{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T22:38:10Z","timestamp":1781649490941,"version":"3.54.5"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T00:00:00Z","timestamp":1701129600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T00:00:00Z","timestamp":1701129600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2153311"],"award-info":[{"award-number":["2153311"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s10994-023-06412-y","type":"journal-article","created":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T17:02:04Z","timestamp":1701190924000},"page":"5235-5271","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Libsignal: an open library for traffic signal control"],"prefix":"10.1007","volume":"113","author":[{"given":"Hao","family":"Mei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoliang","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longchao","family":"Da","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3735-1635","authenticated-orcid":false,"given":"Hua","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,28]]},"reference":[{"key":"6412_CR1","unstructured":"Ault, J., & Sharon, G. (2021). Reinforcement learning benchmarks for traffic signal control. In 35th Conference on neural information processing systems datasets and benchmarks track (Round 1)."},{"key":"6412_CR2","unstructured":"Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., & Zaremba, W. (2016). OpenAI Gym"},{"issue":"10","key":"6412_CR3","doi-asserted-by":"publisher","first-page":"17899","DOI":"10.1109\/TITS.2022.3159714","volume":"23","author":"M Cao","year":"2022","unstructured":"Cao, M., Li, V. O., & Shuai, Q. (2022). A gain with no pain: Exploring intelligent traffic signal control for emergency vehicles. IEEE Transactions on Intelligent Transportation Systems, 23(10), 17899\u201317909.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"6412_CR4","doi-asserted-by":"crossref","unstructured":"Chen, C., Wei, H., Xu, N., Zheng, G., Yang, M., Xiong, Y., Xu, K., & Li, Z. (2020). Toward a thousand lights: Decentralized deep reinforcement learning for large-scale traffic signal control. In Proceedings of the AAAI conference on artificial intelligence (vol. 34, pp. 3414\u20133421).","DOI":"10.1609\/aaai.v34i04.5744"},{"issue":"3","key":"6412_CR5","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1109\/TITS.2019.2901791","volume":"21","author":"T Chu","year":"2019","unstructured":"Chu, T., Wang, J., Codec\u00e0, L., & Li, Z. (2019). Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Transactions on Intelligent Transportation Systems, 21(3), 1086\u20131095.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"7","key":"6412_CR6","doi-asserted-by":"publisher","first-page":"7496","DOI":"10.1109\/TITS.2021.3070835","volume":"23","author":"F-X Devailly","year":"2021","unstructured":"Devailly, F.-X., Larocque, D., & Charlin, L. (2021). Ig-rl: Inductive graph reinforcement learning for massive-scale traffic signal control. IEEE Transactions on Intelligent Transportation Systems, 23(7), 7496\u20137507.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"6412_CR7","doi-asserted-by":"publisher","first-page":"134","DOI":"10.29007\/dkzb","volume":"2","author":"N Kheterpal","year":"2018","unstructured":"Kheterpal, N., Parvate, K., Wu, C., Kreidieh, A., Vinitsky, E., & Bayen, A. (2018). Flow: Deep reinforcement learning for control in sumo. EPiC Series in Engineering, 2, 134\u2013151.","journal-title":"EPiC Series in Engineering"},{"key":"6412_CR8","doi-asserted-by":"crossref","unstructured":"Lopez, P.A., Behrisch, M., Bieker-Walz, L., Erdmann, J., Fl\u00f6tter\u00f6d, Y.-P., Hilbrich, R., L\u00fccken, L., Rummel, J., Wagner, P., & Wie\u00dfner, E. (2018). Microscopic traffic simulation using sumo. In 2018 21st international conference on intelligent transportation systems (ITSC) (pp. 2575\u20132582). IEEE.","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"6412_CR9","unstructured":"Ma, J., & Wu, F. (2020). Feudal multi-agent deep reinforcement learning for traffic signal control. In Proceedings of the 19th international conference on autonomous agents and multiagent systems (AAMAS) (pp. 816\u2013824)."},{"key":"6412_CR10","first-page":"4079","volume":"33","author":"A Oroojlooy","year":"2020","unstructured":"Oroojlooy, A., Nazari, M., Hajinezhad, D., & Silva, J. (2020). Attendlight: Universal attention-based reinforcement learning model for traffic signal control. Advances in Neural Information Processing Systems, 33, 4079\u20134090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6412_CR11","doi-asserted-by":"crossref","unstructured":"Peng, X.B., Andrychowicz, M., Zaremba, W., & Abbeel, P. (2018). Sim-to-real transfer of robotic control with dynamics randomization. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 3803\u20133810). IEEE.","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"6412_CR12","doi-asserted-by":"crossref","unstructured":"Raeis, M., & Leon-Garcia, A. (2021). A deep reinforcement learning approach for fair traffic signal control. In 2021 IEEE international intelligent transportation systems conference (ITSC) (pp. 2512\u20132518). IEEE.","DOI":"10.1109\/ITSC48978.2021.9564847"},{"key":"6412_CR13","doi-asserted-by":"publisher","first-page":"208016","DOI":"10.1109\/ACCESS.2020.3034141","volume":"8","author":"F Rasheed","year":"2020","unstructured":"Rasheed, F., Yau, K.-L.A., Noor, R. M., Wu, C., & Low, Y.-C. (2020). Deep reinforcement learning for traffic signal control: A review. IEEE Access, 8, 208016\u2013208044.","journal-title":"IEEE Access"},{"key":"6412_CR14","unstructured":"Reinforcement Learning for Traffic Signal Control. https:\/\/traffic-signal-control.github.io\/. Accessed 22 May 2022."},{"key":"6412_CR15","doi-asserted-by":"crossref","unstructured":"Rizzo, S.G., Vantini, G., & Chawla, S. (2019). Reinforcement learning with explainability for traffic signal control. In 2019 IEEE intelligent transportation systems conference (ITSC) (pp. 3567\u20133572). IEEE.","DOI":"10.1109\/ITSC.2019.8917519"},{"key":"6412_CR16","doi-asserted-by":"crossref","unstructured":"Rizzo, S.G., Vantini, G., & Chawla, S. (2019). Time critic policy gradient methods for traffic signal control in complex and congested scenarios. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 1654\u20131664).","DOI":"10.1145\/3292500.3330988"},{"key":"6412_CR17","first-page":"15032","volume":"34","author":"J Terry","year":"2021","unstructured":"Terry, J., Black, B., Grammel, N., Jayakumar, M., Hari, A., Sullivan, R., Santos, L. S., Dieffendahl, C., Horsch, C., Perez-Vicente, R., et al. (2021). Pettingzoo: Gym for multi-agent reinforcement learning. Advances in Neural Information Processing Systems, 34, 15032\u201315043.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6412_CR18","doi-asserted-by":"publisher","unstructured":"Tran, T.V., Doan, T.-N., & Sartipi, M. (2021). Tslib: A unified traffic signal control framework using deep reinforcement learning and benchmarking. In 2021 IEEE international conference on big data (Big Data) (pp. 1739\u20131747). https:\/\/doi.org\/10.1109\/BigData52589.2021.9671993","DOI":"10.1109\/BigData52589.2021.9671993"},{"issue":"7","key":"6412_CR19","doi-asserted-by":"publisher","first-page":"6774","DOI":"10.1109\/TITS.2021.3062072","volume":"23","author":"M Wang","year":"2021","unstructured":"Wang, M., Wu, L., Li, J., & He, L. (2021). Traffic signal control with reinforcement learning based on region-aware cooperative strategy. IEEE Transactions on Intelligent Transportation Systems, 23(7), 6774\u20136785.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"6412_CR20","doi-asserted-by":"crossref","unstructured":"Wei, H., Chen, C., Zheng, G., Wu, K., Gayah, V., Xu, K., & Li, Z. (2019). Presslight: Learning max pressure control to coordinate traffic signals in arterial network. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 1290\u201312980).","DOI":"10.1145\/3292500.3330949"},{"key":"6412_CR21","doi-asserted-by":"crossref","unstructured":"Wei, H., Xu, N., Zhang, H., Zheng, G., Zang, X., Chen, C., Zhang, W., Zhu, Y., Xu, K., & Li, Z. (2019). Colight: Learning network-level cooperation for traffic signal control. In Proceedings of the 28th ACM international conference on information and knowledge management (pp. 1913\u20131922)","DOI":"10.1145\/3357384.3357902"},{"key":"6412_CR22","unstructured":"Wei, H., Zheng, G., Gayah, V., & Li, Z. (2019). A survey on traffic signal control methods. arXiv preprint arXiv:1904.08117"},{"key":"6412_CR23","doi-asserted-by":"crossref","unstructured":"Wei, H., Zheng, G., Yao, H., & Li, Z. (2018). Intellilight: A reinforcement learning approach for intelligent traffic light control. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 2496\u20132505).","DOI":"10.1145\/3219819.3220096"},{"issue":"2","key":"6412_CR24","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1145\/3447556.3447565","volume":"22","author":"H Wei","year":"2021","unstructured":"Wei, H., Zheng, G., Gayah, V., & Li, Z. (2021). Recent advances in reinforcement learning for traffic signal control: A survey of models and evaluation. ACM SIGKDD Explorations Newsletter, 22(2), 12\u201318.","journal-title":"ACM SIGKDD Explorations Newsletter"},{"key":"6412_CR25","doi-asserted-by":"crossref","unstructured":"Wu, L., Wang, M., Wu, D., & Wu, J. (2021). Dynstgat: Dynamic spatial-temporal graph attention network for traffic signal control. In Proceedings of the 30th ACM international conference on information & knowledge management (pp. 2150\u20132159).","DOI":"10.1145\/3459637.3482254"},{"key":"6412_CR26","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Zheng, G., Xu, K., & Li, Z. (2019). Learning traffic signal control from demonstrations. In Proceedings of the 28th ACM international conference on information and knowledge management (pp. 2289\u20132292).","DOI":"10.1145\/3357384.3358079"},{"key":"6412_CR27","doi-asserted-by":"crossref","unstructured":"Xu, B., Wang, Y., Wang, Z., Jia, H., & Lu, Z. (2021). Hierarchically and cooperatively learning traffic signal control. In Proceedings of the AAAI conference on artificial intelligence (vol. 35, pp. 669\u2013677).","DOI":"10.1609\/aaai.v35i1.16147"},{"issue":"3","key":"6412_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3068287","volume":"50","author":"K-LA Yau","year":"2017","unstructured":"Yau, K.-L.A., Qadir, J., Khoo, H. L., Ling, M. H., & Komisarczuk, P. (2017). A survey on reinforcement learning models and algorithms for traffic signal control. ACM Computing Surveys (CSUR), 50(3), 1\u201338.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"6412_CR29","doi-asserted-by":"crossref","unstructured":"Yen, C.-C., Ghosal, D., Zhang, M., & Chuah, C.-N. (2020). A deep on-policy learning agent for traffic signal control of multiple intersections. In 2020 IEEE 23rd international conference on intelligent transportation systems (ITSC) (pp. 1\u20136). IEEE.","DOI":"10.1109\/ITSC45102.2020.9294471"},{"key":"6412_CR30","doi-asserted-by":"crossref","unstructured":"Zang, X., Yao, H., Zheng, G., Xu, N., Xu, K., & Li, Z. (2020). Metalight: Value-based meta-reinforcement learning for traffic signal control. In Proceedings of the AAAI conference on artificial intelligence (vol. 34, pp. 1153\u20131160).","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"6412_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, H., Feng, S., Liu, C., Ding, Y., Zhu, Y., Zhou, Z., Zhang, W., Yu, Y., Jin, H., & Li, Z. (2019). Cityflow: A multi-agent reinforcement learning environment for large scale city traffic scenario. In The world wide web conference (pp. 3620\u20133624).","DOI":"10.1145\/3308558.3314139"},{"key":"6412_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, H., Liu, C., Zhang, W., Zheng, G., & Yu, Y. (2020). Generalight: Improving environment generalization of traffic signal control via meta reinforcement learning. In Proceedings of the 29th ACM international conference on information & knowledge management (pp. 1783\u20131792).","DOI":"10.1145\/3340531.3411859"},{"key":"6412_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, W., Queralta, J.P., & Westerlund, T. (2020). Sim-to-real transfer in deep reinforcement learning for robotics: A survey. In 2020 IEEE symposium series on computational intelligence (SSCI) (pp. 737\u2013744). IEEE.","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"6412_CR34","doi-asserted-by":"crossref","unstructured":"Zheng, G., Xiong, Y., Zang, X., Feng, J., Wei, H., Zhang, H., Li, Y., Xu, K., & Li, Z. (2019). Learning phase competition for traffic signal control. In Proceedings of the 28th ACM international conference on information and knowledge management (pp. 1963\u20131972).","DOI":"10.1145\/3357384.3357900"},{"key":"6412_CR35","doi-asserted-by":"publisher","unstructured":"Zheng, G., Zang, X., Xu, N., Wei, H., Yu, Z., Gayah, V., Xu, K., & Li, Z. (2019). Diagnosing reinforcement learning for traffic signal control. arXiv . https:\/\/doi.org\/10.48550\/ARXIV.1905.04716. https:\/\/arxiv.org\/abs\/1905.04716","DOI":"10.48550\/ARXIV.1905.04716"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06412-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-023-06412-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06412-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:03:18Z","timestamp":1764266598000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-023-06412-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,28]]},"references-count":35,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["6412"],"URL":"https:\/\/doi.org\/10.1007\/s10994-023-06412-y","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,28]]},"assertion":[{"value":"9 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Hao Mei agrees to participate. Xiaoliang Lei agrees to participate. Longchao Da agrees to participate. Bin Shi agrees to participate. Hua Wei agrees to participate.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Hao Mei agrees that his individual data and image are published. Xiaoliang Lei agrees that her individual data and image are published. Longchao Da agrees that his individual data and image are published. Bin Shi agrees that his individual data and image are published. Hua Wei agrees that his individual data and image are published.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}