{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T21:57:39Z","timestamp":1730325459431,"version":"3.28.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2018497"],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836011"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539480","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:41Z","timestamp":1660331201000},"page":"1899-1909","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Stabilizing Voltage in Power Distribution Networks via Multi-Agent Reinforcement Learning with Transformer"],"prefix":"10.1145","author":[{"given":"Minrui","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Mingxiao","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"volume-title":"Reducing overestimation bias in multi-agent domains using double centralized critics. arXiv preprint arXiv:1910.01465","year":"2019","author":"Ackermann Johannes","key":"e_1_3_2_2_1_1","unstructured":"Johannes Ackermann, Volker Gabler, Takayuki Osa, and Masashi Sugiyama. 2019. Reducing overestimation bias in multi-agent domains using double centralized critics. arXiv preprint arXiv:1910.01465 (2019)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/MPER.1989.4310642"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.3000652"},{"volume-title":"Distributed voltage regulation of active distribution system based on enhanced multi-agent deep reinforcement learning. arXiv preprint arXiv:2006.00546","year":"2020","author":"Cao Di","key":"e_1_3_2_2_4_1","unstructured":"Di Cao, Junbo Zhao, Weihao Hu, Fei Ding, Qi Huang, and Zhe Chen. 2020. Distributed voltage regulation of active distribution system based on enhanced multi-agent deep reinforcement learning. arXiv preprint arXiv:2006.00546 (2020)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3072251"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"volume-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555","year":"2014","author":"Chung Junyoung","key":"e_1_3_2_2_7_1","unstructured":"Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)."},{"volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","year":"2018","author":"Devlin Jacob","key":"e_1_3_2_2_8_1","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"volume-title":"International Conference on Learning Representations.","year":"2021","author":"Dosovitskiy Alexey","key":"e_1_3_2_2_9_1","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"volume-title":"Proceedings of the IEEE Conference on Decision and Control. IEEE, 2313--2318","year":"2013","author":"Gan Lingwen","key":"e_1_3_2_2_11_1","unstructured":"Lingwen Gan, Na Li, Ufuk Topcu, and Steven H Low. 2013. Optimal power flow in tree networks. In Proceedings of the IEEE Conference on Decision and Control. IEEE, 2313--2318."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"e_1_3_2_2_13_1","unstructured":"Tuomas Haarnoja Aurick Zhou Kristian Hartikainen George Tucker Sehoon Ha Jie Tan Vikash Kumar Henry Zhu Abhishek Gupta Pieter Abbeel et al. 2018. Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)."},{"volume-title":"International Conference on Learning Representations.","year":"2021","author":"Hu Siyi","key":"e_1_3_2_2_14_1","unstructured":"Siyi Hu, Fengda Zhu, Xiaojun Chang, and Xiaodan Liang. 2021. UPDeT: Universal Multi-agent RL via Policy Decoupling with Transformers. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2007.10.002"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3060027"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.11.054"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"volume-title":"Multi-agent actor-critic for mixed cooperative-competitive environments. arXiv preprint arXiv:1706.02275","year":"2017","author":"Lowe Ryan","key":"e_1_3_2_2_19_1","unstructured":"Ryan Lowe, Yi Wu, Aviv Tamar, Jean Harb, Pieter Abbeel, and Igor Mordatch. 2017. Multi-agent actor-critic for mixed cooperative-competitive environments. arXiv preprint arXiv:1706.02275 (2017)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/en13123290"},{"volume-title":"A concise introduction to decentralized POMDPs","author":"Oliehoek Frans A","key":"e_1_3_2_2_21_1","unstructured":"Frans A Oliehoek and Christopher Amato. 2016. A concise introduction to decentralized POMDPs. Springer."},{"volume-title":"Proceedings of the International Conference on Machine Learning. PMLR, 7487--7498","year":"2020","author":"Parisotto Emilio","key":"e_1_3_2_2_22_1","unstructured":"Emilio Parisotto, Francis Song, Jack Rae, Razvan Pascanu, Caglar Gulcehre, Siddhant Jayakumar, Max Jaderberg, Raphael Lopez Kaufman, Aidan Clark, Seb Noury, et al. 2020. Stabilizing transformers for reinforcement learning. In Proceedings of the International Conference on Machine Learning. PMLR, 7487--7498."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2829021"},{"key":"e_1_3_2_2_24_1","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman Tijmen","year":"2012","unstructured":"Tijmen Tieleman, Geoffrey Hinton, et al. 2012. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning 4, 2 (2012), 26--31.","journal-title":"COURSERA: Neural Networks for Machine Learning"},{"volume-title":"Proceedings of the Advances in Neural Information Processing Systems. 5998--6008","year":"2017","author":"Vaswani Ashish","key":"e_1_3_2_2_25_1","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems. 5998--6008."},{"key":"e_1_3_2_2_26_1","first-page":"3271","article-title":"Multi-agent reinforcement learning for active voltage control on power distribution networks","volume":"34","author":"Wang Jianhong","year":"2021","unstructured":"Jianhong Wang, Wangkun Xu, Yunjie Gu, Wenbin Song, and Tim C Green. 2021. Multi-agent reinforcement learning for active voltage control on power distribution networks. Advances in Neural Information Processing Systems 34 (2021), 3271--3284.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.2990179"},{"volume-title":"Hierarchical RNNs-Based transformers MADDPG for mixed cooperative-competitive environments. Journal of Intelligent & Fuzzy Systems Preprint","year":"2021","author":"Wei Xiaolong","key":"e_1_3_2_2_28_1","unstructured":"Xiaolong Wei, Xianglin Huang, LiFang Yang, Gang Cao, Zhulin Tao, Bing Wang, and Jing An. 2021. Hierarchical RNNs-Based transformers MADDPG for mixed cooperative-competitive environments. Journal of Intelligent & Fuzzy Systems Preprint (2021), 1--12."},{"volume-title":"International Conference on Learning Representations.","year":"2020","author":"Yoon Deunsol","key":"e_1_3_2_2_29_1","unstructured":"Deunsol Yoon, Sunghoon Hong, Byung-Jun Lee, and Kee-Eung Kim. 2020. Winning the L2RPN challenge: Power grid management via semi-markov afterstate actor-critic. In International Conference on Learning Representations."},{"volume-title":"The surprising effectiveness of mappo in cooperative, multi-agent games. arXiv preprint arXiv:2103.01955","year":"2021","author":"Yu Chao","key":"e_1_3_2_2_30_1","unstructured":"Chao Yu, Akash Velu, Eugene Vinitsky, Yu Wang, Alexandre Bayen, and Yi Wu. 2021. The surprising effectiveness of mappo in cooperative, multi-agent games. arXiv preprint arXiv:2103.01955 (2021)."}],"event":{"name":"KDD '22: The 28th 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":"Washington DC USA","acronym":"KDD '22"},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T00:08:30Z","timestamp":1723680510000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539480"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":30,"alternative-id":["10.1145\/3534678.3539480","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539480","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}