强化学习
冠军
计算机科学
人工智能
领域(数学分析)
对比度(视觉)
钢筋
学习分类器系统
计算机象棋
机器学习
认知科学
作者
David Silver,Thomas Hubert,Julian Schrittwieser,Ioannis Antonoglou,Matthew Lai,Arthur Guez,Marc Lanctot,Laurent Sifre,Dharshan Kumaran,Thore Graepel,Timothy P. Lillicrap,Karen Simonyan,Demis Hassabis
出处
期刊:Science
[American Association for the Advancement of Science (AAAS)]
日期:2018-12-07
卷期号:362 (6419): 1140-1144
被引量:1236
标识
DOI:10.1126/science.aar6404
摘要
The game of chess is the longest-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcrafted evaluation functions that have been refined by human experts over several decades. By contrast, the AlphaGo Zero program recently achieved superhuman performance in the game of Go by reinforcement learning from self-play. In this paper, we generalize this approach into a single AlphaZero algorithm that can achieve superhuman performance in many challenging games. Starting from random play and given no domain knowledge except the game rules, AlphaZero convincingly defeated a world champion program in the games of chess and shogi (Japanese chess), as well as Go.
科研通智能强力驱动
Strongly Powered by AbleSci AI