{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T01:06:23Z","timestamp":1767834383817,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,4,8]],"date-time":"2019-04-08T00:00:00Z","timestamp":1554681600000},"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":[[2019,4,8]]},"DOI":"10.1145\/3297280.3297371","type":"proceedings-article","created":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T12:18:47Z","timestamp":1556713127000},"page":"922-929","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Hierarchical multi-agent deep reinforcement learning to develop long-term coordination"],"prefix":"10.1145","author":[{"given":"Marie","family":"Ossenkopf","sequence":"first","affiliation":[{"name":"University of Kassel, Kassel, Hessen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mackenzie","family":"Jorgensen","sequence":"additional","affiliation":[{"name":"Villanova University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kurt","family":"Geihs","sequence":"additional","affiliation":[{"name":"University of Kassel, Kassel, Hessen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,4,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-008-9046-9"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157336"},{"key":"e_1_3_2_1_4_1","volume-title":"Deep Recurrent Q-Learning for Partially Observable MDPs. In 2015 AAAI Fall Symposium Series.","author":"Hausknecht Matthew","year":"2015","unstructured":"Matthew Hausknecht and Peter Stone. 2015. Deep Recurrent Q-Learning for Partially Observable MDPs. In 2015 AAAI Fall Symposium Series."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218488598000094"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_7_1","volume-title":"Learning to play guess who? and inventing a grounded language as a consequence. (11","author":"Jorge Emilio","year":"2016","unstructured":"Emilio Jorge, Mikael K\u00e5geb\u00e4ck, Fredrik D Johansson, and Emil Gustavsson. 2016. Learning to play guess who? and inventing a grounded language as a consequence. (11 2016)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","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.","DOI":"10.5555\/3157382.3157509"},{"key":"e_1_3_2_1_9_1","unstructured":"Saurabh Kumar Pararth Shah Dilek Hakkani-Tur and Larry Heck. 2017. Federated Control with Hierarchical Multi-Agent Deep Reinforcement Learning. (2017)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Mike Lewis Denis Yarats Yann Dauphin Devi Parikh and Dhruv Batra. 2017. Deal or No Deal? End-to-End Learning of Negotiation Dialogues. (2017) 2443--2453.","DOI":"10.18653\/v1\/D17-1259"},{"key":"e_1_3_2_1_11_1","volume-title":"Playing atari with deep reinforcement learning. (12","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. (12 2013)."},{"key":"e_1_3_2_1_12_1","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 et al. 2015. Human-level control through deep reinforcement learning. Nature 518 7540 (2015) 529.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_13_1","volume-title":"Multiagent Bidirectionally-Coordinated Nets for Learning to Play StarCraft Combat Games. (03","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. (03 2017)."},{"key":"e_1_3_2_1_15_1","volume-title":"Is imitation learning the route to humanoid robots? Trends in cognitive sciences 3, 6","author":"Schaal Stefan","year":"1999","unstructured":"Stefan Schaal. 1999. Is imitation learning the route to humanoid robots? Trends in cognitive sciences 3, 6 (1999), 233--242."},{"key":"e_1_3_2_1_16_1","volume-title":"Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al.","author":"Silver David","year":"2016","unstructured":"David Silver, Aja Huang, Chris J Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al. 2016. Mastering the game of Go with deep neural networks and tree search. nature 529, 7587 (2016), 484."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Sainbayar Sukhbaatar Rob Fergus et al. 2016. Learning multiagent communication with backpropagation. In Advances in Neural Information Processing Systems. 2244--2252.","DOI":"10.5555\/3157096.3157348"},{"key":"e_1_3_2_1_18_1","volume-title":"Evolution of communication in artificial systems. Artificial Life II","author":"Werner GM","year":"1991","unstructured":"GM Werner and MG Dyer. 1991. Evolution of communication in artificial systems. Artificial Life II, Addison-Wesley, Redwood City, CA (1991), 659--682."}],"event":{"name":"SAC '19: The 34th ACM\/SIGAPP Symposium on Applied Computing","location":"Limassol Cyprus","acronym":"SAC '19","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"]},"container-title":["Proceedings of the 34th ACM\/SIGAPP Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297280.3297371","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297280.3297371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:02:15Z","timestamp":1750208535000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297280.3297371"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,8]]},"references-count":17,"alternative-id":["10.1145\/3297280.3297371","10.1145\/3297280"],"URL":"https:\/\/doi.org\/10.1145\/3297280.3297371","relation":{},"subject":[],"published":{"date-parts":[[2019,4,8]]},"assertion":[{"value":"2019-04-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}