conference on Robot Learning . PMLR , 2017 . A. Dosovitskiy, G. Ros, F. Codevilla, A. Lopez, and V. Koltun. \"CARLA: An open urban driving simulator.\" Conference on Robot Learning. PMLR, 2017."},{"key":"e_1_3_2_1_9_1","volume-title":"Requirements of simulation scenario set for automated driving vehicle. [Online]. Available: http:\/\/www.ttbz.org.cn\/StandardManage\/Detail0","author":"Alliance C.I.I.","year":"2020","unstructured":"C.I.I. Alliance . Requirements of simulation scenario set for automated driving vehicle. [Online]. Available: http:\/\/www.ttbz.org.cn\/StandardManage\/Detail0 . 2020 . C.I.I.Alliance. Requirements of simulation scenario set for automated driving vehicle. [Online]. Available: http:\/\/www.ttbz.org.cn\/StandardManage\/Detail0. 2020."},{"key":"e_1_3_2_1_10_1","volume-title":"Mobil: General lane-changing model for car-following models.\" Dispon\u0131vel Acesso Dezembro","author":"Treiber M.","year":"2016","unstructured":"M. Treiber and D. Helbing . \" Mobil: General lane-changing model for car-following models.\" Dispon\u0131vel Acesso Dezembro , 2016 . M. Treiber and D. Helbing. \"Mobil: General lane-changing model for car-following models.\" Dispon\u0131vel Acesso Dezembro, 2016."},{"key":"e_1_3_2_1_11_1","volume-title":"Proximal policy optimization algorithms.\" arXiv preprint arXiv:1707.06347","author":"Schulman J.","year":"2017","unstructured":"J. Schulman , F. Wolski , P. Dhariwal , A. Radford , and O. Klimov . \" Proximal policy optimization algorithms.\" arXiv preprint arXiv:1707.06347 , 2017 . J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov. \"Proximal policy optimization algorithms.\" arXiv preprint arXiv:1707.06347, 2017."},{"key":"e_1_3_2_1_12_1","volume-title":"PMLR","author":"Mnih V.","year":"2016","unstructured":"V. Mnih , A. P. Badia , M. Mirza , A. Graves , T. Lillicrap , T. Harley , D. Silver , and K. Kavukcuoglu . \" Asynchronous methods for deep reinforcement learning.\" International Conference on Machine Learning . PMLR , 2016 . V. Mnih, A. P. Badia, M. Mirza, A. Graves, T. Lillicrap, T. Harley,D. Silver, and K. Kavukcuoglu. \"Asynchronous methods for deep reinforcement learning.\" International Conference on Machine Learning. PMLR, 2016."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2010.0084"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_15_1","volume-title":"PMLR","author":"Wang Z.","year":"2016","unstructured":"Z. Wang , T. Schaul , M. Hessel , H. Hasselt , M. Lanctot , and N. Freitas . \" Dueling network architectures for deep reinforcement learning.\" International Conference on Machine Learning . PMLR , 2016 . Z. Wang, T. Schaul, M. Hessel, H. Hasselt, M. Lanctot, and N. Freitas. \"Dueling network architectures for deep reinforcement learning.\" International Conference on Machine Learning. PMLR, 2016."},{"key":"e_1_3_2_1_16_1","volume-title":"Deep reinforcement learning with double Q-Learning.\" Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence","author":"Hasselt H. Van","year":"2016","unstructured":"H. Van Hasselt , A. Guez , and D. Silver . \" Deep reinforcement learning with double Q-Learning.\" Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence . 2016 . H. Van Hasselt, A. Guez, and D. Silver. \"Deep reinforcement learning with double Q-Learning.\" Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. 2016."},{"key":"e_1_3_2_1_17_1","article-title":"A survey of end-to-end driving: Architectures and training methods","author":"Tampuu A.","year":"2020","unstructured":"A. Tampuu , T. Matiisen , M. Semikin , D. Fishman , and N. Muhammad . \" A survey of end-to-end driving: Architectures and training methods .\" IEEE Transactions on Neural Networks and Learning Systems. 2020 . A. Tampuu, T. Matiisen, M. Semikin, D. Fishman, and N. Muhammad. \"A survey of end-to-end driving: Architectures and training methods.\" IEEE Transactions on Neural Networks and Learning Systems. 2020.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems."},{"key":"e_1_3_2_1_18_1","volume-title":"IEEE","author":"Wang J.","year":"2019","unstructured":"J. Wang , Q. Zhang , D. Zhao , and Y. Chen . \" Lane change decision-making through deep reinforcement learning with rule-based constraints.\" 2019 International Joint Conference on Neural Networks . IEEE , 2019 . J. Wang, Q. Zhang, D. Zhao, and Y. Chen. \"Lane change decision-making through deep reinforcement learning with rule-based constraints.\" 2019 International Joint Conference on Neural Networks. IEEE, 2019."}],"event":{"name":"ICRAI 2021: 2021 7th International Conference on Robotics and Artificial Intelligence","acronym":"ICRAI 2021","location":"Guangzhou China"},"container-title":["2021 7th International Conference on Robotics and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3505688.3505693","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3505688.3505693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:11:49Z","timestamp":1750191109000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3505688.3505693"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,19]]},"references-count":18,"alternative-id":["10.1145\/3505688.3505693","10.1145\/3505688"],"URL":"https:\/\/doi.org\/10.1145\/3505688.3505693","relation":{},"subject":[],"published":{"date-parts":[[2021,11,19]]},"assertion":[{"value":"2022-04-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}