{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T00:08:23Z","timestamp":1774051703774,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,11,3]],"date-time":"2019-11-03T00:00:00Z","timestamp":1572739200000},"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":["1618448"],"award-info":[{"award-number":["1618448"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1652525"],"award-info":[{"award-number":["1652525"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,11,3]]},"DOI":"10.1145\/3357384.3358079","type":"proceedings-article","created":{"date-parts":[[2019,11,4]],"date-time":"2019-11-04T14:11:35Z","timestamp":1572876695000},"page":"2289-2292","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":40,"title":["Learning Traffic Signal Control from Demonstrations"],"prefix":"10.1145","author":[{"given":"Yuanhao","family":"Xiong","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanjie","family":"Zheng","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, State College, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Tianrang Intelligent Technology Co., Ltd, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhui","family":"Li","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, State College, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,11,3]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control","author":"Chu Tianshu","year":"2019"},{"key":"e_1_3_2_1_2_1","volume-title":"Advances in applied self-organizing systems","author":"Cools Seung-Bae"},{"key":"e_1_3_2_1_3_1","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence .","author":"Hester Todd","year":"2018"},{"key":"e_1_3_2_1_4_1","unstructured":"Jonathan Ho and Stefano Ermon. 2016. Generative adversarial imitation learning. In Advances in Neural Information Processing Systems. 4565--4573.  Jonathan Ho and Stefano Ermon. 2016. Generative adversarial imitation learning. In Advances in Neural Information Processing Systems. 4565--4573."},{"key":"e_1_3_2_1_5_1","volume-title":"Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144","author":"Jang Eric","year":"2016"},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Learning Representations . https:\/\/openreview.net\/forum?id=HJlmHoR5tQ","author":"Qureshi Ahmed H."},{"key":"e_1_3_2_1_7_1","volume-title":"Prioritized experience replay. arXiv preprint arXiv:1511.05952","author":"Schaul Tom","year":"2015"},{"key":"e_1_3_2_1_8_1","unstructured":"van der Pol et al. 2016. Coordinated Deep Reinforcement Learners for Traffic Light Control. NIPS.  van der Pol et al. 2016. Coordinated Deep Reinforcement Learners for Traffic Light Control. NIPS."},{"key":"e_1_3_2_1_9_1","volume-title":"Deep Reinforcement Learning with Double Q-learning. arXiv preprint arXiv:1509.06461","author":"van Hasselt Hado","year":"2015"},{"key":"e_1_3_2_1_10_1","volume-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards. arXiv preprint arXiv:1707.08817","author":"Matej Vevc","year":"2017"},{"key":"e_1_3_2_1_11_1","volume-title":"A Survey on Traffic Signal Control Methods. arXiv preprint arXiv:1904.08117","author":"Wei Hua","year":"2019"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"e_1_3_2_1_13_1","unstructured":"Ronald J Williams. 199"},{"key":"e_1_3_2_1_14_1","volume-title":"CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario. In The World Wide Web Conference. ACM, 3620--3624","author":"Zhang Huichu","year":"2019"},{"key":"e_1_3_2_1_15_1","volume-title":"2019 a. Learning Phase Competition for Traffic Signal Control. arXiv preprint arXiv:1905.04722","author":"Zheng Guanjie","year":"2019"},{"key":"e_1_3_2_1_16_1","volume-title":"2019 b. Diagnosing Reinforcement Learning for Traffic Signal Control. arXiv preprint arXiv:1905.04716","author":"Zheng Guanjie","year":"2019"}],"event":{"name":"CIKM '19: The 28th ACM International Conference on Information and Knowledge Management","location":"Beijing China","acronym":"CIKM '19","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 28th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3357384.3358079","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3357384.3358079","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3357384.3358079","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:44:18Z","timestamp":1750203858000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3357384.3358079"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,3]]},"references-count":16,"alternative-id":["10.1145\/3357384.3358079","10.1145\/3357384"],"URL":"https:\/\/doi.org\/10.1145\/3357384.3358079","relation":{},"subject":[],"published":{"date-parts":[[2019,11,3]]},"assertion":[{"value":"2019-11-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}