{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:38:17Z","timestamp":1772555897230,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M742034"],"award-info":[{"award-number":["2023M742034"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua University-Toyota Research Center"},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2030, 62272260"],"award-info":[{"award-number":["U23B2030, 62272260"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709205","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:48:32Z","timestamp":1743792512000},"page":"1457-1468","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["CoopRide: Cooperate All Grids in City-Scale Ride-Hailing Dispatching with Multi-Agent Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9175-6255","authenticated-orcid":false,"given":"Jingwei","family":"Wang","sequence":"first","affiliation":[{"name":"Department of EE, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7109-3588","authenticated-orcid":false,"given":"Qianyue","family":"Hao","sequence":"additional","affiliation":[{"name":"Department of EE, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0454-7516","authenticated-orcid":false,"given":"Wenzhen","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of EE, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8945-3046","authenticated-orcid":false,"given":"Xiaochen","family":"Fan","sequence":"additional","affiliation":[{"name":"IEIT in Tianjin, Department of EE, BNRist, Tsinghua University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1449-5046","authenticated-orcid":false,"given":"Qin","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen City, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2481-4119","authenticated-orcid":false,"given":"Zhentao","family":"Tang","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0267-3749","authenticated-orcid":false,"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0422-8235","authenticated-orcid":false,"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China & Huawei Noah's Ark Lab, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5617-1659","authenticated-orcid":false,"given":"Yong","family":"Li","sequence":"additional","affiliation":[{"name":"Department of EE, BNRist, Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Mingfei Sun, and Shimon Whiteson.","author":"De Witt Christian Schroeder","year":"2020","unstructured":"Christian Schroeder De Witt, Tarun Gupta, Denys Makoviichuk, Viktor Makoviychuk, Philip HS Torr, Mingfei Sun, and Shimon Whiteson. 2020. Is independent learning all you need in the starcraft multi-agent challenge? arXiv preprint arXiv:2011.09533 (2020)."},{"key":"e_1_3_2_1_2_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Du Yali","year":"2019","unstructured":"Yali Du, Lei Han, Meng Fang, Ji Liu, Tianhong Dai, and Dacheng Tao. 2019. Liir: Learning individual intrinsic reward in multi-agent reinforcement learning. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_3_1","volume-title":"Reinforcement Learning in the Wild: Scalable RL Dispatching Algorithm Deployed in Ridehailing Marketplace. arXiv preprint arXiv:2202.05118","author":"Eshkevari Soheil Sadeghi","year":"2022","unstructured":"Soheil Sadeghi Eshkevari, Xiaocheng Tang, Zhiwei Qin, Jinhan Mei, Cheng Zhang, Qianying Meng, and Jia Xu. 2022. Reinforcement Learning in the Wild: Scalable RL Dispatching Algorithm Deployed in Ridehailing Marketplace. arXiv preprint arXiv:2202.05118 (2022)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599359"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00129"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357978"},{"key":"e_1_3_2_1_8_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3141\/1882-23"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Minne Li Zhiwei Qin Yan Jiao Yaodong Yang Jun Wang Chenxi Wang Guobin Wu and Jieping Ye. 2019. Efficient ridesharing order dispatching with mean field multi-agent reinforcement learning. In The world wide web conference. 983--994.","DOI":"10.1145\/3308558.3313433"},{"key":"e_1_3_2_1_11_1","volume-title":"Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv preprint arXiv:1707.01926","author":"Li Yaguang","year":"2017","unstructured":"Yaguang Li, Rose Yu, Cyrus Shahabi, and Yan Liu. 2017. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv preprint arXiv:1707.01926 (2017)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/769800.769806"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/3091574.3091594"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3096226"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2022.100075"},{"key":"e_1_3_2_1_17_1","volume-title":"OpenAI Pieter Abbeel, and Igor Mordatch","author":"Lowe Ryan","year":"2017","unstructured":"Ryan Lowe, Yi I Wu, Aviv Tamar, Jean Harb, OpenAI Pieter Abbeel, and Igor Mordatch. 2017. Multi-agent actor-critic for mixed cooperative-competitive environments. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1137\/0105003"},{"key":"e_1_3_2_1_19_1","first-page":"10784","article-title":"Learning to simulate self-driven particles system with coordinated policy optimization","volume":"34","author":"Peng Zhenghao","year":"2021","unstructured":"Zhenghao Peng, Quanyi Li, Ka Ming Hui, Chunxiao Liu, and Bolei Zhou. 2021. Learning to simulate self-driven particles system with coordinated policy optimization. Advances in Neural Information Processing Systems, Vol. 34 (2021), 10784--10797.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455894"},{"key":"e_1_3_2_1_21_1","volume-title":"Gregory Farquhar, Nantas Nardelli, Tim GJ Rudner, Chia-Man Hung, Philip HS Torr, Jakob Foerster, and Shimon Whiteson.","author":"Samvelyan Mikayel","year":"2019","unstructured":"Mikayel Samvelyan, Tabish Rashid, Christian Schroeder De Witt, Gregory Farquhar, Nantas Nardelli, Tim GJ Rudner, Chia-Man Hung, Philip HS Torr, Jakob Foerster, and Shimon Whiteson. 2019. The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043 (2019)."},{"key":"e_1_3_2_1_22_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2009.2028577"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539060"},{"key":"e_1_3_2_1_25_1","volume-title":"Vinicius Zambaldi, Max Jaderberg, Marc Lanctot, Nicolas Sonnerat, Joel Z Leibo, Karl Tuyls, et al.","author":"Sunehag Peter","year":"2017","unstructured":"Peter Sunehag, Guy Lever, Audrunas Gruslys, Wojciech Marian Czarnecki, Vinicius Zambaldi, Max Jaderberg, Marc Lanctot, Nicolas Sonnerat, Joel Z Leibo, Karl Tuyls, et al. 2017. Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)."},{"key":"e_1_3_2_1_26_1","volume-title":"Policy gradient methods for reinforcement learning with function approximation. Advances in neural information processing systems","author":"Sutton Richard S","year":"1999","unstructured":"Richard S Sutton, David McAllester, Satinder Singh, and Yishay Mansour. 1999. Policy gradient methods for reinforcement learning with function approximation. Advances in neural information processing systems, Vol. 12 (1999)."},{"key":"e_1_3_2_1_27_1","volume-title":"Scaling law of urban ride sharing. Scientific reports","author":"Tachet Remi","year":"2017","unstructured":"Remi Tachet, Oleguer Sagarra, Paolo Santi, Giovanni Resta, Michael Szell, Steven H Strogatz, and Carlo Ratti. 2017. Scaling law of urban ride sharing. Scientific reports, Vol. 7, 1 (2017), 1--6."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330724"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467096"},{"key":"e_1_3_2_1_31_1","volume-title":"Qplex: Duplex dueling multi-agent q-learning. arXiv preprint arXiv:2008.01062","author":"Wang Jianhao","year":"2020","unstructured":"Jianhao Wang, Zhizhou Ren, Terry Liu, Yang Yu, and Chongjie Zhang. 2020. Qplex: Duplex dueling multi-agent q-learning. arXiv preprint arXiv:2008.01062 (2020)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219824"},{"key":"e_1_3_2_1_33_1","volume-title":"Meta-gradient reinforcement learning. Advances in neural information processing systems","author":"Xu Zhongwen","year":"2018","unstructured":"Zhongwen Xu, Hado P van Hasselt, and David Silver. 2018b. Meta-gradient reinforcement learning. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/nav.21872"},{"key":"e_1_3_2_1_35_1","volume-title":"International conference on machine learning. PMLR, 5571--5580","author":"Yang Yaodong","year":"2018","unstructured":"Yaodong Yang, Rui Luo, Minne Li, Ming Zhou, Weinan Zhang, and Jun Wang. 2018. Mean field multi-agent reinforcement learning. In International conference on machine learning. PMLR, 5571--5580."},{"key":"e_1_3_2_1_36_1","volume-title":"An overview of multi-agent reinforcement learning from game theoretical perspective. arXiv preprint arXiv:2011.00583","author":"Yang Yaodong","year":"2020","unstructured":"Yaodong Yang and Jun Wang. 2020. An overview of multi-agent reinforcement learning from game theoretical perspective. arXiv preprint arXiv:2011.00583 (2020)."},{"key":"e_1_3_2_1_37_1","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","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.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Zheng Zeyu","year":"2018","unstructured":"Zeyu Zheng, Junhyuk Oh, and Satinder Singh. 2018. On learning intrinsic rewards for policy gradient methods. Advances in Neural Information Processing Systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357799"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709205","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:42:33Z","timestamp":1755358953000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709205"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":39,"alternative-id":["10.1145\/3690624.3709205","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709205","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}