Have you tried to look in the source tree where is that function called what() !
https://bitbucket.org/waterreaction/gir ... at=default
Will try to re-compile when I find time ...
Google's AlphaGo team has been working on chess
Moderators: hgm, Rebel, chrisw
-
- Posts: 31
- Joined: Fri Nov 25, 2016 10:14 am
- Location: Singapore
Re: Google's AlphaGo team has been working on chess
Brahim HAMADICHAREF
Singapore
Singapore
-
- Posts: 31
- Joined: Fri Nov 25, 2016 10:14 am
- Location: Singapore
Re: Google's AlphaGo team has been working on chess
A lot of the new AlphaZero versus established Stockfish reminds me of some old papers from Chellapilla and Fogel in 1999-2000 on Evolving neural networks to play checkers without relying on expert knowledge see at IEEE explorer http://ieeexplore.ieee.org/document/809083/ ... At time already the focus was to train / evolve neural network for game and without expert knowledge apart from the rules of the gaome, checkers in this case. Deep
Learning with Residual Nets are today advanced NNets of that time.
Loking forward to more detailed on AlphaZero topology to play ...
Learning with Residual Nets are today advanced NNets of that time.
Loking forward to more detailed on AlphaZero topology to play ...
Brahim HAMADICHAREF
Singapore
Singapore
-
- Posts: 1563
- Joined: Thu Jul 16, 2009 10:47 am
- Location: Almere, The Netherlands
Re: Google's AlphaGo team has been working on chess
Very nice you know that one too!Rebel wrote:It's still sold.
BrainMaker Professional for Windows $795
I was already playing with that package 25 years ago. I still have an old version 'BrainMaker v2.52' (written in Borland C) somewhere on my NAS. The floppies it originally came on are long time gone.
Edit:
Just tried to run it, but it does not work under Windows 10, I will keep it for nostalgic reasons.
-
- Posts: 5566
- Joined: Tue Feb 28, 2012 11:56 pm
Re: Google's AlphaGo team has been working on chess
Linux + Wine probably offers better backward compatibility for old Windows programsJoost Buijs wrote:Just tried to run it, but it does not work under Windows 10, I will keep it for nostalgic reasons.
-
- Posts: 13447
- Joined: Wed Mar 08, 2006 9:02 pm
- Location: Dallas, Texas
- Full name: Matthew Hull
Re: Google's AlphaGo team has been working on chess
IIRC, DOS versions work under FreeDOS, maybe even Windows CMD window. These are the versions I have. I also have a Macintosh version that runs under System 7/8/9.Joost Buijs wrote:Very nice you know that one too!Rebel wrote:It's still sold.
BrainMaker Professional for Windows $795
I was already playing with that package 25 years ago. I still have an old version 'BrainMaker v2.52' (written in Borland C) somewhere on my NAS. The floppies it originally came on are long time gone.
Edit:
Just tried to run it, but it does not work under Windows 10, I will keep it for nostalgic reasons.
Matthew Hull
-
- Posts: 13447
- Joined: Wed Mar 08, 2006 9:02 pm
- Location: Dallas, Texas
- Full name: Matthew Hull
Re: Google's AlphaGo team has been working on chess
CALSCI had a second generation of ISA/PCI accelerator boards that could process 2.3B NN connections per second (a Pentium 90 could do 1.9M connections per second). These boards shipped with either 64 or 128 CPUs and cost up to $8,345.Rebel wrote:It's still sold.
BrainMaker Professional for Windows $795
Current off-the-shelf multi-core systems could probably match those speeds these days.
Matthew Hull
-
- Posts: 6991
- Joined: Thu Aug 18, 2011 12:04 pm
Re: Google's AlphaGo team has been working on chess
Anyone ever tried the training?Rebel wrote:I am trying to train Giraffe exactly how it is described here.
But it crashes,... [snip]
-
- Posts: 536
- Joined: Thu Mar 09, 2006 3:01 pm
Re: Google's AlphaGo team has been working on chess
Works fine with Ubuntu for me. I could not get training to work under Win7.Rebel wrote:Anyone ever tried the training?Rebel wrote:I am trying to train Giraffe exactly how it is described here.
But it crashes,... [snip]
-
- Posts: 6991
- Joined: Thu Aug 18, 2011 12:04 pm
Re: Google's AlphaGo team has been working on chess
Suspected already that it is OS related, Visual Studio debugger pointed to several WINDOWS\SYSTEM32 *.dll files.brianr wrote:Works fine with Ubuntu for me. I could not get training to work under Win7.Rebel wrote:Anyone ever tried the training?Rebel wrote:I am trying to train Giraffe exactly how it is described here.
But it crashes,... [snip]
-
- Posts: 6991
- Joined: Thu Aug 18, 2011 12:04 pm
Re: Google's AlphaGo team has been working on chess
Nice idea, a few points.petero2 wrote:The post describing this test is here.Rebel wrote:Statements like these could make me a believer.Daniel Shawul wrote:That is a start for sure -- proving a NN evaluation could be competive or even much better than a hand crafted evaluation function. The latency of evaluating the NN can be countered with a combination hardware (GPU/TPU) and software (async evaluations) which is what Google did for AlphaGo. Giraffe used only three layers of NN with chess specific inputs such as attack maps while AlphaZero used many more layers of CNN with just the rules of the game as input. Texel actually replaced its evaluation function with Giraffe's NN and showed that the eval is actually better but it would need a time odds to be competitive on the same hardware.
I tried the STS test and saw hardly any similarity between Giraffe (2016) and Texel GI. And so I ran the good old similarity test.
Code: Select all
Positions 8238 Gira Texe
{Giraffe w64 (time: 100 ms scale: 1.0)} ----- 4.72
{Texel Gi (time: 100 ms scale: 1.0)} 4.72 -----
Never seen such a low percentage, running it now at 1 second.
Last, I started a match, TC=40/60, I stopped after 40 games, 37.5 - 2.5 in favor of Texel GI while NPS favored Giraffe (2016) with approx. 20-25%.
------
Unless I have done something wrong I don't see how one can conclude the NN is on par with SF or your evaluation.