Computer Go

Discuss anything you like about chess related matters in this forum.
Roger de Coverly
Posts: 16128
Joined: Tue Apr 15, 2008 2:51 pm

Re: AlphaZero

Post by Roger de Coverly » Thu Dec 07, 2017 1:28 pm

Anthony Appleyard wrote:
Thu Dec 07, 2017 1:12 pm
Today I read in a newspaper about a new chess program called AlphaZero

https://en.wikipedia.org/wiki/AlphaZero

What sort of computer does it run on?
We've been discussing this under a thread titled Computer Go.

The computer used is something home brewed by Google. It's massively powerful.

viewtopic.php?f=36&t=8097&start=120

Roger de Coverly
Posts: 16128
Joined: Tue Apr 15, 2008 2:51 pm

Re: Computer Go

Post by Roger de Coverly » Thu Dec 07, 2017 1:32 pm

Peter Shaw wrote:
Thu Dec 07, 2017 12:30 pm
Of course I don't really understand this, but surely it would take billions of games before it would even start to develop any simple strategy such as 'it's a generally a good idea to take the opponent's pieces'.
I'd think it's a similar program to one they got to play arcade games. I'd imagine it starts with some rudimentary strategy like taking opponent's pieces and retaining its own. They might even have given it a nudge by asking it to solve some simple mates.

User avatar
Clive Blackburn
Posts: 720
Joined: Fri Mar 23, 2012 8:33 am
Location: Coventry

Re: AlphaZero

Post by Clive Blackburn » Thu Dec 07, 2017 1:33 pm

Some details of the Google hardware here:-

https://en.wikipedia.org/wiki/Tensor_processing_unit
"Tactics flow naturally from a superior strategical position".
Bobby Fischer

Matt Fletcher
Posts: 200
Joined: Wed Mar 09, 2011 9:42 pm

Re: Computer Go

Post by Matt Fletcher » Thu Dec 07, 2017 2:10 pm

Peter, I think it did start playing random moves, but I'm not convinced that this is drawish. Agree it would be interesting to see some early games if they're stored!

I also think they do mention the number of games per step - the report says 'mini-batches of 4,096'. So if my maths is right, it self-played almost 3 billion games..!

Roger, I think the whole point was that they just told it the rules and set it running - no training on positions, just self-play and optimisation.

MartinCarpenter
Posts: 2333
Joined: Tue May 24, 2011 10:58 am

Re: Computer Go

Post by MartinCarpenter » Thu Dec 07, 2017 2:21 pm

There are really good fundamental reasons to set it off from scratch too - once you program anything into it beyond the rules you have to fix on some sort of abstractions to definite it all with. Get those wrong and you can really limit its ultimate strength.

A bit like how using existing Go games to train AlphaGo left it with some ultimately unhelpful human derived hang ups....

Deep mind are showing fairly strongly it works better to let the computer pick these sorts of things out itself :) Nothing left for us to do but worshipping our silicon overlords ;)

The other thing about the training is that I presume that those 3 billion games won't have all been purely random by any means - the first X% will have been, later on it'll have been a mixture of 'intelligent' and random moves and near the end it'll have been playing nearly all intelligent moves.

Paul McKeown
Posts: 3103
Joined: Thu Apr 12, 2007 3:01 pm
Location: Hayes (Middx)
Contact:

Re: Computer Go

Post by Paul McKeown » Mon Dec 11, 2017 8:31 am

I have just gone through the 10 published games from the match. Alpha Zero is amazing. It does not play like any computer program I have ever seen before. It seems to me more a superhuman initiative seeker, with a real sense of just going for it. Tal on steroids. The depth at which its material sacrifices are seen to be justified is staggering. Beautiful stuff. Of course, this is preliminary, as there are the other hundred odd unpublished games, which may ultimately give a different impression. I'm not sure who it was selected the games to be published, but do you get the feeling they liked seeing the Queen's Indian getting tin canned? Chuckle.

User avatar
Christopher Kreuzer
Posts: 6589
Joined: Fri Aug 06, 2010 2:34 am
Location: London

Re: AlphaZero

Post by Christopher Kreuzer » Wed Dec 13, 2017 5:23 pm

Chessbase article:

https://en.chessbase.com/post/alpha-zer ... and-apples

(There are other articles out there, if anyone wants to add other links.)

Paul McKeown
Posts: 3103
Joined: Thu Apr 12, 2007 3:01 pm
Location: Hayes (Middx)
Contact:

Re: AlphaZero

Post by Paul McKeown » Wed Dec 13, 2017 7:29 pm

It might be useful it the other Alpha Go thread were moved into the main forum, as it now concerns chess.

User avatar
Carl Hibbard
Posts: 5509
Joined: Fri Dec 08, 2006 8:05 pm
Location: Evesham

Re: AlphaZero

Post by Carl Hibbard » Wed Dec 13, 2017 8:41 pm

Paul McKeown wrote:
Wed Dec 13, 2017 7:29 pm
It might be useful it the other Alpha Go thread were moved into the main forum, as it now concerns chess.
The topics where combined.

This chap is a little loud but it was interesting:
https://www.youtube.com/watch?v=9CoNk3EYOpc&t=1032s
Cheers
Carl Hibbard

Paul McKeown
Posts: 3103
Joined: Thu Apr 12, 2007 3:01 pm
Location: Hayes (Middx)
Contact:

Re: Computer Go

Post by Paul McKeown » Wed Dec 13, 2017 9:18 pm

Thanks!

User avatar
Christopher Kreuzer
Posts: 6589
Joined: Fri Aug 06, 2010 2:34 am
Location: London

Re: Computer Go

Post by Christopher Kreuzer » Thu Dec 14, 2017 10:25 pm

We do really still need an AlphaZero thread that is separate from the AlphaGo thread, surely?

Just played through all the 10 sample wins by AlphaZero. Difficult to understand some of it, but some scarily impressive play and mix of tactics, positional play, and (to me) incomprehensible moves.

Post Reply