{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T13:05:37Z","timestamp":1785503137526,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","funder":[{"name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","award":["JYB2025XDXM910"],"award-info":[{"award-number":["JYB2025XDXM910"]}]},{"name":"National Natural Science Foundation of China","award":["42595590"],"award-info":[{"award-number":["42595590"]}]},{"name":"National Natural Science Foundation of China","award":["42595593"],"award-info":[{"award-number":["42595593"]}]},{"name":"Talent Scientific Fund of Lanzhou University","award":["561120208"],"award-info":[{"award-number":["561120208"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780308","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"704-713","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CFLight: Enhancing Safety with Traffic Signal Control through Counterfactual Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2522-8426","authenticated-orcid":false,"given":"Mingyuan","family":"Li","sequence":"first","affiliation":[{"name":"Lanzhou University, Lan Zhou, China and Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2230-3363","authenticated-orcid":false,"given":"Chunyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6613-7042","authenticated-orcid":false,"given":"Zhuojun","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4823-6011","authenticated-orcid":false,"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6111-1607","authenticated-orcid":false,"given":"Guangsheng","family":"Yu","sequence":"additional","affiliation":[{"name":"Independent Researcher, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5790-4682","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"Griffith University, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9403-7140","authenticated-orcid":false,"given":"Jun","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Wollongong, Wollongong, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0655-0479","authenticated-orcid":false,"given":"Qiang","family":"Wu","sequence":"additional","affiliation":[{"name":"Lanzhou University, Lan Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML).","author":"Achiam Joshua","year":"2017","unstructured":"Joshua Achiam, David Held, Aviv Tamar, and Pieter Abbeel. 2017. Constrained policy optimization. In Proceedings of the International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_2_2_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_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"e_1_3_2_2_4_1","volume-title":"Advances in applied self-organizing systems","author":"Cools Seung-Bae","unstructured":"Seung-Bae Cools, Carlos Gershenson, and Bart D'Hooghe. 2013. Self-organizing traffic lights: A realistic simulation. In Advances in applied self-organizing systems. Springer, 45-55."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26729"},{"key":"e_1_3_2_2_6_1","volume-title":"https:\/\/highways.dot.gov\/safety\/intersection-safety\/about Accessed on","author":"Intersection Safety FHWA.","year":"2023","unstructured":"FHWA. 2023. Intersection Safety. https:\/\/highways.dot.gov\/safety\/intersection-safety\/about Accessed on: August 1, 2023."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2020.105655"},{"key":"e_1_3_2_2_8_1","unstructured":"Shangding Gu Long Yang Yali Du Guang Chen Florian Walter Jun Wang Yaodong Yang and Alois Knoll. 2023. A Review of Safe Reinforcement Learning: Methods Theory and Applications. arXiv:2205.10330 [cs.AI]"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917268"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsr.2019.12.010"},{"key":"e_1_3_2_2_11_1","first-page":"216","volume-title":"Perth","author":"Jaiswal Ayush","year":"2019","unstructured":"Ayush Jaiswal, Wael AbdAlmageed, Yue Wu, and Premkumar Natarajan. 2019. Bidirectional conditional generative adversarial networks. In Computer Vision-ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2-6, 2018, Revised Selected Papers, Part III 14. Springer, 216-232."},{"key":"e_1_3_2_2_12_1","volume-title":"An intelligent control system for traffic lights with simulation-based evaluation. Control engineering practice","author":"Jin Junchen","year":"2017","unstructured":"Junchen Jin, Xiaoliang Ma, and Iisakki Kosonen. 2017. An intelligent control system for traffic lights with simulation-based evaluation. Control engineering practice, Vol. 58 (2017), 24-33."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.01.007"},{"key":"e_1_3_2_2_14_1","unstructured":"P Koonce. 2008. Traffic signal timing manual. technical report. Kittelson & Associates Inc. Portland OR USA Tech. Rep. FHWA-HOP-08-024 (2008)."},{"key":"e_1_3_2_2_15_1","volume-title":"International journal on advances in systems and measurements","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)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467420"},{"key":"e_1_3_2_2_17_1","volume-title":"FuzzyLight: A Robust Two-Stage Fuzzy Approach for Traffic Signal Control Works in Real Cities. arXiv preprint arXiv:2501.15820","author":"Li Mingyuan","year":"2025","unstructured":"Mingyuan Li, Jiahao Wang, Bo Du, Jun Shen, and Qiang Wu. 2025. FuzzyLight: A Robust Two-Stage Fuzzy Approach for Traffic Signal Control Works in Real Cities. arXiv preprint arXiv:2501.15820 (2025)."},{"key":"e_1_3_2_2_18_1","volume-title":"Forty-second International Conference on Machine Learning.","author":"Li Mingyuan","unstructured":"Mingyuan Li, Jiahao Wang, Guangsheng Yu, Xu Wang, Qianrun Chen, Wei Ni, Lixiang Li, and Haipeng Peng. [n.d.]. RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control. In Forty-second International Conference on Machine Learning."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890726"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-023-09615-8"},{"key":"e_1_3_2_2_21_1","volume-title":"Kun Zhang, and Bernhard Sch\u00f6lkopf.","author":"Lu Chaochao","year":"2020","unstructured":"Chaochao Lu, Biwei Huang, Ke Wang, Jos\u00e9 Miguel Hern\u00e1ndez-Lobato, Kun Zhang, and Bernhard Sch\u00f6lkopf. 2020. Sample-efficient reinforcement learning via counterfactual-based data augmentation. arXiv preprint arXiv:2012.09092 (2020)."},{"key":"e_1_3_2_2_22_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_23_1","unstructured":"Thomas Mesnard Th\u00e9ophane Weber Fabio Viola Shantanu Thakoor Alaa Saade Anna Harutyunyan Will Dabney Tom Stepleton Nicolas Heess Arthur Guez et al. 2020. Counterfactual credit assignment in model-free reinforcement learning. arXiv preprint arXiv:2011.09464 (2020)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26113"},{"key":"e_1_3_2_2_25_1","unstructured":"World Health Organization et al. 2018. Global status report on road safety 2018: Summary (No. WHO\/NMH\/NVI\/18.20). World Health Organization (2018)."},{"key":"e_1_3_2_2_26_1","first-page":"4079","article-title":"Attendlight: Universal attention-based reinforcement learning model for traffic signal control","volume":"33","author":"Oroojlooy Afshin","year":"2020","unstructured":"Afshin Oroojlooy, Mohammadreza Nazari, Davood Hajinezhad, and Jorge Silva. 2020. Attendlight: Universal attention-based reinforcement learning model for traffic signal control. Advances in Neural Information Processing Systems, Vol. 33 (2020), 4079-4090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_27_1","unstructured":"Judea Pearl. 2009. Causality. Cambridge university press."},{"key":"e_1_3_2_2_28_1","volume-title":"INRIX (December","author":"Pishue Bob","year":"2021","unstructured":"Bob Pishue. 2021. 2021 inrix global traffic scorecard. In INRIX (December 2021)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0197-y"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.03.065"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0037350"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6047"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of Learning, Inference and Control of Multi-Agent Systems (at NIPS 2016)","author":"der Pol Elise Van","year":"2016","unstructured":"Elise Van der Pol and Frans A Oliehoek. 2016. Coordinated deep reinforcement learners for traffic light control. Proceedings of Learning, Inference and Control of Multi-Agent Systems (at NIPS 2016) (2016)."},{"key":"e_1_3_2_2_34_1","unstructured":"Sahil Verma Varich Boonsanong Minh Hoang Keegan E. Hines John P. Dickerson and Chirag Shah. 2022. Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review. arXiv:2010.10596 [cs.LG]"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599530"},{"key":"e_1_3_2_2_37_1","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Xu Da","year":"2020","unstructured":"Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, and Kannan Achan. 2020. Adversarial Counterfactual Learning and Evaluation for Recommender System. Advances in Neural Information Processing Systems, Vol. 33."},{"key":"e_1_3_2_2_38_1","first-page":"26645","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Zhang Liang","year":"2022","unstructured":"Liang Zhang, Qiang Wu, Jun Shen, Linyuan L\u00fc, Bo Du, and Jianqing Wu. 2022. Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control. In Proceedings of the 39th International Conference on Machine Learning, Vol. 162. 26645-26654."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:21:21Z","timestamp":1785500481000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780308"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":38,"alternative-id":["10.1145\/3770854.3780308","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780308","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}