{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:55:24Z","timestamp":1783526124616,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3680013","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:11Z","timestamp":1729452851000},"page":"5054-5061","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["An End-to-End Reinforcement Learning Based Approach for Micro-View Order-Dispatching in Ride-Hailing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8228-5256","authenticated-orcid":false,"given":"Xinlang","family":"Yue","sequence":"first","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\/0009-0000-4210-712X","authenticated-orcid":false,"given":"Fangzhou","family":"Shi","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6450-0516","authenticated-orcid":false,"given":"Sihong","family":"Luo","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7503-3064","authenticated-orcid":false,"given":"Chen","family":"Zhong","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, 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\/0000-0002-3902-2595","authenticated-orcid":false,"given":"Zhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Machine Learning. PMLR, 864--872","author":"Chen Xi","year":"2018","unstructured":"Xi Chen, Nikhil Mishra, Mostafa Rohaninejad, and Pieter Abbeel. 2018. Pixelsnail: An improved autoregressive generative model. In International Conference on Machine Learning. PMLR, 864--872."},{"key":"e_1_3_2_1_2_1","volume-title":"On empirical comparisons of optimizers for deep learning. arXiv preprint arXiv:1910.05446","author":"Choi Dami","year":"2019","unstructured":"Dami Choi, Christopher J Shallue, Zachary Nado, Jaehoon Lee, Chris J Maddison, and George E Dahl. 2019. On empirical comparisons of optimizers for deep learning. arXiv preprint arXiv:1910.05446 (2019)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1080\/00029890.1962.11989827"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539141"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the AAAI conference on artificial intelligence","volume":"26","author":"Ho Chien-Ju","year":"2012","unstructured":"Chien-Ju Ho and Jennifer Vaughan. 2012. Online task assignment in crowdsourcing markets. In Proceedings of the AAAI conference on artificial intelligence, Vol. 26. 45--51."},{"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":"10.1287\/msom.2020.0952"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357978"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1006\/jagm.1993.1026"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/100216.100262"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3006084"},{"key":"e_1_3_2_1_12_1","volume-title":"The Hungarian method for the assignment problem. Naval research logistics quarterly","author":"Kuhn Harold W","year":"1955","unstructured":"Harold W Kuhn. 1955. The Hungarian method for the assignment problem. Naval research logistics quarterly, Vol. 2, 1--2 (1955), 83--97."},{"key":"e_1_3_2_1_13_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_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"key":"e_1_3_2_1_15_1","first-page":"23609","article-title":"A hierarchical reinforcement learning based optimization framework for large-scale dynamic pickup and delivery problems","volume":"34","author":"Ma Yi","year":"2021","unstructured":"Yi Ma, Xiaotian Hao, Jianye Hao, Jiawen Lu, Xing Liu, Tong Xialiang, Mingxuan Yuan, Zhigang Li, Jie Tang, and Zhaopeng Meng. 2021. A hierarchical reinforcement learning based optimization framework for large-scale dynamic pickup and delivery problems. Advances in Neural Information Processing Systems, Vol. 34 (2021), 23609--23620.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_16_1","volume-title":"Discrete sequential prediction of continuous actions for deep rl. arXiv preprint arXiv:1705.05035","author":"Metz Luke","year":"2017","unstructured":"Luke Metz, Julian Ibarz, Navdeep Jaitly, and James Davidson. 2017. Discrete sequential prediction of continuous actions for deep rl. arXiv preprint arXiv:1705.05035 (2017)."},{"key":"e_1_3_2_1_17_1","unstructured":"Thomas PIERROT Valentin Mac\u00e9 Jean-Baptiste Sevestre Louis Monier Alexandre Laterre Nicolas Perrin Karim Beguir and Olivier Sigaud. 2020. Factored Action Spaces in Deep Reinforcement Learning. (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103239"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103852"},{"key":"e_1_3_2_1_20_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_21_1","volume-title":"Optimal stopping rules","author":"Shiryaev Albert N","unstructured":"Albert N Shiryaev. 2007. Optimal stopping rules. Vol. 8. Springer Science & Business Media."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539060"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330724"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467096"},{"key":"e_1_3_2_1_25_1","volume-title":"Combinatorial optimization meets reinforcement learning: Effective taxi order dispatching at large-scale","author":"Tong Yongxin","year":"2021","unstructured":"Yongxin Tong, Dingyuan Shi, Yi Xu, Weifeng Lv, Zhiwei Qin, and Xiaocheng Tang. 2021. Combinatorial optimization meets reinforcement learning: Effective taxi order dispatching at large-scale. IEEE Transactions on Knowledge and Data Engineering (2021)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00133"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00077"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219824"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2019.11.005"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems. 1961--1968","author":"Zeng Hao","year":"2023","unstructured":"Hao Zeng, Qiong Wu, Kunpeng Han, Junying He, and Haoyuan Hu. 2023. A Deep Reinforcement Learning Approach for Online Parcel Assignment. In Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems. 1961--1968."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2018.00037"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357799"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680013","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3680013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:17Z","timestamp":1750294697000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680013"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":32,"alternative-id":["10.1145\/3627673.3680013","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3680013","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}