{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:24:48Z","timestamp":1779294288373,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T00:00:00Z","timestamp":1531958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1565596, IIS-1615597, IIS-1749940"],"award-info":[{"award-number":["IIS-1565596, IIS-1615597, IIS-1749940"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007297","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-14-1-0631, N00014- 17-1-2265"],"award-info":[{"award-number":["N00014-14-1-0631, N00014- 17-1-2265"]}],"id":[{"id":"10.13039\/100007297","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,7,19]]},"DOI":"10.1145\/3219819.3219993","type":"proceedings-article","created":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T13:05:12Z","timestamp":1532005512000},"page":"1774-1783","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":296,"title":["Efficient Large-Scale Fleet Management via Multi-Agent Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Kaixiang","family":"Lin","sequence":"first","affiliation":[{"name":"Michigan State University, East Lansing, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Didi Chuxing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Michigan State University, East Lansing, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,7,19]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Miles Brundage, and Anil Anthony Bharath .","author":"Arulkumaran Kai","year":"2017"},{"key":"e_1_3_2_2_2_1","volume-title":"Interactive Collaborative Information Systems","author":"Bakker Bram"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/2566972.2566979"},{"key":"e_1_3_2_2_4_1","volume-title":"OpenAI gym. arXiv preprint arXiv:1606.01540","author":"Brockman Greg","year":"2016"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"e_1_3_2_2_6_1","unstructured":"Didi Chuxing . {n. d.}. (. {n. d.}). deftempurl%http:\/\/www.didichuxing.com\/en\/ tempurl  Didi Chuxing . {n. d.}. (. {n. d.}). deftempurl%http:\/\/www.didichuxing.com\/en\/ tempurl"},{"key":"e_1_3_2_2_7_1","volume-title":"Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289","author":"Clevert Djork-Arn\u00e9","year":"2015"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.21.4.227"},{"key":"e_1_3_2_2_9_1","volume-title":"Counterfactual Multi-Agent Policy Gradients. arXiv preprint arXiv:1705.08926","author":"Foerster Jakob","year":"2017"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.36.1.21.570"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.36.1.40.572"},{"key":"e_1_3_2_2_12_1","volume-title":"Identity mappings in deep residual networks","author":"He Kaiming"},{"key":"e_1_3_2_2_14_1","volume-title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. arXiv preprint arXiv:1706.02275","author":"Lowe Ryan","year":"2017"},{"key":"e_1_3_2_2_15_1","volume-title":"The influence of multi-agent cooperation on the efficiency of taxi dispatching PPAM","author":"Maciejewski Micha\u0142"},{"key":"e_1_3_2_2_16_1","volume-title":"Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu .","author":"Mnih Volodymyr","year":"2016"},{"key":"e_1_3_2_2_17_1","volume-title":"et almbox","author":"Mnih Volodymyr","year":"2015"},{"key":"e_1_3_2_2_18_1","volume-title":"2017 a. Collective multiagent sequential decision making under uncertainty. AAAI","author":"Nguyen Duc Thien","year":"2017"},{"key":"e_1_3_2_2_19_1","volume-title":"2017 b. Policy gradient with value function approximation for collective multiagent planning. NIPS","author":"Nguyen Duc Thien","year":"2017"},{"key":"e_1_3_2_2_20_1","volume-title":"Giovanni De Magistris, and Ryuki Tachibana","author":"Pham Tu-Hoa","year":"2017"},{"key":"e_1_3_2_2_21_1","first-page":"607","article-title":"A collaborative multiagent taxi-dispatch system","volume":"7","author":"Seow Kiam Tian","year":"2010","journal-title":"IEEE T-ASE"},{"key":"e_1_3_2_2_22_1","volume-title":"Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et almbox. .","author":"Silver David","year":"2016"},{"key":"e_1_3_2_2_23_1","volume-title":"et almbox","author":"Silver David","year":"2017"},{"key":"e_1_3_2_2_24_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Ming Tan . 1993. Multi-agent reinforcement learning: Independent vs. cooperative agents ICML. 330--337.   Ming Tan . 1993. Multi-agent reinforcement learning: Independent vs. cooperative agents ICML. 330--337.","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"e_1_3_2_2_27_1","unstructured":"Uber . {n. d.}. (. {n. d.}). deftempurl%https:\/\/www.uber.com\/ tempurl  Uber . {n. d.}. (. {n. d.}). deftempurl%https:\/\/www.uber.com\/ tempurl"},{"key":"e_1_3_2_2_28_1","volume-title":"Look-ahead Insertion Policy for A Shared-taxi System Based on Reinforcement Learning","author":"Wei Chong","year":"2017"},{"key":"e_1_3_2_2_29_1","volume-title":"Mean Field Multi-Agent Reinforcement Learning. ICML","author":"Yang Yaodong","year":"2018"},{"key":"e_1_3_2_2_30_1","volume-title":"MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence. arXiv preprint arXiv:1712.00600","author":"Zheng Lianmin","year":"2017"}],"event":{"name":"KDD '18: The 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","location":"London United Kingdom","acronym":"KDD '18","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 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3219819.3219993","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3219819.3219993","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3219819.3219993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:07:22Z","timestamp":1750212442000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3219819.3219993"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,19]]},"references-count":29,"alternative-id":["10.1145\/3219819.3219993","10.1145\/3219819"],"URL":"https:\/\/doi.org\/10.1145\/3219819.3219993","relation":{},"subject":[],"published":{"date-parts":[[2018,7,19]]},"assertion":[{"value":"2018-07-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}