-
摘要: 谷歌的围棋系统阿法狗(AlphaGo)在三月的比赛中以4:1的成绩击败了围棋世界冠军李世石, 大大超过了许多人对计算机围棋程序何时能赶上人类职业高手的预期(约10～30年).本文在技术层面分析了阿法狗系统的组成部分, 并基于它过去的公开对局预测了它可能的弱点.Abstract: In March 2016, the AlphaGo system from Google DeepMind beat the World Go Champion Lee Sedol 4:1 in a historic five-game match. This is a giant leap filling the gap between Go AI and top human professional players, which was once regarded to be filled in at least 10～30 years. In this paper, based on published results [Silver et al., 2016], i analyze the components of AlphaGo and predict its potential technical weakness based on the public games of AlphaGo.
-
Key words:
- Deep learning /
- deep convolutional neural network /
- computer Go /
- reinforcement learning /
- AlphaGo
-
表 1 阿法狗在快速走子中使用的盘面特征
Table 1 Input features for rollout and tree policy
Feature # of patterns Description Response 1 Whether move matches one or more response pattern features Save atari 1 Move saves stone(s) from capture Neighbour 8 Move is 8-connected to previous move Nakade 8 192 Move matches a nakade pattern at captured stone Response pattern 32 207 Move matches 12-point diamond pattern near previous move Non-response pattern 69 338 Move matches 3 £ 3 pattern around move Self-atari 1 Move allows stones to be captured Last move distance 34 Manhattan distance to previous two moves Non-response pattern 32 207 Move matches 12-point diamond pattern centred around move (Features used by the rollout pollcy (the frst set) and tree policy (the frst and second sets). Patterns are based on stone colour (black/white/empty) and liberties (1, 2,≥3) at each intersection of the pattern.) 
下载: 导出CSV
表 2 不同版本阿法狗的等级分比较(等级分由一场内部锦标赛决出)
Table 2 Results of a tournament between di®erent variants of AlphaGo
Short name Policy network Value network Rollouts Mixing constant Policy GPUs Value GPUs Elo rating αrvp pσ vθ pπ λ= 0.5 2 6 2 890 αvp pσ vθ - λ= 0 2 6 2 177 αrp pσ - pπ λ= 1 8 0 2 416 αrv [pτ] vθ pπ λ= 0.5 0 8 2 077 αv [pτ] vθ - λ= 0 0 8 1 655 αr [pτ] - pπ λ= 1 0 0 1 457 αp pσ - - - 0 0 1 517 Evaluating positions using rollouts only (αrp; αr), value nets only (αvp; αv), or mixing both (αrvp; αrv); either using the policy network ρσ(αrvp; αvp; αrp) or no policy network (αrvp; αvp; αrp), that is, instead using the placeholder probabilities from the tree policy pτ throughout. Each program used 5 s per move on a single machine with 48 CPUs and 8 GPUs. Elo ratings were computed by BayesElo.
下载: 导出CSV
-
[1] Silver D, Huang A, Maddison C J, Guez A, Sifre L, van den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M, Dieleman S, Grewe D, Nham J, Kalchbrenner N, Sutskever I, Lillicrap T, Leach M, Kavukcuoglu K, Graepel T, Hassabis D. Mastering the game of go with deep neural networks and tree search. Nature, 2016, 529(7587): 484-489 [2] Tian Y D, Zhu Y. Better computer go player with neural network and long-term prediction. In: International Conference on Learning Representation (ICLR). San Juan, Puerto Rico, 2016. 期刊类型引用(8)
1. 董良振，田建艳，杨胜强，陈海滨. 基于光照校正和图像融合的零件表面图像增强. 计算机工程. 2024(06): 245-254 . 
百度学术2. 王琛，张凌云，刘波，张航. 基于无人机图像的城市道路停车巡检方法. 交通信息与安全. 2024(04): 90-101 . 百度学术3. 徐少平，林珍玉，陈孝国，李芬，杨晓辉. 采用多通道浅层CNN构建的多降噪器最优组合模型. 自动化学报. 2022(11): 2797-2811 . 本站查看4. 苏素平，李虹，孙志毅，孙前来，王银. 无人机图像的输电线断股检测方法研究. 太原科技大学学报. 2021(01): 32-36 . 百度学术5. 索岩，崔智勇. 基于中国剩余定理的高动态图像可逆数据隐藏. 计算机仿真. 2021(01): 167-171 . 百度学术6. 张媛媛，张红英. 结合饱和度调节的单曝光HDR图像生成方法. 吉林大学学报(理学版). 2021(02): 309-318 . 百度学术7. 曹义亲，何恬，刘龙标. 基于改进LSD直线检测算法的钢轨表面边界提取. 华东交通大学学报. 2021(03): 95-101 . 百度学术8. 吴卓钊，范科峰，莫玮. 多尺度权重评估的MSRCR混合曝光成像算法. 计算机工程与应用. 2021(17): 224-229 . 百度学术其他类型引用(14)
-
图(2) / 表(2)
计量
- 文章访问数: 4346
- HTML全文浏览量: 887
- PDF下载量: 4902
- 被引次数: 22
