{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T06:09:15Z","timestamp":1759730955390,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T00:00:00Z","timestamp":1722556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,2]]},"DOI":"10.1145\/3696271.3696284","type":"proceedings-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T10:47:56Z","timestamp":1733136476000},"page":"78-84","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep Reinforcement Learning for Autonomous Driving with Multi-Scenario Fusion: A Unified Reward Function Approach"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0336-9818","authenticated-orcid":false,"given":"Dongkun","family":"Han","sequence":"first","affiliation":[{"name":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8653-2483","authenticated-orcid":false,"given":"Sen","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"e_1_3_3_1_1_2","doi-asserted-by":"publisher","DOI":"10.1117\/12.2644369"},{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3185159"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3226579"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/OJITS.2022.3172981"},{"key":"e_1_3_3_1_7_2","volume-title":"Playing Atari with Deep Reinforcement Learning","author":"V. Mnih","year":"2013","unstructured":"V. Mnih et al., \u201cPlaying Atari with Deep Reinforcement Learning.\u201d arXiv, 2013."},{"key":"e_1_3_3_1_8_2","volume-title":"Quantitative Analysis and Prediction of Academic Performance of Students Using Machine Learning.\u00a0Sustainability, no.\u00a015, 12531","author":"H.","year":"2023","unstructured":"Zhao, L.; Ren, J.; Zhang, L.; Zhao, H. Quantitative Analysis and Prediction of Academic Performance of Students Using Machine Learning.\u00a0Sustainability, no.\u00a015, 12531, 2023."},{"issue":"268","key":"e_1_3_3_1_9_2","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin A.","year":"2021","unstructured":"A. Raffin, A. Hill, A. Gleave, A. Kanervisto, M. Ernestus, and N. Dormann, \u201cStable-baselines3: Reliable reinforcement learning implementations,\u201d Journal of Machine Learning Research, vol. 22, no. 268, pp. 1\u20138, 2021.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_3_1_10_2","volume-title":"Q-ensemble for offline RL: Don't scale the ensemble, scale the batch size. arXiv preprint arXiv:2211.11092","author":"Nikulin","year":"2022","unstructured":"Nikulin A, Kurenkov V, Tarasov D, et al. Q-ensemble for offline RL: Don't scale the ensemble, scale the batch size. arXiv preprint arXiv:2211.11092, 2022"},{"key":"e_1_3_3_1_11_2","volume-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","author":"M. Abadi","year":"2016","unstructured":"M. Abadi et al., \u201cTensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems.\u201d arXiv, 2016."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.18178\/joig.8.1.15-20"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.18178\/joig.12.1.16-22"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2894587"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2217971"}],"event":{"name":"MLMI 2024: 2024 The 7th International Conference on Machine Learning and Machine Intelligence (MLMI)","acronym":"MLMI 2024","location":"Osaka Japan"},"container-title":["Proceedings of the 2024 7th International Conference on Machine Learning and Machine Intelligence (MLMI)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696271.3696284","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696271.3696284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:00Z","timestamp":1750291440000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696271.3696284"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,2]]},"references-count":15,"alternative-id":["10.1145\/3696271.3696284","10.1145\/3696271"],"URL":"https:\/\/doi.org\/10.1145\/3696271.3696284","relation":{},"subject":[],"published":{"date-parts":[[2024,8,2]]},"assertion":[{"value":"2024-12-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}