{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T09:29:24Z","timestamp":1781774964421,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":30,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF China","award":["U21A20519,U20A20181,62372288,62202298"],"award-info":[{"award-number":["U21A20519,U20A20181,62372288,62202298"]}]},{"name":"DiDi GAIA Research Collaboration Plan"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3672028","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:54:55Z","timestamp":1724561695000},"page":"3863-3873","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Rethinking Order Dispatching in Online Ride-Hailing Platforms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7008-7629","authenticated-orcid":false,"given":"Zhaoxing","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5178-7198","authenticated-orcid":false,"given":"Haiming","family":"Jin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7007-6110","authenticated-orcid":false,"given":"Guiyun","family":"Fan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2238-5365","authenticated-orcid":false,"given":"Min","family":"Lu","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3819-6743","authenticated-orcid":false,"given":"Yiran","family":"Liu","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8228-5256","authenticated-orcid":false,"given":"Xinlang","family":"Yue","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6235-8860","authenticated-orcid":false,"given":"Hao","family":"Pan","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3902-2595","authenticated-orcid":false,"given":"Zhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9510-2279","authenticated-orcid":false,"given":"Guobin","family":"Wu","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0944-6723","authenticated-orcid":false,"given":"Qun","family":"Li","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9093-1182","authenticated-orcid":false,"given":"Xiaotong","family":"Wang","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2402-6562","authenticated-orcid":false,"given":"Jiecheng","family":"Guo","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Deep policies for online bipartite matching: A reinforcement learning approach. arXiv preprint arXiv:2109.10380","author":"Alomrani Mohammad Ali","year":"2021","unstructured":"Mohammad Ali Alomrani, Reza Moravej, and Elias B Khalil. 2021. Deep policies for online bipartite matching: A reinforcement learning approach. arXiv preprint arXiv:2109.10380 (2021)."},{"key":"e_1_3_2_2_2_1","unstructured":"David Brandfonbrener Will Whitney Rajesh Ranganath and Joan Bruna. 2021. Offline RL without Off-Policy Evaluation. In NeurIPS."},{"key":"e_1_3_2_2_3_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_2_4_1","volume-title":"Edge-weighted online bipartite matching. J. ACM","author":"Fahrbach Matthew","year":"2022","unstructured":"Matthew Fahrbach, Zhiyi Huang, Runzhou Tao, and Morteza Zadimoghaddam. 2022. Edge-weighted online bipartite matching. J. ACM (2022)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Jakob Foerster Gregory Farquhar Triantafyllos Afouras Nantas Nardelli and Shimon Whiteson. 2018. Counterfactual multi-agent policy gradients. In AAAI.","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"e_1_3_2_2_6_1","volume-title":"College admissions and the stability of marriage. The American Mathematical Monthly","author":"Gale David","year":"1962","unstructured":"David Gale and Lloyd S Shapley. 1962. College admissions and the stability of marriage. The American Mathematical Monthly (1962)."},{"key":"e_1_3_2_2_7_1","volume-title":"Xiaowei Wu, Yuhao Zhang, and Xue Zhu.","author":"Huang Zhiyi","year":"2018","unstructured":"Zhiyi Huang, Ning Kang, Zhihao Gavin Tang, Xiaowei Wu, Yuhao Zhang, and Xue Zhu. 2018. How to match when all vertices arrive online. In STOC."},{"key":"e_1_3_2_2_8_1","volume-title":"Xiaowei Wu, and Yuhao Zhang.","author":"Huang Zhiyi","year":"2019","unstructured":"Zhiyi Huang, Zhihao Gavin Tang, Xiaowei Wu, and Yuhao Zhang. 2019. Online vertex-weighted bipartite matching: Beating 1--1\/e with random arrivals. ACM Transactions on Algorithms (2019)."},{"key":"e_1_3_2_2_9_1","volume-title":"Xiaowei Wu, and Yuhao Zhang.","author":"Huang Zhiyi","year":"2020","unstructured":"Zhiyi Huang, Zhihao Gavin Tang, Xiaowei Wu, and Yuhao Zhang. 2020. Fully Online Matching II: Beating Ranking and Water-filling. In FOCS."},{"key":"e_1_3_2_2_10_1","unstructured":"Haiming Jin Yifei Wei Zhaoxing Yang Zirui Liu and Guiyun Fan. 2023. Multi-Intersection Management for Connected Autonomous Vehicles by Reinforcement Learning. In ICDCS."},{"key":"e_1_3_2_2_11_1","unstructured":"Jiarui Jin Ming Zhou Weinan Zhang Minne Li Zilong Guo Zhiwei Qin Yan Jiao Xiaocheng Tang Chenxi Wang Jun Wang Guobin Wu and Jieping Ye. 2019. CoRide: Joint Order Dispatching and Fleet Management for Multi-Scale Ride-Hailing Platforms. In CIKM."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"R. M. Karp U. V. Vazirani and V. V. Vazirani. 1990. An Optimal Algorithm for On-Line Bipartite Matching. In STOC.","DOI":"10.1145\/100216.100262"},{"key":"e_1_3_2_2_13_1","unstructured":"Ilya Kostrikov Ashvin Nair and Sergey Levine. 2022. Offline Reinforcement Learning with Implicit Q-Learning. In ICLR."},{"key":"e_1_3_2_2_14_1","volume-title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems. arXiv preprint arXiv:2005.01643","author":"Levine Sergey","year":"2020","unstructured":"Sergey Levine, Aviral Kumar, G. Tucker, and Justin Fu. 2020. Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems. arXiv preprint arXiv:2005.01643 (2020)."},{"key":"e_1_3_2_2_15_1","volume-title":"Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees. arXiv preprint arXiv:2306.00172","author":"Li Pengfei","year":"2023","unstructured":"Pengfei Li, Jianyi Yang, and Shaolei Ren. 2023. Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees. arXiv preprint arXiv:2306.00172 (2023)."},{"key":"e_1_3_2_2_16_1","volume-title":"OpenAI Pieter Abbeel, and Igor Mordatch","author":"Lowe Ryan","year":"2017","unstructured":"Ryan Lowe, Yi Wu, Aviv Tamar, Jean Harb, OpenAI Pieter Abbeel, and Igor Mordatch. 2017. Multi-agent actor-critic for mixed cooperative-competitive environments. In NeurIPS."},{"key":"e_1_3_2_2_17_1","unstructured":"James Munkres. 1957. Algorithms for the assignment and transportation problems. J. Soc. Indust. Appl. Math. (1957)."},{"key":"e_1_3_2_2_18_1","unstructured":"OpenAI. 2023. Introducing ChatGPT. https:\/\/openai.com\/blog\/chatgpt Sep. 20."},{"key":"e_1_3_2_2_19_1","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. In NeurIPS."},{"key":"e_1_3_2_2_20_1","volume-title":"Singh","author":"Precup Doina","year":"2000","unstructured":"Doina Precup, Richard S. Sutton, and Satinder P. Singh. 2000. Eligibility Traces for Off-Policy Policy Evaluation. In ICML."},{"key":"e_1_3_2_2_21_1","volume-title":"Gregory Farquhar, Jakob Foerster, and Shimon Whiteson.","author":"Rashid Tabish","year":"2020","unstructured":"Tabish Rashid, Mikayel Samvelyan, Christian Schroeder De Witt, Gregory Farquhar, Jakob Foerster, and Shimon Whiteson. 2020. Monotonic value function factorisation for deep multi-agent reinforcement learning. The Journal of Machine Learning Research (2020)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","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. In KDD.","DOI":"10.1145\/3534678.3539095"},{"key":"e_1_3_2_2_23_1","unstructured":"Jiahui Sun Haiming Jin Zhaoxing Yang Lu Su and Xinbing Wang. 2022. Optimizing Long-Term Efficiency and Fairness in Ride-Hailing via Joint Order Dispatching and Driver Repositioning. In KDD."},{"key":"e_1_3_2_2_24_1","unstructured":"Xiaocheng Tang Zhiwei Qin Fan Zhang Zhaodong Wang Zhe Xu Yintai Ma Hongtu Zhu and Jieping Ye. 2019. A deep value-network based approach for multi-driver order dispatching. In KDD."},{"key":"e_1_3_2_2_25_1","unstructured":"Xiaocheng Tang Fan Zhang Zhiwei Qin Yansheng Wang Dingyuan Shi Bingchen Song Yongxin Tong Hongtu Zhu and Jieping Ye. 2021. Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms. In KDD."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3022173"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Zhe Xu Zhixin Li Qingwen Guan Dingshui Zhang Qiang Li Junxiao Nan Chunyang Liu Wei Bian and Jieping Ye. 2018. Large-Scale Order Dispatch in On-Demand Ride-Hailing Platforms: A Learning and Planning Approach. In KDD.","DOI":"10.1145\/3219819.3219824"},{"key":"e_1_3_2_2_28_1","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. In NeurIPS."},{"key":"e_1_3_2_2_29_1","volume-title":"Understanding of Didi's Trading Strategy: Driver Order Matching. https:\/\/mp.weixin.qq.com\/s\/i8IIaMYaFub0a9M9MtFgSw. [Online","author":"Zhong Chen","year":"2023","unstructured":"Chen Zhong. 2023. Understanding of Didi's Trading Strategy: Driver Order Matching. https:\/\/mp.weixin.qq.com\/s\/i8IIaMYaFub0a9M9MtFgSw. [Online; accessed 7-Nov-2023]."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Ming Zhou Jiarui Jin Weinan Zhang Zhiwei Qin Yan Jiao Chenxi Wang Guobin Wu Yong Yu and Jieping Ye. 2019. Multi-Agent Reinforcement Learning for Order-Dispatching via Order-Vehicle Distribution Matching. In CIKM.","DOI":"10.1145\/3357384.3357799"}],"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\/3637528.3672028","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3672028","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\/3637528.3672028"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":30,"alternative-id":["10.1145\/3637528.3672028","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3672028","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"}}]}}