Alphazero news

Discussion of anything and everything relating to chess playing software and machines.

Moderators: bob, hgm, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
matthewlai
Posts: 793
Joined: Sun Aug 03, 2014 2:48 am
Location: London, UK
Contact:

Re: Alphazero news

Post by matthewlai » Sat Dec 08, 2018 11:45 am

glennsamuel32 wrote:
Sat Dec 08, 2018 5:27 am
Matthew, could you divulge the size of the network file that A0 used ?
The details are in supplementary materials:
Architecture
Apart from the representation of positions and actions described above, AlphaZero uses the
same network architecture as AlphaGo Zero (9), briefly recapitulated here.
The neural network consists of a “body” followed by both policy and value “heads”. The
body consists of a rectified batch-normalized convolutional layer followed by 19 residual blocks (48).
Each such block consists of two rectified batch-normalized convolutional layers with a skip connection.
Each convolution applies 256 filters of kernel size 3 ⇥ 3 with stride 1. The policy head
applies an additional rectified, batch-normalized convolutional layer, followed by a final convolution
of 73 filters for chess or 139 filters for shogi, or a linear layer of size 362 for Go,
representing the logits of the respective policies described above. The value head applies an
additional rectified, batch-normalized convolution of 1 filter of kernel size 1 ⇥ 1 with stride 1,
followed by a rectified linear layer of size 256 and a tanh-linear layer of size 1.
Disclosure: I work for DeepMind on the AlphaZero project, but everything I say here is personal opinion and does not reflect the views of DeepMind / Alphabet.

Rein Halbersma
Posts: 685
Joined: Tue May 22, 2007 9:13 am

Re: Alphazero news

Post by Rein Halbersma » Sat Dec 08, 2018 12:16 pm

So why is it that A0's learning curve seems to flatten to almost no progress beyond it's current level? If e.g. the number of layers or channels is expanded, would you expect that a few hundred Elo more could be obtained? Or is A0 approaching perfection with its current network and is an absolute upperbound of Elo in sight?

nabildanial
Posts: 104
Joined: Thu Jun 05, 2014 3:29 am
Location: Malaysia

Re: Alphazero news

Post by nabildanial » Sat Dec 08, 2018 12:38 pm

matthewlai wrote:
Sat Dec 08, 2018 11:45 am
glennsamuel32 wrote:
Sat Dec 08, 2018 5:27 am
Matthew, could you divulge the size of the network file that A0 used ?
The details are in supplementary materials:
Architecture
Apart from the representation of positions and actions described above, AlphaZero uses the
same network architecture as AlphaGo Zero (9), briefly recapitulated here.
The neural network consists of a “body” followed by both policy and value “heads”. The
body consists of a rectified batch-normalized convolutional layer followed by 19 residual blocks (48).
Each such block consists of two rectified batch-normalized convolutional layers with a skip connection.
Each convolution applies 256 filters of kernel size 3 ⇥ 3 with stride 1. The policy head
applies an additional rectified, batch-normalized convolutional layer, followed by a final convolution
of 73 filters for chess or 139 filters for shogi, or a linear layer of size 362 for Go,
representing the logits of the respective policies described above. The value head applies an
additional rectified, batch-normalized convolution of 1 filter of kernel size 1 ⇥ 1 with stride 1,
followed by a rectified linear layer of size 256 and a tanh-linear layer of size 1.
I think what glenn meant by the question is how big the filesize is as in MB.

Alexander Schmidt
Posts: 1086
Joined: Thu May 10, 2007 12:49 pm

Re: Alphazero news

Post by Alexander Schmidt » Sat Dec 08, 2018 12:48 pm

nabildanial wrote:
Sat Dec 08, 2018 11:39 am
Alexander Schmidt wrote:
Sat Dec 08, 2018 11:29 am
Maybe people will go to jail because an AI thinks he will someday do a crime. One day autonomous robots will decide which person to kill, on a battlefield or to prevent a possible crime. Maybe one day an AI will press the red button.
We have the so-called "Ethics of artificial intelligence" to prevent those things from happening.
These things already happen:
http://www.israeltoday.co.il/NewsItem/t ... fault.aspx
https://www.datanami.com/2017/07/17/neu ... ion-banks/

jp
Posts: 815
Joined: Mon Apr 23, 2018 5:54 am

Re: Alphazero news

Post by jp » Sat Dec 08, 2018 12:54 pm

nabildanial wrote:
Sat Dec 08, 2018 12:38 pm
matthewlai wrote:
Sat Dec 08, 2018 11:45 am
glennsamuel32 wrote:
Sat Dec 08, 2018 5:27 am
Matthew, could you divulge the size of the network file that A0 used ?
The details are in supplementary materials
I think what glenn meant by the question is how big the filesize is as in MB.
Yep. How big is the filesize in MB?

shrapnel
Posts: 1198
Joined: Fri Nov 02, 2012 8:43 am
Location: New Delhi, India

Re: Alphazero news

Post by shrapnel » Sat Dec 08, 2018 12:57 pm

Any Plans to Commercialize AlphaZero ?
Can't wait to get my hands on AlphaZero engine no matter what the Price.
i7 5960X @ 4.1 Ghz, 64 GB G.Skill RipJaws RAM, Twin Asus ROG Strix OC 11 GB Geforce 2080 Tis

matthewlai
Posts: 793
Joined: Sun Aug 03, 2014 2:48 am
Location: London, UK
Contact:

Re: Alphazero news

Post by matthewlai » Sat Dec 08, 2018 1:55 pm

jp wrote:
Sat Dec 08, 2018 12:54 pm
nabildanial wrote:
Sat Dec 08, 2018 12:38 pm
matthewlai wrote:
Sat Dec 08, 2018 11:45 am
glennsamuel32 wrote:
Sat Dec 08, 2018 5:27 am
Matthew, could you divulge the size of the network file that A0 used ?
The details are in supplementary materials
I think what glenn meant by the question is how big the filesize is as in MB.
Yep. How big is the filesize in MB?
Not sure. We don't store the networks locally. They are just TensorFlow SavedModels. If you construct the same network and save it you'll get the same size. https://www.tensorflow.org/guide/saved_model
Disclosure: I work for DeepMind on the AlphaZero project, but everything I say here is personal opinion and does not reflect the views of DeepMind / Alphabet.

Jouni
Posts: 2003
Joined: Wed Mar 08, 2006 7:15 pm

Re: Alphazero news

Post by Jouni » Sat Dec 08, 2018 2:36 pm

Of course Alphazero is stunning achievement! But so far not better than Stockfish only alternative approach. BTW in 22 move loss game A0 is already lost after 12.-Nb6 based my short analysis. May be 12. -Nf8 can still save game?
Jouni

corres
Posts: 1642
Joined: Wed Nov 18, 2015 10:41 am
Location: hungary

Re: Alphazero news

Post by corres » Sat Dec 08, 2018 3:57 pm

Astatos wrote:
Fri Dec 07, 2018 12:01 pm
OK what we know :
...
2) LC0 guys did manage to reverse engineer A0 successfully
...
Do you think the developers of LC0 can get the binaries used by the team of A0?
They only try to develop an NN based chess engine from the rather incomplete information made public
about A0 by the team of A0.
They are working hard and well and to now the chess power of LC0 comes near to A0.
A lot of thanks to the team of LC0 and their voluntary helpers!
I think maybe the results of the developers of LC0 forces the team of A0 to come to public more information about A0.

corres
Posts: 1642
Joined: Wed Nov 18, 2015 10:41 am
Location: hungary

Re: Alphazero news

Post by corres » Sat Dec 08, 2018 4:02 pm

shrapnel wrote:
Sat Dec 08, 2018 12:57 pm
Any Plans to Commercialize AlphaZero ?
Can't wait to get my hands on AlphaZero engine no matter what the Price.
You should become the main share-holder of Google to get that engine...

Post Reply