AlphaGo的突破与兵棋推演的挑战

被引：36

作者：

胡晓峰 ^{[1
]}

贺筱媛 ^{[1
]}

陶九阳 ^{[1
,2
]}

机构：

[1] 国防大学信息作战与指挥训练教研部

[2] 陆军工程大学指挥信息系统学院

来源：

科技导报 | 2017年 / 35卷 / 21期

关键词：

AlphaGo; 深度学习; 兵棋推演; 态势认知;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

概述了AlphaGo的原理、方法创新、技术突破和在认识论上的意义。分析了兵棋推演面临的瓶颈,指出了作战智能态势认知是亟需突破的关键环节。提出了解决作战态势智能认知的实现途径。展望了"人机智能"为兵棋推演带来的新机遇。

引用

页码：49 / 60

页数：12

共 11 条

[1] AlphaGo技术原理分析及人工智能军事应用展望
陶九阳
吴琳
胡晓峰
[J]. 指挥与控制学报, 2016, 2 (02) : 114 - 120
[2] Where Does AlphaGo Go: From Church-Turing Thesis to AlphaGo Thesis and Beyond
Fei-Yue Wang
Jun Jason Zhang
Xinhu Zheng
Xiao Wang
Yong Yuan
Xiaoxiao Dai
Jie Zhang
Liuqing Yang
[J]. IEEE/CAAJournalofAutomaticaSinica, 2016, 3 (02) : 113 - 120
[3] 战争模拟原理与系统[M]. 国防大学出版社 , 胡晓峰等, 2009
[4] Human-level concept learning through probabilistic program induction
Lake, Brenden M.
Salakhutdinov, Ruslan
Tenenbaum, Joshua B.
[J]. SCIENCE, 2015, 350 (6266) : 1332 - 1338
[5] WHY WARGAMING WORKS
Perla, Peter P.
McGrady, E. D.
[J]. NAVAL WAR COLLEGE REVIEW, 2011, 64 (03) : 111 - 130
[6] A historical review of evolutionary learning methods for Mamdani-type fuzzy rule-based systems: Designing interpretable genetic fuzzy systems[J] . Oscar Cordón.International Journal of Approximate Reasoning . 2011 (6)
[7] A fast learning algorithm for deep belief nets
Hinton, Geoffrey E.
Osindero, Simon
Teh, Yee-Whye
[J]. NEURAL COMPUTATION, 2006, 18 (07) : 1527 - 1554
[8] Deep Blue[J] . Murray Campbell,A.Joseph Hoane,Feng-hsiung Hsu.Artificial Intelligence . 2001 (1)
[9] Mixing floating- and fixed-point formats for neural network learning on neuroprocessors
Anguita, D
Gomes, BA
[J]. MICROPROCESSING AND MICROPROGRAMMING, 1996, 41 (10): : 757 - 769
[10] Searching for solutions in games and artifcial intelligence. ALLIS L V. University Limburg . 1994

← 1 2 →