[Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search

Brian Sheppard sheppardco at aol.com
Mon Feb 1 14:15:54 PST 2016


You play until neither player wishes to make a move. The players are willing to move on any point that is not self-atari, and they are willing to make self-atari plays if capture would result in a Nakade (http://senseis.xmp.net/?Nakade)

 

This correctly plays seki. 

 

From: Computer-go [mailto:computer-go-bounces at computer-go.org] On Behalf Of Brian Cloutier
Sent: Monday, February 1, 2016 5:02 PM
To: computer-go <computer-go at computer-go.org>
Subject: Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search

 

> One thing that is not explained is how to determine that a game is over

You'll find that very little of the literature explicitly covers this. When I asked this question I had to search a lot of papers on MCTS which mentioned "terminal states" before finding one which defined them.

Let me see if I can find the actual paper, but they defined it as a position where there are no more legal moves. You're right though, that ignores sekis, which makes me think I'm remembering wrong.

On Mon, Feb 1, 2016, 13:45 Álvaro Begué <alvaro.begue at gmail.com <mailto:alvaro.begue at gmail.com> > wrote:

 

Aja,

 

I read the paper with great interest. [Insert appropriate praises here.]

 

I am trying to understand the part where you use reinforcement learning to improve upon the CNN trained by imitating humans. One thing that is not explained is how to determine that a game is over, particularly when a player is simply a CNN that has a probability distribution as its output. Do you play until every point is either a suicide or looks like an eye? Do you do anything to make sure you don't play in a seki?

 

I am sure you are a busy man these days, so please answer only when you have time.

 

Thanks!

Álvaro.

 

 

 

On Wed, Jan 27, 2016 at 1:46 PM, Aja Huang <ajahuang at google.com <mailto:ajahuang at google.com> > wrote:

Hi all,

 

We are very excited to announce that our Go program, AlphaGo, has beaten a professional player for the first time. AlphaGo beat the European champion Fan Hui by 5 games to 0. We hope you enjoy our paper, published in Nature today. The paper and all the games can be found here: 

 

http://www.deepmind.com/alpha-go.html

 

AlphaGo will be competing in a match against Lee Sedol in Seoul, this March, to see whether we finally have a Go program that is stronger than any human! 

 

Aja

 

PS I am very busy preparing AlphaGo for the match, so apologies in advance if I cannot respond to all questions about AlphaGo.


_______________________________________________
Computer-go mailing list
Computer-go at computer-go.org <mailto:Computer-go at computer-go.org> 
http://computer-go.org/mailman/listinfo/computer-go

 

_______________________________________________
Computer-go mailing list
Computer-go at computer-go.org <mailto:Computer-go at computer-go.org> 
http://computer-go.org/mailman/listinfo/computer-go

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://computer-go.org/pipermail/computer-go/attachments/20160201/a18362ee/attachment.html>


More information about the Computer-go mailing list