CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 智能化团队
王成红; 孙长银; 苏剑波; 周彤; 赵东斌; 胡跃明
Source Publication控制理论与应用
Other Abstract

       20163, 谷歌公司开发的计算机程序AlphaGo(初弈号)在韩国首都首尔挑战当今世界顶级棋手 —–韩国职业九段李世石(Lee Sedol), 并最终取得41负的令世界震惊战绩. 这标志着人工智能方法已经 能够在复杂的棋类博弈游戏中达到匹敌、甚至超越人类的水平. 其基本原理是将具有“感知”能力的深 度学习(deep learning)和具有“决策”能力的强化学习(reinforcement learning)紧密结合, 构成深度强化学 习(deep reinforcement learning)算法, 并与蒙特卡罗树搜索结合. 它极大地减少了目标优化过程的计算量, 提升了对棋局估计的准确度

;      In March 2016, AlphaGo, a computer program developed by Google Corporation, challenged Lee Sedol, Korea's top nine player in the Korean capital, to challenge the world record of 4-1 in Korea's capital Seoul This signifies that artificial intelligence methods have been able to match or even surpass humankind in complex chess game games whose basic principle is to combine deep learning with "perceived" abilities and "decision-making" abilities Reinforcement learning is tightly coupled to form a deep reinforcement learning algorithm that is combined with Monte Carlo tree search, which greatly reduces the computational complexity of the goal optimization process and improves the accuracy of the game estimate.
Keyword机器智能 系统优化 最优决策
Document Type期刊论文
Recommended Citation
GB/T 7714
王成红,孙长银,苏剑波,等. “机器智能、系统优化与最优决策”专刊前言[J]. 控制理论与应用,2016,33(12):1553-1554.
APA 王成红,孙长银,苏剑波,周彤,赵东斌,&胡跃明.(2016).“机器智能、系统优化与最优决策”专刊前言.控制理论与应用,33(12),1553-1554.
MLA 王成红,et al."“机器智能、系统优化与最优决策”专刊前言".控制理论与应用 33.12(2016):1553-1554.
Files in This Item: Download All
File Name/Size DocType Version Access License
“机器智能、系统优化与最优决策”专刊前言(164KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[王成红]'s Articles
[孙长银]'s Articles
[苏剑波]'s Articles
Baidu academic
Similar articles in Baidu academic
[王成红]'s Articles
[孙长银]'s Articles
[苏剑波]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[王成红]'s Articles
[孙长银]'s Articles
[苏剑波]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: “机器智能、系统优化与最优决策”专刊前言.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.