{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T14:49:38Z","timestamp":1783954178924,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92370204"],"award-info":[{"award-number":["92370204"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2023YFF0725001"],"award-info":[{"award-number":["2023YFF0725001"]}]},{"name":"Guangzhou-HKUST(GZ) Joint Funding Program","award":["2023A03J0008"],"award-info":[{"award-number":["2023A03J0008"]}]},{"name":"Education Bureau of Guangzhou Municipality"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671927","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:54:55Z","timestamp":1724561695000},"page":"2765-2774","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["CrossLight: Offline-to-Online Reinforcement Learning for Cross-City Traffic Signal Control"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2205-4566","authenticated-orcid":false,"given":"Qian","family":"Sun","sequence":"first","affiliation":[{"name":"The Division of Emerging Interdisciplinary Areas, Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6557-123X","authenticated-orcid":false,"given":"Rui","family":"Zha","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0894-9651","authenticated-orcid":false,"given":"Le","family":"Zhang","sequence":"additional","affiliation":[{"name":"Baidu Research, Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2677-7021","authenticated-orcid":false,"given":"Jingbo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Baidu Research, Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2620-3589","authenticated-orcid":false,"given":"Yu","family":"Mei","sequence":"additional","affiliation":[{"name":"Department of Intelligent Transportation System, Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1341-308X","authenticated-orcid":false,"given":"Zhiling","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Intelligent Driving Group Business Management, Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6016-6465","authenticated-orcid":false,"given":"Hui","family":"Xiong","sequence":"additional","affiliation":[{"name":"Thrust of Artificial Intelligence, Hong Kong University of Science and Technology (Guangzhou) & Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).","author":"Ault James","year":"2021","unstructured":"James Ault and Guni Sharon. 2021. Reinforcement learning benchmarks for traffic signal control. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3618475"},{"key":"e_1_3_2_2_3_1","unstructured":"Micah Carroll Orr Paradise Jessy Lin Raluca Georgescu Mingfei Sun David Bignell Stephanie Milani Katja Hofmann Matthew Hausknecht Anca Dragan et al. 2022. Uni [mask]: Unified inference in sequential decision problems. Advances in neural information processing systems 35 (2022) 35365--35378."},{"key":"e_1_3_2_2_4_1","volume-title":"Boltzmann exploration done right. Advances in neural information processing systems 30","author":"Cesa-Bianchi Nicol\u00f2","year":"2017","unstructured":"Nicol\u00f2 Cesa-Bianchi, Claudio Gentile, G\u00e1bor Lugosi, and Gergely Neu. 2017. Boltzmann exploration done right. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"e_1_3_2_2_6_1","volume-title":"Decision transformer: Reinforcement learning via sequence modeling. Advances in neural information processing systems 34","author":"Chen Lili","year":"2021","unstructured":"Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Misha Laskin, Pieter Abbeel, Aravind Srinivas, and Igor Mordatch. 2021. Decision transformer: Reinforcement learning via sequence modeling. Advances in neural information processing systems 34 (2021), 15084--15097."},{"key":"e_1_3_2_2_7_1","volume-title":"Self-organizing traffic lights: A realistic simulation. Advances in applied self-organizing systems","author":"Cools Seung-Bae","year":"2013","unstructured":"Seung-Bae Cools, Carlos Gershenson, and Bart D'Hooghe. 2013. Self-organizing traffic lights: A realistic simulation. Advances in applied self-organizing systems (2013), 45--55."},{"key":"e_1_3_2_2_8_1","volume-title":"International conference on machine learning. PMLR, 1126--1135","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta- learning for fast adaptation of deep networks. In International conference on machine learning. PMLR, 1126--1135."},{"key":"e_1_3_2_2_9_1","volume-title":"Traffic Signal Control Using Lightweight Transformers: An Offline-to-Online RL Approach. arXiv preprint arXiv:2312.07795","author":"Huang Xingshuai","year":"2023","unstructured":"Xingshuai Huang, Di Wu, and Benoit Boulet. 2023. Traffic Signal Control Using Lightweight Transformers: An Offline-to-Online RL Approach. arXiv preprint arXiv:2312.07795 (2023)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539250"},{"key":"e_1_3_2_2_11_1","volume-title":"Offline reinforcement learning with implicit q-learning. arXiv preprint arXiv:2110.06169","author":"Kostrikov Ilya","year":"2021","unstructured":"Ilya Kostrikov, Ashvin Nair, and Sergey Levine. 2021. Offline reinforcement learning with implicit q-learning. arXiv preprint arXiv:2110.06169 (2021)."},{"key":"e_1_3_2_2_12_1","volume-title":"Reinforcement learning: State-of-the-art","author":"Lange Sascha","unstructured":"Sascha Lange, Thomas Gabel, and Martin Riedmiller. 2012. Batch reinforcement learning. In Reinforcement learning: State-of-the-art. Springer, 45--73."},{"key":"e_1_3_2_2_13_1","volume-title":"Conference on Robot Learning. PMLR, 1702--1712","author":"Lee Seunghyun","year":"2022","unstructured":"Seunghyun Lee, Younggyo Seo, Kimin Lee, Pieter Abbeel, and Jinwoo Shin. 2022. Offline-to-online reinforcement learning via balanced replay and pessimistic q-ensemble. In Conference on Robot Learning. PMLR, 1702--1712."},{"key":"e_1_3_2_2_14_1","volume-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643","author":"Levine Sergey","year":"2020","unstructured":"Sergey Levine, Aviral Kumar, George Tucker, and Justin Fu. 2020. Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)."},{"key":"e_1_3_2_2_15_1","volume-title":"A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning. arXiv preprint arXiv:2311.15920","author":"Li Jianxiong","year":"2023","unstructured":"Jianxiong Li, Shichao Lin, Tianyu Shi, Chujie Tian, Yu Mei, Jian Song, Xianyuan Zhan, and Ruimin Li. 2023. A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning. arXiv preprint arXiv:2311.15920 (2023)."},{"key":"e_1_3_2_2_16_1","first-page":"12608","article-title":"Masked autoencoding for scalable and generalizable decision making","volume":"35","author":"Liu Fangchen","year":"2022","unstructured":"Fangchen Liu, Hao Liu, Aditya Grover, and Pieter Abbeel. 2022. Masked autoencoding for scalable and generalizable decision making. Advances in Neural Information Processing Systems 35 (2022), 12608--12618.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614829"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539281"},{"key":"e_1_3_2_2_19_1","volume-title":"Trade-offs and Practical Solutions. arXiv preprint arXiv:2303.17396","author":"Luo Yicheng","year":"2023","unstructured":"Yicheng Luo, Jackie Kay, Edward Grefenstette, and Marc Peter Deisenroth. 2023. Finetuning from Offline Reinforcement Learning: Challenges, Trade-offs and Practical Solutions. arXiv preprint arXiv:2303.17396 (2023)."},{"key":"e_1_3_2_2_20_1","volume-title":"LibSignal: An Open Library for Traffic Signal Control. arXiv preprint arXiv:2211.10649","author":"Mei Hao","year":"2022","unstructured":"Hao Mei, Xiaoliang Lei, Longchao Da, Bin Shi, and Hua Wei. 2022. LibSignal: An Open Library for Traffic Signal Control. arXiv preprint arXiv:2211.10649 (2022)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599839"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2013.08.014"},{"key":"e_1_3_2_2_23_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","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. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3619878"},{"key":"e_1_3_2_2_25_1","volume-title":"Cross-city Transfer Learning for Deep Spatio-temporal Prediction. In IJCAI International Joint Conference on Artificial Intelligence.","author":"Wang Leye","year":"2019","unstructured":"Leye Wang, Xu Geng, Xiaojuan Ma, Feng Liu, and Qiang Yang. 2019. Cross-city Transfer Learning for Deep Spatio-temporal Prediction. In IJCAI International Joint Conference on Artificial Intelligence. 1893."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3033782"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447556.3447565"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-023-2689-5"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482254"},{"key":"e_1_3_2_2_33_1","volume-title":"Masked trajectory models for prediction, representation, and control. arXiv preprint arXiv:2305.02968","author":"Wu Philipp","year":"2023","unstructured":"Philipp Wu, Arjun Majumdar, Kevin Stone, Yixin Lin, Igor Mordatch, Pieter Abbeel, and Aravind Rajeswaran. 2023. Masked trajectory models for prediction, representation, and control. arXiv preprint arXiv:2305.02968 (2023)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599530"},{"key":"e_1_3_2_2_35_1","unstructured":"Huaxiu Yao Yiding Liu Ying Wei Xianfeng Tang and Zhenhui Li. 2019. Learning from multiple cities: A meta-learning approach for spatial-temporal prediction. In The world wide web conference. 2181--2191."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651158"},{"key":"e_1_3_2_2_38_1","volume-title":"Data Might be Enough: Bridge Real- World Traffic Signal Control Using Offline Reinforcement Learning. arXiv preprint arXiv:2303.10828","author":"Zhang Liang","year":"2023","unstructured":"Liang Zhang and Jianming Deng. 2023. Data Might be Enough: Bridge Real- World Traffic Signal Control Using Offline Reinforcement Learning. arXiv preprint arXiv:2303.10828 (2023)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40649-019-0069-y"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539416"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29633"},{"key":"e_1_3_2_2_42_1","volume-title":"Adaptive policy learning for offline-to-online reinforcement learning. arXiv preprint arXiv:2303.07693","author":"Zheng Han","year":"2023","unstructured":"Han Zheng, Xufang Luo, Pengfei Wei, Xuan Song, Dongsheng Li, and Jing Jiang. 2023. Adaptive policy learning for offline-to-online reinforcement learning. arXiv preprint arXiv:2303.07693 (2023)."},{"key":"e_1_3_2_2_43_1","volume-title":"international conference on machine learning. PMLR, 27042--27059","author":"Zheng Qinqing","year":"2022","unstructured":"Qinqing Zheng, Amy Zhang, and Aditya Grover. 2022. Online decision transformer. In international conference on machine learning. PMLR, 27042--27059."},{"key":"e_1_3_2_2_44_1","volume-title":"Metavim: Meta variationally intrinsic motivated reinforcement learning for decentralized traffic signal control","author":"Zhu Liwen","year":"2023","unstructured":"Liwen Zhu, Peixi Peng, Zongqing Lu, and Yonghong Tian. 2023. Metavim: Meta variationally intrinsic motivated reinforcement learning for decentralized traffic signal control. IEEE Transactions on Knowledge and Data Engineering (2023)."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671927","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:15Z","timestamp":1750291455000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671927"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":43,"alternative-id":["10.1145\/3637528.3671927","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671927","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}