Interpretation of the artificial intelligence technology behind Alphago

被引：0

作者：

Liu Z.-Q. ^{[1
]}

Wu X.-Z. ^{[1
]}

机构：

[1] College of Software, Beijing University of Posts and Telecommunications, Beijing

来源：

Kongzhi Lilun Yu Yingyong/Control Theory and Applications | 2016年 / 33卷 / 12期

关键词：

AlphaGo; Deep learning; Policy network; Value network;

D O I：

10.7641/CTA.2016.60526

中图分类号：

学科分类号：

摘要：

With the application of artificial intelligence in various fields, more and more problems have been solved. But computer Go has been a difficult problem in the field of artificial intelligence, because of the complexity of the game. AlphaGo team has trained a Go AI program which took advantage of an important branch of artificial intelligence-deep learning. In March 2016 AlphaGo won 4-1 the game with professional Go player Lee se-dol (9P), received extensive attention of the public. © 2016, Editorial Department of Control Theory & Applications South China University of Technology. All right reserved.

引用

页码：1685 / 1687

页数：2

共 6 条

[1] Silver D., Huang A., Maddison C., Et al., Mastering the game of Go with deep neural networks and tree search, Nature, 529, 7587, pp. 484-489, (2016)
[2] Caflisch R.E., Monte Carlo and quasi-Monte Carlo methods, Acta Numerica, pp. 1-49, (1998)
[3] Thrun S., Monte Carlo POMDPs, Advances in Neural Information Processing Systems, 12, pp. 1064-1070, (1999)
[4] Littman M.L., Reinforcement learning improves behaviour from evaluative feedback, Nature, 521, 7553, pp. 445-451, (2015)
[5] Tian Y., A simple analysis of AlphaGo, Acta Automatica, 42, 5, pp. 671-675, (2016)
[6] Zhao D., Shao K., Zhu Y., Et al., Review of deep reinforcement learning and discussions on the development of computer Go, Control Theory & Applications, 33, 6, pp. 701-717, (2016)

← 1 →