{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:32:48Z","timestamp":1750221168878,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,5,21]],"date-time":"2018-05-21T00:00:00Z","timestamp":1526860800000},"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":[[2018,5,21]]},"DOI":"10.1145\/3205326.3205346","type":"proceedings-article","created":{"date-parts":[[2018,5,16]],"date-time":"2018-05-16T11:57:40Z","timestamp":1526471860000},"page":"11-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Learning to Communicate via Supervised Attentional Message Processing"],"prefix":"10.1145","author":[{"given":"Zhaoqing","family":"Peng","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Libo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Software Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiejian","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,5,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473","author":"Bahdanau Dzmitry","year":"2014","unstructured":"Dzmitry Bahdanau , Kyunghyun Cho , and Yoshua Bengio . 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 ( 2014 ). Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)."},{"key":"e_1_3_2_1_2_1","volume-title":"Nando de Freitas, and Shimon Whiteson.","author":"Foerster Jakob","year":"2016","unstructured":"Jakob Foerster , Ioannis Alexandros Assael , Nando de Freitas, and Shimon Whiteson. 2016 . Learning to communicate with deep multi-agent reinforcement learning. In Advances in Neural Information Processing Systems . 2137--2145. Jakob Foerster, Ioannis Alexandros Assael, Nando de Freitas, and Shimon Whiteson. 2016. Learning to communicate with deep multi-agent reinforcement learning. In Advances in Neural Information Processing Systems. 2137--2145."},{"key":"e_1_3_2_1_3_1","volume-title":"Counterfactual multi-agent policy gradients. arXiv preprint arXiv:1705.08926","author":"Foerster Jakob","year":"2017","unstructured":"Jakob Foerster , Gregory Farquhar , Triantafyllos Afouras , Nantas Nardelli , and Shimon Whiteson . 2017. Counterfactual multi-agent policy gradients. arXiv preprint arXiv:1705.08926 ( 2017 ). Jakob Foerster, Gregory Farquhar, Triantafyllos Afouras, Nantas Nardelli, and Shimon Whiteson. 2017. Counterfactual multi-agent policy gradients. arXiv preprint arXiv:1705.08926 (2017)."},{"unstructured":"Jakob Foerster Nantas Nardelli Gregory Farquhar Philip Torr Pushmeet Kohli Shimon Whiteson etal 2017. Stabilising experience replay for deep multi-agent reinforcement learning. arXiv preprint arXiv:1702.08887 (2017).  Jakob Foerster Nantas Nardelli Gregory Farquhar Philip Torr Pushmeet Kohli Shimon Whiteson et al. 2017. Stabilising experience replay for deep multi-agent reinforcement learning. arXiv preprint arXiv:1702.08887 (2017).","key":"e_1_3_2_1_4_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"e_1_3_2_1_6_1","volume-title":"Grounded Semantic Networks for Learning Shared Communication Protocols. In International Conference on Machine Learning (Workshop).","author":"Hausknecht Matthew","year":"2016","unstructured":"Matthew Hausknecht and Peter Stone . 2016 . Grounded Semantic Networks for Learning Shared Communication Protocols. In International Conference on Machine Learning (Workshop). Matthew Hausknecht and Peter Stone. 2016. Grounded Semantic Networks for Learning Shared Communication Protocols. In International Conference on Machine Learning (Workshop)."},{"key":"e_1_3_2_1_7_1","volume-title":"Vain: Attentional multi-agent predictive modeling. In Advances in Neural Information Processing Systems. 2698--2708.","author":"Hoshen Yedid","year":"2017","unstructured":"Yedid Hoshen . 2017 . Vain: Attentional multi-agent predictive modeling. In Advances in Neural Information Processing Systems. 2698--2708. Yedid Hoshen. 2017. Vain: Attentional multi-agent predictive modeling. In Advances in Neural Information Processing Systems. 2698--2708."},{"key":"e_1_3_2_1_8_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling . 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 ( 2016 ). Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"unstructured":"Tejas D Kulkarni Karthik Narasimhan Ardavan Saeedi and Josh Tenenbaum. 2016. Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation. In Advances in neural information processing systems. 3675--3683.   Tejas D Kulkarni Karthik Narasimhan Ardavan Saeedi and Josh Tenenbaum. 2016. Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation. In Advances in neural information processing systems. 3675--3683.","key":"e_1_3_2_1_9_1"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems. International Foundation for Autonomous Agents and Multiagent Systems, 464--473","author":"Leibo Joel Z","year":"2017","unstructured":"Joel Z Leibo , Vinicius Zambaldi , Marc Lanctot , Janusz Marecki , and Thore Graepel . 2017 . Multi-agent reinforcement learning in sequential social dilemmas . In Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems. International Foundation for Autonomous Agents and Multiagent Systems, 464--473 . Joel Z Leibo, Vinicius Zambaldi, Marc Lanctot, Janusz Marecki, and Thore Graepel. 2017. Multi-agent reinforcement learning in sequential social dilemmas. In Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems. International Foundation for Autonomous Agents and Multiagent Systems, 464--473."},{"unstructured":"Hangyu Mao Yan Ni Zhibo Gong Weichen Ke Chao Ma Yang Xiao Yuan Wang Jiakang Wang Quanbin Wang Xiangyu Liu etal 2017. ACCNet: Actor-Coordinator-Critic Net for\" Learning-to-Communicate\" with Deep Multi-agent Reinforcement Learning. arXiv preprint arXiv:1706.03235 (2017).  Hangyu Mao Yan Ni Zhibo Gong Weichen Ke Chao Ma Yang Xiao Yuan Wang Jiakang Wang Quanbin Wang Xiangyu Liu et al. 2017. ACCNet: Actor-Coordinator-Critic Net for\" Learning-to-Communicate\" with Deep Multi-agent Reinforcement Learning. arXiv preprint arXiv:1706.03235 (2017).","key":"e_1_3_2_1_11_1"},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Machine Learning. 1928--1937","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih , Adria Puigdomenech Badia , Mehdi Mirza , Alex Graves , Timothy Lillicrap , Tim Harley , David Silver , and Koray Kavukcuoglu . 2016 . Asynchronous methods for deep reinforcement learning . In International Conference on Machine Learning. 1928--1937 . Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous methods for deep reinforcement learning. In International Conference on Machine Learning. 1928--1937."},{"doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A Rusu Joel Veness Marc G Bellemare Alex Graves Martin Riedmiller Andreas K Fidjeland Georg Ostrovski etal 2015. Human-level control through deep reinforcement learning. Nature 518 7540 (2015) 529.  Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A Rusu Joel Veness Marc G Bellemare Alex Graves Martin Riedmiller Andreas K Fidjeland Georg Ostrovski et al. 2015. Human-level control through deep reinforcement learning. Nature 518 7540 (2015) 529.","key":"e_1_3_2_1_13_1","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_14_1","volume-title":"Emergence of grounded compositional language in multi-agent populations. arXiv preprint arXiv:1703.04908","author":"Mordatch Igor","year":"2017","unstructured":"Igor Mordatch and Pieter Abbeel . 2017. Emergence of grounded compositional language in multi-agent populations. arXiv preprint arXiv:1703.04908 ( 2017 ). Igor Mordatch and Pieter Abbeel. 2017. Emergence of grounded compositional language in multi-agent populations. arXiv preprint arXiv:1703.04908 (2017)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1016\/j.procs.2014.08.103"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Machine Learning. arXiv preprint arXiv:1703","author":"Omidshafiei Shayegan","year":"2017","unstructured":"Shayegan Omidshafiei , Jason Pazis , Christopher Amato , Jonathan P How , and John Vian . 2017 . Deep Decentralized Multi-task Multi-Agent RL under Partial Observability , In International Conference on Machine Learning. arXiv preprint arXiv:1703 .06182, 2681--2690. Shayegan Omidshafiei, Jason Pazis, Christopher Amato, Jonathan P How, and John Vian. 2017. Deep Decentralized Multi-task Multi-Agent RL under Partial Observability, In International Conference on Machine Learning. arXiv preprint arXiv:1703.06182, 2681--2690."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.1007\/s10458-005-2631-2"},{"key":"e_1_3_2_1_18_1","volume-title":"Multiagent Bidirectionally-Coordinated nets for learning to play StarCraft combat games. arXiv preprint arXiv:1703.10069","author":"Peng Peng","year":"2017","unstructured":"Peng Peng , Quan Yuan , Ying Wen , Yaodong Yang , Zhenkun Tang , Haitao Long , and Jun Wang . 2017. Multiagent Bidirectionally-Coordinated nets for learning to play StarCraft combat games. arXiv preprint arXiv:1703.10069 ( 2017 ). Peng Peng, Quan Yuan, Ying Wen, Yaodong Yang, Zhenkun Tang, Haitao Long, and Jun Wang. 2017. Multiagent Bidirectionally-Coordinated nets for learning to play StarCraft combat games. arXiv preprint arXiv:1703.10069 (2017)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1109\/GCCE.2015.7398644"},{"unstructured":"Sainbayar Sukhbaatar Rob Fergus etal 2016. Learning multiagent communication with backpropagation. In Advances in Neural Information Processing Systems. 2244--2252.   Sainbayar Sukhbaatar Rob Fergus et al. 2016. Learning multiagent communication with backpropagation. In Advances in Neural Information Processing Systems. 2244--2252.","key":"e_1_3_2_1_20_1"},{"unstructured":"Richard S Sutton David A McAllester Satinder P Singh and Yishay Mansour. 2000. Policy gradient methods for reinforcement learning with function approximation. In Advances in neural information processing systems. 1057--1063.   Richard S Sutton David A McAllester Satinder P Singh and Yishay Mansour. 2000. Policy gradient methods for reinforcement learning with function approximation. In Advances in neural information processing systems. 1057--1063.","key":"e_1_3_2_1_21_1"}],"event":{"sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques","Chinese Academy of Sciences"],"acronym":"CASA 2018","name":"CASA 2018: 31st International Conference on Computer Animation and Social Agents","location":"Beijing China"},"container-title":["Proceedings of the 31st International Conference on Computer Animation and Social Agents"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3205326.3205346","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3205326.3205346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:08:55Z","timestamp":1750208935000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3205326.3205346"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,21]]},"references-count":21,"alternative-id":["10.1145\/3205326.3205346","10.1145\/3205326"],"URL":"https:\/\/doi.org\/10.1145\/3205326.3205346","relation":{},"subject":[],"published":{"date-parts":[[2018,5,21]]},"assertion":[{"value":"2018-05-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}