{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T08:14:03Z","timestamp":1782980043039,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,1,7]],"date-time":"2020-01-07T00:00:00Z","timestamp":1578355200000},"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":[[2020,1,7]]},"DOI":"10.1145\/3378184.3378194","type":"proceedings-article","created":{"date-parts":[[2020,2,18]],"date-time":"2020-02-18T03:31:51Z","timestamp":1581996711000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["deep-MARLIN"],"prefix":"10.1145","author":[{"given":"Robin","family":"Kl\u00f6ckner","sequence":"first","affiliation":[{"name":"Goethe University, Frankfurt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Klose","sequence":"additional","affiliation":[{"name":"Goethe University, Frankfurt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,2,17]]},"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.2009.0070"},{"key":"e_1_3_2_1_3_1","unstructured":"T. Ba\u015far and G.J. Olsder. 1982. Dynamic Noncooperative Game Theory. Academic Press Inc.  T. Ba\u015far and G.J. Olsder. 1982. Dynamic Noncooperative Game Theory. Academic Press Inc."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"e_1_3_2_1_5_1","unstructured":"T. Chu J. Wang L. Codec\u00e0 and Z. Li. 2019. Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control. IEEE Transactions on Intelligent Transportation Systems (2019).  T. Chu J. Wang L. Codec\u00e0 and Z. Li. 2019. Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control. IEEE Transactions on Intelligent Transportation Systems (2019)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/15472450.2013.810991"},{"key":"e_1_3_2_1_8_1","unstructured":"J. Gao Y. Shen J. Liu M. Ito and Shiratori N. 2017. Adaptive Traffic Signal Control: Deep Reinforcement Learning Algorithm with Experience Replay and Target Network. arXiv:1705.02755 (2017).  J. Gao Y. Shen J. Liu M. Ito and Shiratori N. 2017. Adaptive Traffic Signal Control: Deep Reinforcement Learning Algorithm with Experience Replay and Target Network. arXiv:1705.02755 (2017)."},{"key":"e_1_3_2_1_9_1","volume-title":"INRIX 2018 Global Traffic Scorecard. http:\/\/inrix.com\/scorecard\/","author":"INRIX.","year":"2019"},{"key":"e_1_3_2_1_10_1","volume-title":"Adam: A Method for Stochastic Optimization. arXiv:1412.6980","author":"Kingma D. P.","year":"2014"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87479-9_61"},{"key":"e_1_3_2_1_12_1","unstructured":"P. Lillicrap T. J. Hunt J. A. Pritzel N. Heess T. Erez Y. Tassa D. Silver and D. Wierstra. 2015. Continuous Control with Deep Reinforcement Learning. arXiv:1509.02971 (2015).  P. Lillicrap T. J. Hunt J. A. Pritzel N. Heess T. Erez Y. Tassa D. Silver and D. Wierstra. 2015. Continuous Control with Deep Reinforcement Learning. arXiv:1509.02971 (2015)."},{"key":"e_1_3_2_1_13_1","unstructured":"L.-J. Lin. 1993. Reinforcement Learning for Robots Using Neural Networks. Dissertation (Carnegie Mellon University Pittsburgh) (1993).  L.-J. Lin. 1993. Reinforcement Learning for Robots Using Neural Networks. Dissertation (Carnegie Mellon University Pittsburgh) (1993)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 21st IEEE International Conference on Intelligent Transportation Systems","author":"Lopez P. A.","year":"2018"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 30th International Conference on Machine Learning","author":"Maas A. L.","year":"2013"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 33rd International Conference on Machine Learning","author":"Mnih V.","year":"2016"},{"key":"e_1_3_2_1_18_1","unstructured":"V. Mnih K. Kavukcuoglu D. Silver A. Graves I. Antonoglou D. Wierstra and M. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. arXiv:1312.5602 (2013).  V. Mnih K. Kavukcuoglu D. Silver A. Graves I. Antonoglou D. Wierstra and M. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"V. Mnih K. Kavukcuoglu D. Silver A. A. Rusu J. Veness M. G. Bellemare A. Graves M. Riedmiller A. K. Fidjeland G. Ostrovski S. Petersen C. Beattie A. Sadik I. Antonoglou H. King D. Kumaran D. Wierstra S. Legg and D. Hassabis. 2015. Human-level Control through Deep Reinforcement Learning. Nature 518 7540 (2015) 529--533.  V. Mnih K. Kavukcuoglu D. Silver A. A. Rusu J. Veness M. G. Bellemare A. Graves M. Riedmiller A. K. Fidjeland G. Ostrovski S. Petersen C. Beattie A. Sadik I. Antonoglou H. King D. Kumaran D. Wierstra S. Legg and D. Hassabis. 2015. Human-level Control through Deep Reinforcement Learning. Nature 518 7540 (2015) 529--533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 20th National Conference on Artificial Intelligence","author":"Nair R.","year":"2005"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 2nd International Conference on Multiagent Systems","author":"Ono N.","year":"1996"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"e_1_3_2_1_23_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R. S.","year":"2018"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"e_1_3_2_1_25_1","unstructured":"C. J. C. H. Watkins. 1989. Learning from Delayed Rewards. Dissertation (King's College London) (1989).  C. J. C. H. Watkins. 1989. Learning from Delayed Rewards. Dissertation (King's College London) (1989)."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 17th International Conference on Machine Learning","author":"Wiering M. A.","year":"2000"}],"event":{"name":"APPIS 2020: 3rd International Conference on Applications of Intelligent Systems","location":"Las Palmas de Gran Canaria Spain","acronym":"APPIS 2020"},"container-title":["Proceedings of the 3rd International Conference on Applications of Intelligent Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3378184.3378194","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3378184.3378194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:24:01Z","timestamp":1750202641000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3378184.3378194"}},"subtitle":["Using Deep Multi-Agent Reinforcement Learning for Adaptive Traffic Light Control"],"short-title":[],"issued":{"date-parts":[[2020,1,7]]},"references-count":26,"alternative-id":["10.1145\/3378184.3378194","10.1145\/3378184"],"URL":"https:\/\/doi.org\/10.1145\/3378184.3378194","relation":{},"subject":[],"published":{"date-parts":[[2020,1,7]]},"assertion":[{"value":"2020-02-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}