{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:24:42Z","timestamp":1750220682585,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,12,24]],"date-time":"2020-12-24T00:00:00Z","timestamp":1608768000000},"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":[[2020,12,24]]},"DOI":"10.1145\/3446132.3446137","type":"proceedings-article","created":{"date-parts":[[2021,3,10]],"date-time":"2021-03-10T00:15:23Z","timestamp":1615335323000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Coordinating Multi-Agent Deep Reinforcement Learning in Wargame"],"prefix":"10.1145","author":[{"given":"Yanghui","family":"Fu","sequence":"first","affiliation":[{"name":"National University of Defense Technology, China"}]},{"given":"Xingxing","family":"Liang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}]},{"given":"Yang","family":"Ma","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}]},{"given":"Kuihua","family":"Huang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}]},{"given":"Yan","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}]}],"member":"320","published-online":{"date-parts":[[2021,3,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"e_1_3_2_1_4_1","volume-title":"Dota 2 with Large Scale Deep Reinforcement Learning[J]. arXiv: Learning","author":"Openai C","year":"2019","unstructured":"Openai , Berner C , Brockman G , Dota 2 with Large Scale Deep Reinforcement Learning[J]. arXiv: Learning , 2019 . Openai, Berner C, Brockman G, Dota 2 with Large Scale Deep Reinforcement Learning[J]. arXiv: Learning, 2019."},{"key":"e_1_3_2_1_5_1","volume-title":"ImageNet Classification with Deep Convolutional Neural Networks[C]. neural information processing systems","author":"Krizhevsky A","year":"2012","unstructured":"Krizhevsky A , Sutskever I , Hinton G E , ImageNet Classification with Deep Convolutional Neural Networks[C]. neural information processing systems , 2012 : 1097-1105. Krizhevsky A, Sutskever I, Hinton G E, ImageNet Classification with Deep Convolutional Neural Networks[C]. neural information processing systems, 2012: 1097-1105."},{"key":"e_1_3_2_1_6_1","volume-title":"The Application of AlphaZero to wargame[C]. australasian joint conference on artificial intelligence","author":"Moy G","year":"2019","unstructured":"Moy G , Shekh S. The Application of AlphaZero to wargame[C]. australasian joint conference on artificial intelligence , 2019 : 3-14. Moy G, Shekh S. The Application of AlphaZero to wargame[C]. australasian joint conference on artificial intelligence, 2019: 3-14."},{"issue":"4","key":"e_1_3_2_1_7_1","first-page":"948","article-title":"Algorithm based on Attention-based Value Function and Autoregressive Environment Model","volume":"2020","author":"Liang XX","unstructured":"Liang XX , Feng YH , Huang JC, A Novel Deep Reinforcement Learning Algorithm based on Attention-based Value Function and Autoregressive Environment Model . Ruan Jian Xue Bao\/Journal of Software , 2020 ( 4 ): 948 - 966 . (in Chinese). Liang XX, Feng YH, Huang JC, A Novel Deep Reinforcement Learning Algorithm based on Attention-based Value Function and Autoregressive Environment Model. Ruan Jian Xue Bao\/Journal of Software, 2020(4):948-966. (in Chinese).","journal-title":"Ruan Jian Xue Bao\/Journal of Software"},{"key":"e_1_3_2_1_8_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R. S.","year":"2017","unstructured":"Sutton , R. S. and Barto , A. G . Reinforcement Learning: An Introduction ( 2 nd Edition, inpreparation). MIT Press , 2017 . Sutton, R. S. and Barto, A. G. Reinforcement Learning: An Introduction (2nd Edition, inpreparation). MIT Press, 2017.","edition":"2"},{"key":"e_1_3_2_1_9_1","volume-title":"Deep Multi-Agent Reinforcement Learning: A Survey[J\/OL]. Acta Automatica Sinica, https:\/\/doi.org\/10.16383\/j.aas.c180372.[10]Ian Editor","author":"Liang XX","year":"2018","unstructured":"Liang XX , Feng YF , Ma Y , Deep Multi-Agent Reinforcement Learning: A Survey[J\/OL]. Acta Automatica Sinica, https:\/\/doi.org\/10.16383\/j.aas.c180372.[10]Ian Editor (Ed.). 2018 . The title of book two (2nd. ed.). University of XXX Press , City, Chapter 100. DOI: http:\/\/dx.doi.org\/10.1000\/0-000-00000-0. 10.16383\/j.aas.c180372.[10]Ian Liang XX, Feng YF, Ma Y, Deep Multi-Agent Reinforcement Learning: A Survey[J\/OL]. Acta Automatica Sinica, https:\/\/doi.org\/10.16383\/j.aas.c180372.[10]Ian Editor (Ed.). 2018. The title of book two (2nd. ed.). University of XXX Press, City, Chapter 100. DOI: http:\/\/dx.doi.org\/10.1000\/0-000-00000-0."},{"key":"e_1_3_2_1_10_1","first-page":"60","article-title":"Curriculum learning","volume":"2009","author":"Bengio Y.","unstructured":"[ Bengio , Y. & Louradour , J\u00e9r\u00f4me & Collobert, Ronan & Weston, Jason . Curriculum learning . Journal of the American Podiatry Association. 2009 : 60 . 6. 10.1145\/1553374.1553380. [Bengio, Y. & Louradour, J\u00e9r\u00f4me & Collobert, Ronan & Weston, Jason. Curriculum learning. Journal of the American Podiatry Association. 2009: 60. 6. 10.1145\/1553374.1553380.","journal-title":"Journal of the American Podiatry Association."},{"key":"e_1_3_2_1_11_1","volume-title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning.[J]. arXiv: Artificial Intelligence","author":"Sunehag P","year":"2017","unstructured":"Sunehag P , Lever G , Gruslys A , Value-Decomposition Networks For Cooperative Multi-Agent Learning.[J]. arXiv: Artificial Intelligence , 2017 . Sunehag P, Lever G, Gruslys A, Value-Decomposition Networks For Cooperative Multi-Agent Learning.[J]. arXiv: Artificial Intelligence, 2017."},{"key":"e_1_3_2_1_12_1","volume-title":"Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games[C]. computational intelligence and games","author":"Andersen P","year":"2018","unstructured":"Andersen P , Goodwin M , Granmo O , Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games[C]. computational intelligence and games , 2018 : 1-8. Andersen P, Goodwin M, Granmo O, Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games[C]. computational intelligence and games, 2018: 1-8."}],"event":{"name":"ACAI 2020: 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","acronym":"ACAI 2020","location":"Sanya China"},"container-title":["2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3446132.3446137","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3446132.3446137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:03:25Z","timestamp":1750197805000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3446132.3446137"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,24]]},"references-count":12,"alternative-id":["10.1145\/3446132.3446137","10.1145\/3446132"],"URL":"https:\/\/doi.org\/10.1145\/3446132.3446137","relation":{},"subject":[],"published":{"date-parts":[[2020,12,24]]},"assertion":[{"value":"2021-03-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}