{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T00:11:34Z","timestamp":1774051894299,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,12,28]],"date-time":"2021-12-28T00:00:00Z","timestamp":1640649600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"MOST","award":["108-2221-E-005-021-MY3"],"award-info":[{"award-number":["108-2221-E-005-021-MY3"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,12,28]]},"DOI":"10.1145\/3491396.3506544","type":"proceedings-article","created":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T23:54:52Z","timestamp":1641599692000},"page":"28-33","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Agent Reinforcement Learning based on Two-Step Neighborhood Experience for Traffic Light Control"],"prefix":"10.1145","author":[{"given":"Yu-Chen","family":"Luo","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"}]},{"given":"Chun-Wei","family":"Tsai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"}]}],"member":"320","published-online":{"date-parts":[[2022,1,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1057\/jors.1963.61"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2613997"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2011.04.011"},{"key":"e_1_3_2_1_4_1","first-page":"1151","article-title":"Multi-agent reinforcement leraning for traffic light control","author":"Wiering M.","year":"2000","unstructured":"M. Wiering , \" Multi-agent reinforcement leraning for traffic light control ,\" in Proceedings of International Conference on Machine Learning , 2000 , pp. 1151 -- 1158 . M. Wiering, \"Multi-agent reinforcement leraning for traffic light control,\" in Proceedings of International Conference on Machine Learning, 2000, pp. 1151--1158.","journal-title":"Proceedings of International Conference on Machine Learning"},{"issue":"3","key":"e_1_3_2_1_5_1","first-page":"4","article-title":"Q-learning","volume":"8","author":"Watkins C. J.","year":"1992","unstructured":"C. J. Watkins and P. Dayan , \" Q-learning ,\" Machine Learning , vol. 8 , no. 3 -- 4 , pp. 279--292, 1992 . C. J. Watkins and P. Dayan, \"Q-learning,\" Machine Learning, vol. 8, no. 3--4, pp. 279--292, 1992.","journal-title":"Machine Learning"},{"key":"e_1_3_2_1_6_1","volume-title":"Playing atari with deep reinforcement learning,\" arXiv preprint arXiv:1312.5602","author":"Mnih V.","year":"2013","unstructured":"V. Mnih , K. Kavukcuoglu , D. Silver , A. Graves , I. Antonoglou , D. Wierstra , and M. Riedmiller , \" Playing atari with deep reinforcement learning,\" arXiv preprint arXiv:1312.5602 , 2013 . V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller, \"Playing atari with deep reinforcement learning,\" arXiv preprint arXiv:1312.5602, 2013."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"e_1_3_2_1_8_1","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent vs. cooperative agents","author":"Tan M.","year":"1993","unstructured":"M. Tan , \" Multi-agent reinforcement learning: Independent vs. cooperative agents ,\" in Proceedings of International Conference on Machine Learning , 1993 , pp. 330 -- 337 . M. Tan, \"Multi-agent reinforcement learning: Independent vs. cooperative agents,\" in Proceedings of International Conference on Machine Learning, 1993, pp. 330--337.","journal-title":"Proceedings of International Conference on Machine Learning"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0070"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1080\/15472450.2017.1387546"},{"key":"e_1_3_2_1_11_1","first-page":"129","article-title":"Multiagent traffic management: Opportunities for multiagent learning","author":"Dresner K.","year":"2005","unstructured":"K. Dresner and P. Stone , \" Multiagent traffic management: Opportunities for multiagent learning ,\" in Proceedings of International Workshop on Learning and Adaption in Multi-Agent Systems , 2005 , pp. 129 -- 138 . K. Dresner and P. Stone, \"Multiagent traffic management: Opportunities for multiagent learning,\" in Proceedings of International Workshop on Learning and Adaption in Multi-Agent Systems, 2005, pp. 129--138.","journal-title":"Proceedings of International Workshop on Learning and Adaption in Multi-Agent Systems"},{"key":"e_1_3_2_1_12_1","first-page":"1","article-title":"Learning to schedule communication in multi-agent reinforcement learning","author":"Kim D.","year":"2018","unstructured":"D. Kim , S. Moon , D. Hostallero , W. J. Kang , T. Lee , K. Son , and Y. Yi , \" Learning to schedule communication in multi-agent reinforcement learning ,\" in Proceedings of International Conference on Learning Representations , 2018 , pp. 1 -- 17 . D. Kim, S. Moon, D. Hostallero, W. J. Kang, T. Lee, K. Son, and Y. Yi, \"Learning to schedule communication in multi-agent reinforcement learning,\" in Proceedings of International Conference on Learning Representations, 2018, pp. 1--17.","journal-title":"Proceedings of International Conference on Learning Representations"},{"key":"e_1_3_2_1_13_1","first-page":"1","article-title":"Multi-agent reinforcement learning for networked system control","author":"Chu T.","year":"2019","unstructured":"T. Chu , S. Chinchali , and S. Katti , \" Multi-agent reinforcement learning for networked system control ,\" in Proceedings of International Conference on Learning Representations , 2019 , pp. 1 -- 17 . T. Chu, S. Chinchali, and S. Katti, \"Multi-agent reinforcement learning for networked system control,\" in Proceedings of International Conference on Learning Representations, 2019, pp. 1--17.","journal-title":"Proceedings of International Conference on Learning Representations"},{"issue":"5","key":"e_1_3_2_1_14_1","first-page":"679","article-title":"A markovian decision process","volume":"6","author":"Bellman R.","year":"1957","unstructured":"R. Bellman , \" A markovian decision process ,\" Journal of Mathematics and Mechanics , vol. 6 , no. 5 , pp. 679 -- 684 , 1957 . R. Bellman, \"A markovian decision process,\" Journal of Mathematics and Mechanics, vol. 6, no. 5, pp. 679--684, 1957.","journal-title":"Journal of Mathematics and Mechanics"},{"key":"e_1_3_2_1_15_1","volume-title":"Intelligent traffic light control,\" Utrecht University: Information and Computing Sciences","author":"Wiering M.","year":"2004","unstructured":"M. Wiering , J. v. Veenen , J. Vreeken , and A. Koopman , \" Intelligent traffic light control,\" Utrecht University: Information and Computing Sciences , Padualaan, Utrecht, The Netherlands, Tech. Rep ., 2004 . M. Wiering, J. v. Veenen, J. Vreeken, and A. Koopman, \"Intelligent traffic light control,\" Utrecht University: Information and Computing Sciences, Padualaan, Utrecht, The Netherlands, Tech. Rep., 2004."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7508798"},{"key":"e_1_3_2_1_17_1","first-page":"1","article-title":"Coordinated deep reinforcement learners for traffic light control","author":"Van der Pol E.","year":"2016","unstructured":"E. Van der Pol and F. A. Oliehoek , \" Coordinated deep reinforcement learners for traffic light control ,\" in Proceedings of International Conference on Neural Information Processing Systems , 2016 , pp. 1 -- 8 . E. Van der Pol and F. A. Oliehoek, \"Coordinated deep reinforcement learners for traffic light control,\" in Proceedings of International Conference on Neural Information Processing Systems, 2016, pp. 1--8.","journal-title":"Proceedings of International Conference on Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","volume-title":"Using a deep reinforcement learning agent for traffic signal control,\" arXiv preprint arXiv:1611.01142","author":"Genders W.","year":"2016","unstructured":"W. Genders and S. Razavi , \" Using a deep reinforcement learning agent for traffic signal control,\" arXiv preprint arXiv:1611.01142 , 2016 . W. Genders and S. Razavi, \"Using a deep reinforcement learning agent for traffic signal control,\" arXiv preprint arXiv:1611.01142, 2016."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.04.008"},{"issue":"2","key":"e_1_3_2_1_20_1","first-page":"412","article-title":"Reinforcement learning with function approximation for traffic signal control","volume":"12","author":"Prashanth L.","year":"2010","unstructured":"L. Prashanth and S. Bhatnagar , \" Reinforcement learning with function approximation for traffic signal control ,\" IEEE Transactions on Intelligent Transportation Systems , vol. 12 , no. 2 , pp. 412 -- 421 , 2010 . L. Prashanth and S. Bhatnagar, \"Reinforcement learning with function approximation for traffic signal control,\" IEEE Transactions on Intelligent Transportation Systems, vol. 12, no. 2, pp. 412--421, 2010.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"e_1_3_2_1_22_1","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"Foerster J. N.","year":"2016","unstructured":"J. N. Foerster , Y. M. Assael , N. de Freitas , and S. Whiteson , \" Learning to communicate with deep multi-agent reinforcement learning ,\" in Proceedings of International Conference on Neural Information Processing Systems , 2016 , pp. 2145 -- 2153 . J. N. Foerster, Y. M. Assael, N. de Freitas, and S. Whiteson, \"Learning to communicate with deep multi-agent reinforcement learning,\" in Proceedings of International Conference on Neural Information Processing Systems, 2016, pp. 2145--2153.","journal-title":"Proceedings of International Conference on Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","first-page":"2252","article-title":"Learning multiagent communication with backpropagation","author":"Sukhbaatar S.","year":"2016","unstructured":"S. Sukhbaatar , a. szlam, and R. Fergus , \" Learning multiagent communication with backpropagation ,\" in Proceedings of Advances in Neural Information Processing Systems , 2016 , pp. 2252 -- 2260 . S. Sukhbaatar, a. szlam, and R. Fergus, \"Learning multiagent communication with backpropagation,\" in Proceedings of Advances in Neural Information Processing Systems, 2016, pp. 2252--2260.","journal-title":"Proceedings of Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvjsf522"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10058-007-0029-0"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.2307\/2297517"},{"key":"e_1_3_2_1_27_1","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih V.","year":"2016","unstructured":"V. Mnih , A. P. Badia , M. Mirza , A. Graves , T. Lillicrap , T. Harley , D. Silver , and K. Kavukcuoglu , \" Asynchronous methods for deep reinforcement learning ,\" in Proceedings of International Conference on Machine Learning , 2016 , pp. 1928 -- 1937 . V. Mnih, A. P. Badia, M. Mirza, A. Graves, T. Lillicrap, T. Harley, D. Silver, and K. Kavukcuoglu, \"Asynchronous methods for deep reinforcement learning,\" in Proceedings of International Conference on Machine Learning, 2016, pp. 1928--1937.","journal-title":"Proceedings of International Conference on Machine Learning"}],"event":{"name":"ACM ICEA '21: 2021 ACM International Conference on Intelligent Computing and its Emerging Applications","location":"Jinan China","acronym":"ACM ICEA '21","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"]},"container-title":["Proceedings of the 2021 ACM International Conference on Intelligent Computing and its Emerging Applications"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3491396.3506544","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3491396.3506544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:48Z","timestamp":1750188648000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3491396.3506544"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,28]]},"references-count":27,"alternative-id":["10.1145\/3491396.3506544","10.1145\/3491396"],"URL":"https:\/\/doi.org\/10.1145\/3491396.3506544","relation":{},"subject":[],"published":{"date-parts":[[2021,12,28]]},"assertion":[{"value":"2022-01-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}