乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T10:06:00Z","timestamp":1743761160657,"version":"3.28.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,7,25]],"date-time":"2019-07-25T00:00:00Z","timestamp":1564012800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,7,25]]},"DOI":"10.1145\/3292500.3330988","type":"proceedings-article","created":{"date-parts":[[2019,7,26]],"date-time":"2019-07-26T09:17:26Z","timestamp":1564132646000},"page":"1654-1664","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["Time Critic Policy Gradient Methods for Traffic Signal Control in Complex and Congested Scenarios"],"prefix":"10.1145","author":[{"given":"Stefano Giovanni","family":"Rizzo","sequence":"first","affiliation":[{"name":"Qatar Computing Research Institute, Doha, Qatar"}]},{"given":"Giovanna","family":"Vantini","sequence":"additional","affiliation":[{"name":"Qatar Computing Research Institute, Doha, Qatar"}]},{"given":"Sanjay","family":"Chawla","sequence":"additional","affiliation":[{"name":"Qatar Computing Research Institute, Doha, Qatar"}]}],"member":"320","published-online":{"date-parts":[[2019,7,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-947X(2003)129:3(278)"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0096"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1992.219989"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/1797096.1797172"},{"key":"e_1_3_2_1_5_1","volume-title":"Quantifying Generalization in Reinforcement Learning. arXiv preprint arXiv:1812.02341","author":"Cobbe Karl","year":"2018","unstructured":"Karl Cobbe , Oleg Klimov , Chris Hesse , Taehoon Kim , and John Schulman . 2018. Quantifying Generalization in Reinforcement Learning. arXiv preprint arXiv:1812.02341 ( 2018 ). Karl Cobbe, Oleg Klimov, Chris Hesse, Taehoon Kim, and John Schulman. 2018. Quantifying Generalization in Reinforcement Learning. arXiv preprint arXiv:1812.02341 (2018)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2015.98"},{"key":"e_1_3_2_1_7_1","volume-title":"Adaptive Traffic Signal Control: Deep Reinforcement Learning Algorithm with Experience Replay and Target Network. arXiv preprint arXiv:1705.02755","author":"Gao Juntao","year":"2017","unstructured":"Juntao Gao , Yulong Shen , Jia Liu , Minoru Ito , and Norio Shiratori . 2017. Adaptive Traffic Signal Control: Deep Reinforcement Learning Algorithm with Experience Replay and Target Network. arXiv preprint arXiv:1705.02755 ( 2017 ). Juntao Gao, Yulong Shen, Jia Liu, Minoru Ito, and Norio Shiratori. 2017. Adaptive Traffic Signal Control: Deep Reinforcement Learning Algorithm with Experience Replay and Target Network. arXiv preprint arXiv:1705.02755 (2017)."},{"key":"e_1_3_2_1_8_1","volume-title":"Using a deep reinforcement learning agent for traffic signal control. arXiv preprint arXiv:1611.01142","author":"Genders Wade","year":"2016","unstructured":"Wade Genders and Saiedeh Razavi . 2016. Using a deep reinforcement learning agent for traffic signal control. arXiv preprint arXiv:1611.01142 ( 2016 ). Wade Genders and Saiedeh Razavi. 2016. Using a deep reinforcement learning agent for traffic signal control. arXiv preprint arXiv:1611.01142 (2016)."},{"volume-title":"Machine Learning and Knowledge Discovery in Databases ,","author":"Kuyer Lior","key":"e_1_3_2_1_9_1","unstructured":"Lior Kuyer , Shimon Whiteson , Bram Bakker , and Nikos Vlassis . 2008. Multiagent Reinforcement Learning for Urban Traffic Control Using Coordination Graphs . In Machine Learning and Knowledge Discovery in Databases , , Walter Daelemans, Bart Goethals, and Katharina Morik (Eds.). Springer Berlin Heidelberg , Berlin, Heidelberg , 656--671. Lior Kuyer, Shimon Whiteson, Bram Bakker, and Nikos Vlassis. 2008. Multiagent Reinforcement Learning for Urban Traffic Control Using Coordination Graphs. In Machine Learning and Knowledge Discovery in Databases , , Walter Daelemans, Bart Goethals, and Katharina Morik (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 656--671."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7508798"},{"key":"e_1_3_2_1_11_1","unstructured":"X. Liang X. Du G. Wang and Z. Han. 2019. A Deep Q Learning Network for Traffic Lights' Cycle Control in Vehicular Networks. IEEE Transactions on Vehicular Technology (2019) 1--1. X. Liang X. Du G. Wang and Z. Han. 2019. A Deep Q Learning Network for Traffic Lights' Cycle Control in Vehicular Networks. IEEE Transactions on Vehicular Technology (2019) 1--1."},{"key":"e_1_3_2_1_12_1","first-page":"105","article-title":"A survey of intelligence methods in urban traffic signal control","volume":"7","author":"Liu Zhiyong","year":"2007","unstructured":"Zhiyong Liu . 2007 . A survey of intelligence methods in urban traffic signal control . IJCSNS International Journal of Computer Science and Network Security , Vol. 7 , 7 (2007), 105 -- 112 . Zhiyong Liu. 2007. A survey of intelligence methods in urban traffic signal control. IJCSNS International Journal of Computer Science and Network Security , Vol. 7, 7 (2007), 105--112.","journal-title":"IJCSNS International Journal of Computer Science and Network Security"},{"key":"e_1_3_2_1_13_1","volume-title":"Integrated optimization of lane markings and timings for signalized roundabouts. Transportation research part C: emerging technologies","author":"Ma Wanjing","year":"2013","unstructured":"Wanjing Ma , Yue Liu , Larry Head , and Xiaoguang Yang . 2013. Integrated optimization of lane markings and timings for signalized roundabouts. Transportation research part C: emerging technologies , Vol. 36 ( 2013 ), 307--323. Wanjing Ma, Yue Liu, Larry Head, and Xiaoguang Yang. 2013. Integrated optimization of lane markings and timings for signalized roundabouts. Transportation research part C: emerging technologies , Vol. 36 (2013), 307--323."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8667.2007.00524.x"},{"key":"e_1_3_2_1_15_1","volume-title":"HCM2010","author":"Manual Highway Capacity","year":"2010","unstructured":"Highway Capacity Manual . 2010 . HCM2010 . Transportation Research Board, National Research Council, Washington, DC (2010). Highway Capacity Manual. 2010. HCM2010. Transportation Research Board, National Research Council, Washington, DC (2010)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2017.0153"},{"key":"e_1_3_2_1_17_1","unstructured":"Ofir Nachum Mohammad Norouzi Kelvin Xu and Dale Schuurmans. 2017. Bridging the gap between value and policy based reinforcement learning. In Advances in Neural Information Processing Systems. 2775--2785. Ofir Nachum Mohammad Norouzi Kelvin Xu and Dale Schuurmans. 2017. Bridging the gap between value and policy based reinforcement learning. In Advances in Neural Information Processing Systems. 2775--2785."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICICTA.2008.49"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/710938"},{"volume-title":"Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark. In 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning. 254--261","author":"Riedmiller M.","key":"e_1_3_2_1_20_1","unstructured":"M. Riedmiller , J. Peters , and S. Schaal . 2007 . Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark. In 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning. 254--261 . M. Riedmiller, J. Peters, and S. Schaal. 2007. Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark. In 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning. 254--261."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0947-3580(98)70119-0"},{"volume-title":"Introduction to reinforcement learning","author":"Sutton Richard S","key":"e_1_3_2_1_22_1","unstructured":"Richard S Sutton and Andrew G Barto . 1998. Introduction to reinforcement learning . Vol. 135 . MIT press Cambridge . Richard S Sutton and Andrew G Barto. 1998. Introduction to reinforcement learning . Vol. 135. MIT press Cambridge."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIMSiM.2010.95"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of Learning, Inference and Control of Multi-Agent Systems (at NIPS 2016)","author":"der Pol Elise Van","year":"2016","unstructured":"Elise Van der Pol and Frans A Oliehoek . 2016 . Coordinated deep reinforcement learners for traffic light control . Proceedings of Learning, Inference and Control of Multi-Agent Systems (at NIPS 2016) (2016). Elise Van der Pol and Frans A Oliehoek. 2016. Coordinated deep reinforcement learners for traffic light control. Proceedings of Learning, Inference and Control of Multi-Agent Systems (at NIPS 2016) (2016)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the Seventeenth International Conference on Machine Learning. 1151--1158","author":"Wiering Marco","year":"2000","unstructured":"Marco Wiering . 2000 . Multi-agent reinforcement learning for traffic light control . In Proceedings of the Seventeenth International Conference on Machine Learning. 1151--1158 . Marco Wiering. 2000. Multi-agent reinforcement learning for traffic light control. In Proceedings of the Seventeenth International Conference on Machine Learning. 1151--1158."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3068287"}],"event":{"name":"KDD '19: The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Anchorage AK USA","acronym":"KDD '19"},"container-title":["Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3292500.3330988","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T06:44:11Z","timestamp":1673419451000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3292500.3330988"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,25]]},"references-count":27,"alternative-id":["10.1145\/3292500.3330988","10.1145\/3292500"],"URL":"https:\/\/doi.org\/10.1145\/3292500.3330988","relation":{},"subject":[],"published":{"date-parts":[[2019,7,25]]},"assertion":[{"value":"2019-07-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}