AlphaGo

My colleagues David Silver, Aja Huang, and others have just published their excellent work on Go in Nature.  The system is called AlphaGo, and it combines Monte-Carlo tree search with deep neural networks, trained by supervised learning and by reinforcement learning from self-play.  The landmark achievement was beating the human European champion 5-0 in tournament games.  This is the first time that a computer beat a human professional player.

In March, AlphaGo will take on Lee Sedol, one of the best Go players in the world.  The match will be in Seoul from March 9th until March 15th.

Exciting times.

Update:

AlphaGo beat Lee Sedol by winning 4 of the 5 games.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s