- AlphaGo Zero does not use “rollouts” - fast, random games used by other Go programs to predict which player will win from the current board position. Instead, it relies on its high quality neural networks to evaluate positions.
All of these differences help improve the performance of the system and make it more general. But it is the algorithmic change that makes the system much more powerful and efficient.
AlphaGo has become progressively more efficient thanks to hardware gains and more recently algorithmic advances
AlphaGo的效率越来越高得益于硬件的进步和算法的优化。
After just three days of self-play training, AlphaGo Zero emphatically defeated the previously [published version of AlphaGo](https://research.googleblog.com/2016/01/alphago-mastering-ancient-game-of-go.html) - which had itself [defeated 18-time world champion Lee Sedol](https://deepmind.com/research/alphago/alphago-korea/) - by 100 games to 0. After 40 days of self training, AlphaGo Zero became even stronger, outperforming the version of AlphaGo known as “Master”, which has defeated the world's best players and [world number one Ke Jie](https://deepmind.com/research/alphago/alphago-china/).
Elo ratings - a measure of the relative skill levels of players in competitive games such as Go - show how AlphaGo has become progressively stronger during its development
Over the course of millions of AlphaGo vs AlphaGo games, the system progressively learned the game of Go from scratch, accumulating thousands of years of human knowledge during a period of just a few days. AlphaGo Zero also discovered new knowledge, developing unconventional strategies and creative new moves that echoed and surpassed the novel techniques it played in the games against Lee Sedol and Ke Jie.
![AlphaGo Zero knowledge timeline](https://storage.googleapis.com/deepmind-live-cms/documents/Knowledge%2520Timeline.gif)
These moments of creativity give us confidence that AI will be a multiplier for human ingenuity, helping us with [our mission](https://deepmind.com/about/) to solve some of the most important challenges humanity is facing.
While it is still early days, AlphaGo Zero constitutes a critical step towards this goal. If similar techniques can be applied to other structured problems, such as protein folding, reducing energy consumption or searching for revolutionary new materials, the resulting breakthroughs have the potential to positively impact society.
Read the accompanying[Nature News and Views article](https://www.nature.com/articles/550336a.epdf?shared_access_token=QbXlOw9nSIP_MS1moc_M0tRgN0jAjWel9jnR3ZoTv0PvinEKRXS2Dk736vL8i-Uo2-6AN8KRxOlLhDGorUgFzEgC3fwrX95r3LQ7u2FBwQ5axjmpMSZrWg4i6D7_g5rV5ze0zLhgo4jufsSKL-UZmw%3D%3D)
阅读这篇文章相关的[Nature News and Views article](https://www.nature.com/articles/550336a.epdf?shared_access_token=QbXlOw9nSIP_MS1moc_M0tRgN0jAjWel9jnR3ZoTv0PvinEKRXS2Dk736vL8i-Uo2-6AN8KRxOlLhDGorUgFzEgC3fwrX95r3LQ7u2FBwQ5axjmpMSZrWg4i6D7_g5rV5ze0zLhgo4jufsSKL-UZmw%3D%3D)
Download[AlphaGo Zero games](http://www.alphago-games.com/)
下载[AlphaGo Zero games](http://www.alphago-games.com/)
Read [more about AlphaGo](https://deepmind.com/research/alphago/)
**\*This work was done by David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, Yutian Chen, Timothy Lillicrap, Fan Hui, Laurent Sifre, George van den Driessche, Thore Graepel and Demis Hassabis.***
\ No newline at end of file
**\*这个作品是由David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, Yutian Chen, Timothy Lillicrap, Fan Hui, Laurent Sifre, George van den Driessche, Thore Graepel和Demis Hassabis完成的***