{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:04:33Z","timestamp":1780675473298,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","funder":[{"name":"EPSRC","award":["EP\/Y016289\/1"],"award-info":[{"award-number":["EP\/Y016289\/1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792352","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:34Z","timestamp":1775771674000},"page":"5368-5379","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["HALO: Hierarchical Reinforcement Learning for Large-Scale Adaptive Traffic Signal Control"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1482-3240","authenticated-orcid":false,"given":"Yaqiao","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Exeter, Exeter, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1159-090X","authenticated-orcid":false,"given":"Hongkai","family":"Wen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Warwick, Coventry, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1395-7314","authenticated-orcid":false,"given":"Geyong","family":"Min","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Exeter, Exeter, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7346-9024","authenticated-orcid":false,"given":"Man","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Exeter, Exeter, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"OpenAI Pieter Abbeel, and Wojciech Zaremba","author":"Andrychowicz Marcin","year":"2017","unstructured":"Marcin Andrychowicz, Filip Wolski, Alex Ray, Jonas Schneider, Rachel Fong, Peter Welinder, Bob McGrew, Josh Tobin, OpenAI Pieter Abbeel, and Wojciech Zaremba. 2017. Hindsight experience replay. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.09.020"},{"key":"e_1_3_2_1_3_1","volume-title":"Learning an interpretable traffic signal control policy. arXiv preprint arXiv:1912.11023","author":"Ault James","year":"2019","unstructured":"James Ault, Josiah P Hanna, and Guni Sharon. 2019. Learning an interpretable traffic signal control policy. arXiv preprint arXiv:1912.11023 (2019)."},{"key":"e_1_3_2_1_4_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_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039557"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27758"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383645"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3376745"},{"key":"e_1_3_2_1_11_1","volume-title":"Meta Learning Shared Hierarchies. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SyX0IeWAW","author":"Frans Kevin","year":"2018","unstructured":"Kevin Frans, Jonathan Ho, Xi Chen, Pieter Abbeel, and John Schulman. 2018. Meta Learning Shared Hierarchies. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SyX0IeWAW"},{"key":"e_1_3_2_1_12_1","volume-title":"Using a deep reinforcement learning agent for traffic signal control. arXiv preprint arXiv:1611.01142","author":"Genders Wade","year":"2016","unstructured":"Wade Genders and Saiedeh Razavi. 2016. Using a deep reinforcement learning agent for traffic signal control. arXiv preprint arXiv:1611.01142 (2016)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.04.008"},{"key":"e_1_3_2_1_14_1","first-page":"21107","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Gu Yin","year":"2024","unstructured":"Yin Gu, Kai Zhang, Qi Liu, Weibo Gao, Longfei Li, and Jun Zhou. 2024. \u03c0-light: Programmatic interpretable reinforcement learning for resource-limited traffic signal control. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 21107-21115."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3377106"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. 94-102","author":"Jiang Haoyuan","year":"2024","unstructured":"Haoyuan Jiang, Ziyue Li, Hua Wei, Xuantang Xiong, Jingqing Ruan, Jiaming Lu, Hangyu Mao, and Rui Zhao. 2024b. X-Light: Cross-City Traffic Signal Control Using Transformer on Transformer as Meta Multi-Agent Reinforcement Learner. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. 94-102. https:\/\/www.ijcai.org\/proceedings\/2024\/11"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3141\/2421-15"},{"key":"e_1_3_2_1_18_1","first-page":"128","article-title":"Recent Development and Applications of SUMO - Simulation of Urban Mobility","volume":"5","author":"Krajzewicz Daniel","year":"2012","unstructured":"Daniel Krajzewicz, Jakob Erdmann, Michael Behrisch, and Laura Bieker. 2012. Recent Development and Applications of SUMO - Simulation of Urban Mobility. International Journal On Advances in Systems and Measurements, Vol. 5, 3&4 (2012), 128-138.","journal-title":"International Journal On Advances in Systems and Measurements"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/672"},{"key":"e_1_3_2_1_20_1","first-page":"199","article-title":"GPLight","author":"Liu Yilin","year":"2023","unstructured":"Yilin Liu, Guiyang Luo, Quan Yuan, Jinglin Li, Lei Jin, Bo Chen, and Rui Pan. 2023. GPLight: Grouped Multi-agent Reinforcement Learning for Large-scale Traffic Signal Control. In IJCAI. 199-207.","journal-title":"In IJCAI."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557640"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/251"},{"key":"e_1_3_2_1_23_1","volume-title":"Honglak Lee, and Sergey Levine.","author":"Nachum Ofir","year":"2018","unstructured":"Ofir Nachum, Shixiang Shane Gu, Honglak Lee, and Sergey Levine. 2018. Data-efficient hierarchical reinforcement learning. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_24_1","volume-title":"Natural actor-critic for road traffic optimisation. Advances in neural information processing systems","author":"Richter Silvia","year":"2006","unstructured":"Silvia Richter, Douglas Aberdeen, and Jin Yu. 2006. Natural actor-critic for road traffic optimisation. Advances in neural information processing systems, Vol. 19 (2006)."},{"key":"e_1_3_2_1_25_1","unstructured":"Roger P Roess Elena S Prassas and William R McShane. 2004. Traffic engineering. Pearson\/Prentice Hall."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671998"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-VT.1980.23833"},{"key":"e_1_3_2_1_28_1","volume-title":"Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial intelligence","author":"Sutton Richard S","year":"1999","unstructured":"Richard S Sutton, Doina Precup, and Satinder Singh. 1999. Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial intelligence, Vol. 112, 1-2 (1999), 181-211."},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 3540-3549","author":"Vezhnevets Alexander Sasha","year":"2017","unstructured":"Alexander Sasha Vezhnevets, Simon Osindero, Tom Schaul, Nicolas Heess, Max Jaderberg, David Silver, and Koray Kavukcuoglu. 2017. Feudal networks for hierarchical reinforcement learning. In International conference on machine learning. PMLR, 3540-3549."},{"key":"e_1_3_2_1_30_1","volume-title":"Adaptive Traffic Signal Control for large-scale scenario with Cooperative Group-based Multi-agent reinforcement learning. Transportation research part C: emerging technologies","author":"Wang Tong","year":"2021","unstructured":"Tong Wang, Jiahua Cao, and Azhar Hussain. 2021. Adaptive Traffic Signal Control for large-scale scenario with Cooperative Group-based Multi-agent reinforcement learning. Transportation research part C: emerging technologies, Vol. 125 (2021), 103046."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16147"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.03.087"},{"key":"e_1_3_2_1_34_1","first-page":"847","article-title":"Fedlight: Federated reinforcement learning for autonomous multi-intersection traffic signal control. In 2021 58th ACM\/IEEE design automation conference (DAC)","author":"Ye Yutong","year":"2021","unstructured":"Yutong Ye, Wupan Zhao, Tongquan Wei, Shiyan Hu, and Mingsong Chen. 2021. Fedlight: Federated reinforcement learning for autonomous multi-intersection traffic signal control. In 2021 58th ACM\/IEEE design automation conference (DAC). IEEE, 847-852.","journal-title":"IEEE"},{"key":"e_1_3_2_1_35_1","volume-title":"The surprising effectiveness of ppo in cooperative multi-agent games. Advances in neural information processing systems","author":"Yu Chao","year":"2022","unstructured":"Chao Yu, Akash Velu, Eugene Vinitsky, Jiaxuan Gao, Yu Wang, Alexandre Bayen, and Yi Wu. 2022. The surprising effectiveness of ppo in cooperative multi-agent games. Advances in neural information processing systems, Vol. 35 (2022), 24611-24624."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9921819"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411859"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3232711"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:36:44Z","timestamp":1780673804000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792352"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":39,"alternative-id":["10.1145\/3774904.3792352","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792352","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}