{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T15:53:02Z","timestamp":1776441182183,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":67,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671998","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"2500-2511","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["CoSLight: Co-optimizing Collaborator Selection and Decision-making to Enhance Traffic Signal Control"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4857-9053","authenticated-orcid":false,"given":"Jingqing","family":"Ruan","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Science, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4983-9352","authenticated-orcid":false,"given":"Ziyue","family":"Li","sequence":"additional","affiliation":[{"name":"University of Cologne, EWI gGmbH, Cologne, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3735-1635","authenticated-orcid":false,"given":"Hua","family":"Wei","sequence":"additional","affiliation":[{"name":"Arizona State University, Arizona, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3768-865X","authenticated-orcid":false,"given":"Haoyuan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2327-3285","authenticated-orcid":false,"given":"Jiaming","family":"Lu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8824-1324","authenticated-orcid":false,"given":"Xuantang","family":"Xiong","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Science, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4499-7581","authenticated-orcid":false,"given":"Hangyu","family":"Mao","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5874-131X","authenticated-orcid":false,"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[{"name":"Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Learning an interpretable traffic signal control policy. arXiv preprint arXiv:1912.11023","author":"Ault J.","year":"2019","unstructured":"Ault, J., Hanna, J. P., and Sharon, G. Learning an interpretable traffic signal control policy. arXiv preprint arXiv:1912.11023 (2019)."},{"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 J.","year":"2021","unstructured":"Ault, J., and Sharon, G. Reinforcement learning benchmarks for traffic signal control. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1) (2021)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"e_1_3_2_2_4_1","first-page":"980","volume-title":"International Conference on Machine Learning","author":"B\u00f6hmer W.","year":"2020","unstructured":"B\u00f6hmer, W., Kurin, V., and Whiteson, S. Deep coordination graphs. In International Conference on Machine Learning (2020), PMLR, pp. 980--991."},{"key":"e_1_3_2_2_5_1","first-page":"195","volume-title":"TARK","volume":"96","author":"Boutilier C.","year":"1996","unstructured":"Boutilier, C. Planning, learning and coordination in multiagent decision processes. In TARK (1996), vol. 96, pp. 195--210."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27758"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383645"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3070835"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26729"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3376745"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"e_1_3_2_2_13_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Han X.","year":"2023","unstructured":"Han, X., Zhao, T., Liu, Y., Hu, X., and Shah, N. MLPInit: Embarrassingly simple GNN training acceleration with MLP initialization. In The Eleventh International Conference on Learning Representations (2023)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599359"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3377106"},{"key":"e_1_3_2_2_16_1","volume-title":"X-light: Cross-city traffic signal control using transformer on transformer as meta multi-agent reinforcement learner. arXiv preprint arXiv:2404.12090","author":"Jiang H.","year":"2024","unstructured":"Jiang, H., Li, Z., Wei, H., Xiong, X., Ruan, J., Lu, J., Mao, H., and Zhao, R. X-light: Cross-city traffic signal control using transformer on transformer as meta multi-agent reinforcement learner. arXiv preprint arXiv:2404.12090 (2024)."},{"key":"e_1_3_2_2_17_1","volume-title":"Graph convolutional reinforcement learning. arXiv preprint arXiv:1810.09202","author":"Jiang J.","year":"2018","unstructured":"Jiang, J., Dun, C., Huang, T., and Lu, Z. Graph convolutional reinforcement learning. arXiv preprint arXiv:1810.09202 (2018)."},{"key":"e_1_3_2_2_18_1","unstructured":"Jiang Q. Li J. Sun W. and Zheng B. Dynamic lane traffic signal control with group attention and multi-timescale reinforcement learning. IJCAI."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.3141\/2421-15"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87479-9_61"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI50451.2021.9659871"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20378"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/23"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557640"},{"key":"e_1_3_2_2_25_1","volume-title":"Dualight: Enhancing traffic signal control by leveraging scenario-specific and scenario-shared knowledge. arXiv preprint arXiv:2312.14532","author":"Lu J.","year":"2023","unstructured":"Lu, J., Ruan, J., Jiang, H., Li, Z.,Mao, H., and Zhao, R. Dualight: Enhancing traffic signal control by leveraging scenario-specific and scenario-shared knowledge. arXiv preprint arXiv:2312.14532 (2023)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/3398761.3398858"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6212"},{"key":"e_1_3_2_2_28_1","volume-title":"Transformer in transformer as backbone for deep reinforcement learning. arXiv preprint arXiv:2212.14538","author":"Mao H.","year":"2022","unstructured":"Mao, H., Zhao, R., Chen, H., Hao, J., Chen, Y., Li, D., Zhang, J., and Xiao, Z. Transformer in transformer as backbone for deep reinforcement learning. arXiv preprint arXiv:2212.14538 (2022)."},{"key":"e_1_3_2_2_29_1","volume-title":"Pdit: Interleaving perception and decision-making transformers for deep reinforcement learning. arXiv preprint arXiv:2312.15863","author":"Mao H.","year":"2023","unstructured":"Mao, H., Zhao, R., Li, Z., Xu, Z., Chen, H., Chen, Y., Zhang, B., Xiao, Z., Zhang, J., and Yin, J. Pdit: Interleaving perception and decision-making transformers for deep reinforcement learning. arXiv preprint arXiv:2312.15863 (2023)."},{"key":"e_1_3_2_2_30_1","volume-title":"Libsignal: An open library for traffic signal control. Machine Learning","author":"Mei H.","year":"2023","unstructured":"Mei, H., Lei, X., Da, L., Shi, B., and Wei, H. Libsignal: An open library for traffic signal control. Machine Learning (2023), 1--37."},{"key":"e_1_3_2_2_31_1","volume-title":"Reinforcement learning approaches for traffic signal control under missing data. arXiv preprint arXiv:2304.10722","author":"Mei H.","year":"2023","unstructured":"Mei, H., Li, J., Shi, B., and Wei, H. Reinforcement learning approaches for traffic signal control under missing data. arXiv preprint arXiv:2304.10722 (2023)."},{"key":"e_1_3_2_2_32_1","first-page":"4079","article-title":"Attendlight: Universal attention-based reinforcement learning model for traffic signal control","volume":"33","author":"Oroojlooy A.","year":"2020","unstructured":"Oroojlooy, A., Nazari, M., Hajinezhad, D., and Silva, J. Attendlight: Universal attention-based reinforcement learning model for traffic signal control. Advances in Neural Information Processing Systems 33 (2020), 4079--4090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_33_1","volume-title":"Traffic engineering","author":"Roess R. P.","year":"2004","unstructured":"Roess, R. P., Prassas, E. S., and McShane, W. R. Traffic engineering. 2004."},{"key":"e_1_3_2_2_34_1","volume-title":"Gcs: Graph-based coordination strategy for multi-agent reinforcement learning. arXiv preprint arXiv:2201.06257","author":"Ruan J.","year":"2022","unstructured":"Ruan, J., Du, Y., Xiong, X., Xing, D., Li, X., Meng, L., Zhang, H., Wang, J., and Xu, B. Gcs: Graph-based coordination strategy for multi-agent reinforcement learning. arXiv preprint arXiv:2201.06257 (2022)."},{"key":"e_1_3_2_2_35_1","volume-title":"Learning to collaborate by grouping: a consensus-oriented strategy for multi-agent reinforcement learning. arXiv preprint arXiv:2307.15530","author":"Ruan J.","year":"2023","unstructured":"Ruan, J., Hao, X., Li, D., and Mao, H. Learning to collaborate by grouping: a consensus-oriented strategy for multi-agent reinforcement learning. arXiv preprint arXiv:2307.15530 (2023)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447913"},{"key":"e_1_3_2_2_37_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman J.","year":"2017","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., and Klimov, O. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_2_38_1","volume-title":"Learning to predict by the methods of temporal differences. Machine learning 3","author":"Sutton R. S.","year":"1988","unstructured":"Sutton, R. S. Learning to predict by the methods of temporal differences. Machine learning 3 (1988), 9--44."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"e_1_3_2_2_40_1","first-page":"24261","volume-title":"Advances in Neural Information Processing Systems","author":"Tolstikhin I. O.","year":"2021","unstructured":"Tolstikhin, I. O., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J., Lucic, M., and Dosovitskiy, A. Mlp-mixer: An all-mlp architecture for vision. In Advances in Neural Information Processing Systems (2021), pp. 24261--24272."},{"key":"e_1_3_2_2_41_1","volume-title":"Visualizing data using t-sne. Journal of machine learning research 9, 11","author":"Van der Maaten L.","year":"2008","unstructured":"Van der Maaten, L., and Hinton, G. Visualizing data using t-sne. Journal of machine learning research 9, 11 (2008)."},{"key":"e_1_3_2_2_42_1","volume-title":"Proceedings of learning, inference and control of multi-agent systems (at NIPS 2016)","author":"Van der Pol E.","year":"2016","unstructured":"Van der Pol, E., and Oliehoek, F. A. Coordinated deep reinforcement learners for traffic light control. Proceedings of learning, inference and control of multi-agent systems (at NIPS 2016) 8 (2016), 21--38."},{"key":"e_1_3_2_2_43_1","volume-title":"The max-pressure controller for arbitrary networks of signalized intersections. Advances in dynamic network modeling in complex transportation systems","author":"Varaiya P.","year":"2013","unstructured":"Varaiya, P. The max-pressure controller for arbitrary networks of signalized intersections. Advances in dynamic network modeling in complex transportation systems (2013), 27--66."},{"key":"e_1_3_2_2_44_1","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani A.","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. Attention is all you need. In Advances in Neural Information Processing Systems (2017), pp. 5998--6008."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104593"},{"key":"e_1_3_2_2_46_1","volume-title":"Adaptive traffic signal control for largescale scenario with cooperative group-based multi-agent reinforcement learning. Transportation research part C: emerging technologies 125","author":"Wang T.","year":"2021","unstructured":"Wang, T., Cao, J., and Hussain, A. Adaptive traffic signal control for largescale scenario with cooperative group-based multi-agent reinforcement learning. Transportation research part C: emerging technologies 125 (2021), 103046."},{"key":"e_1_3_2_2_47_1","volume-title":"Roma: Multi-agent reinforcement learning with emergent roles. arXiv preprint arXiv:2003.08039","author":"Wang T.","year":"2020","unstructured":"Wang, T., Dong, H., Lesser, V., and Zhang, C. Roma: Multi-agent reinforcement learning with emergent roles. arXiv preprint arXiv:2003.08039 (2020)."},{"key":"e_1_3_2_2_48_1","volume-title":"Rode: Learning roles to decompose multi-agent tasks. arXiv preprint arXiv:2010.01523","author":"Wang T.","year":"2020","unstructured":"Wang, T., Gupta, T., Mahajan, A., Peng, B.,Whiteson, S., and Zhang, C. Rode: Learning roles to decompose multi-agent tasks. arXiv preprint arXiv:2010.01523 (2020)."},{"key":"e_1_3_2_2_49_1","volume-title":"Y. Graph-free learning in graph-structured data: A more efficient and accurate spatiotemporal learning perspective. arXiv preprint arXiv:2301.11742","author":"Wang X.","year":"2023","unstructured":"Wang, X., Gu, P.,Wang, P.,Wang, B., Zhou, Z., Bai, L., andWang, Y. Graph-free learning in graph-structured data: A more efficient and accurate spatiotemporal learning perspective. arXiv preprint arXiv:2301.11742 (2023)."},{"key":"e_1_3_2_2_50_1","unstructured":"Wei H. Chen C. Wu K. Zheng G. Yu Z. Gayah V. and Li Z. Deep reinforcement learning for traffic signal control along arterials."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"e_1_3_2_2_53_1","volume-title":"A survey on traffic signal control methods. arXiv preprint arXiv:1904.08117","author":"Wei H.","year":"2019","unstructured":"Wei, H., Zheng, G., Gayah, V., and Li, Z. A survey on traffic signal control methods. arXiv preprint arXiv:1904.08117 (2019)."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"e_1_3_2_2_55_1","first-page":"16509","article-title":"Multiagent reinforcement learning is a sequence modeling problem","volume":"35","author":"Wen M.","year":"2022","unstructured":"Wen, M., Kuba, J., Lin, R., Zhang, W., Wen, Y., Wang, J., and Yang, Y. Multiagent reinforcement learning is a sequence modeling problem. Advances in Neural Information Processing Systems 35 (2022), 16509--16521.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482254"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16575"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586175"},{"key":"e_1_3_2_2_59_1","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu C.","year":"2022","unstructured":"Yu, C., Velu, A., Vinitsky, E., Gao, J., Wang, Y., Bayen, A., and Wu, Y. The surprising effectiveness of ppo in cooperative multi-agent games. Advances in Neural Information Processing Systems 35 (2022), 24611--24624.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_60_1","first-page":"2491","volume-title":"Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence","author":"Yu Z.","year":"2021","unstructured":"Yu, Z., Liang, S., Wei, L., Jin, Z., Huang, J., Cai, D., He, X., and Hua, X.-S. Macar: Urban traffic light control via active multi-agent communication and action rectification. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence (2021), pp. 2491--2497."},{"key":"e_1_3_2_2_61_1","volume-title":"Stackelberg decision transformer for asynchronous action coordination in multi-agent systems. arXiv preprint arXiv:2305.07856","author":"Zhang B.","year":"2023","unstructured":"Zhang, B., Mao, H., Li, L., Xu, Z., Li, D., Zhao, R., and Fan, G. Stackelberg decision transformer for asynchronous action coordination in multi-agent systems. arXiv preprint arXiv:2305.07856 (2023)."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411859"},{"key":"e_1_3_2_2_63_1","first-page":"5872","volume-title":"International Conference on Machine Learning","author":"Zhang K.","year":"2018","unstructured":"Zhang, K., Yang, Z., Liu, H., Zhang, T., and Basar, T. Fully decentralized multi-agent reinforcement learning with networked agents. In International Conference on Machine Learning (2018), pp. 5872--5881."},{"key":"e_1_3_2_2_64_1","volume-title":"Attentionlight: Rethinking queue length and attention mechanism for traffic signal control. arXiv preprint arXiv:2201.00006","author":"Zhang L.","year":"2021","unstructured":"Zhang, L., Wu, Q., and Deng, J. Attentionlight: Rethinking queue length and attention mechanism for traffic signal control. arXiv preprint arXiv:2201.00006 (2021)."},{"key":"e_1_3_2_2_65_1","first-page":"26645","volume-title":"International Conference on Machine Learning","author":"Zhang L.","year":"2022","unstructured":"Zhang, L., Wu, Q., Shen, J., L\u00fc, L., Du, B., and Wu, J. Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control. In International Conference on Machine Learning (2022), PMLR, pp. 26645--26654."},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357900"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3254888"}],"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\/3637528.3671998","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671998","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:06Z","timestamp":1750291566000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671998"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":67,"alternative-id":["10.1145\/3637528.3671998","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671998","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"}}]}}