正好刚刚看到有人贴链接，就把摘要翻译了一下。 我个人对计算机技术有一定了解，所以中间一些术语做了一点简单的注释。大家如果对外面瞎扯的新闻有疑问，可以参考。 先放英文，后放译文
The gameof Go has long been viewed as the most challenging of classic games for ar-tificial intelligence due to its enormous search space and the difficulty ofevaluating board positions and moves. We introduce a new approach to computerGo that uses value networks to evaluateboard positions and policy networks toselect moves. These deep neural networks are trained by a novel combination ofsupervised learning from human expert games, and reinforcement learning fromgames of self-play. Without any lookahead search, the neural networks play Goat the level of state-of-the-art Monte-Carlo tree search programs that sim-ulate thousands of random games of self-play. We also introduce a new searchalgorithm that combines Monte-Carlo simulation with value and policy networks.Using this search al- gorithm, our program AlphaGoachieved a 99.8% winning rate against other Go programs, and defeatedthe European Go champion by 5 games to 0. This is the first time that a com-puter program has defeated a human professional player in the full-sized gameof Go, a feat previously thought to be at least a decade away.