Damage 15.3

Discussion about development of draughts in the time of computer and Internet.
Post Reply
BertTuyt
Posts: 1436
Joined: Wed Sep 01, 2004 19:42

Re: Damage 15.3

Post by BertTuyt » Fri Feb 21, 2020 22:28

I still do not believe that there is a huge ELO gain possible beyond Scan / Kingsrow with normal time settings.
But advanced approaches like A0, can learn us much about the relevant features (like material value man/king temp, left right balance, game phase) in draughts, which are now (more or less) pre-defined by the programmers (although the value is determined through ML).

Bert

BertTuyt
Posts: 1436
Joined: Wed Sep 01, 2004 19:42

Re: Damage 15.3

Post by BertTuyt » Fri Feb 21, 2020 22:51

As stated in a previous post, I will do now some tests to measure ELO as a function of games with increased win/loss ratio.
I used the same data set, but only used 1 out of X of the draw games.
The test now running is with X = 3, so only on out of 3 draws are used, effectively increasing the decisive ratio with the same factor 3.

Tomorrow I can share a first result.

Bert

Sidiki
Posts: 178
Joined: Thu Jan 15, 2015 16:28
Real name: Coulibaly Sidiki

Re: Damage 15.3

Post by Sidiki » Fri Feb 21, 2020 23:42

BertTuyt wrote:
Fri Feb 21, 2020 22:51
As stated in a previous post, I will do now some tests to measure ELO as a function of games with increased win/loss ratio.
I used the same data set, but only used 1 out of X of the draw games.
The test now running is with X = 3, so only on out of 3 draws are used, effectively increasing the decisive ratio with the same factor 3.

Tomorrow I can share a first result.

Bert
OK Bert,
We hope that X=3 will be promising.
What's, for you the maximum X value to reach for an efficient test ?
Or it's linked to the saturation graph posted early ?
Thank.

Sidiki

Sidiki
Posts: 178
Joined: Thu Jan 15, 2015 16:28
Real name: Coulibaly Sidiki

Re: Damage 15.3

Post by Sidiki » Fri Feb 21, 2020 23:43

BertTuyt wrote:
Fri Feb 21, 2020 22:28
I still do not believe that there is a huge ELO gain possible beyond Scan / Kingsrow with normal time settings.
But advanced approaches like A0, can learn us much about the relevant features (like material value man/king temp, left right balance, game phase) in draughts, which are now (more or less) pre-defined by the programmers (although the value is determined through ML).

Bert
ML, it's definely the best programming approch to get a strong engine.

Krzysztof Grzelak
Posts: 933
Joined: Thu Jun 20, 2013 17:16
Real name: Krzysztof Grzelak

Re: Damage 15.3

Post by Krzysztof Grzelak » Sat Feb 22, 2020 11:21

Rein Halbersma wrote:
Fri Feb 21, 2020 18:30
You do understand that Google/Deepmind used 1700 years worth of computing *in parallel* in order to achieve all that in 4 hours?
You trust too much Google.

Sidiki
Posts: 178
Joined: Thu Jan 15, 2015 16:28
Real name: Coulibaly Sidiki

Re: Damage 15.3

Post by Sidiki » Sat Feb 22, 2020 12:21

Krzysztof Grzelak wrote:
Sat Feb 22, 2020 11:21
Rein Halbersma wrote:
Fri Feb 21, 2020 18:30
You do understand that Google/Deepmind used 1700 years worth of computing *in parallel* in order to achieve all that in 4 hours?
You trust too much Google.
I am asking myself if A0 can beat RedFish that crashed LC0

Rein Halbersma
Posts: 1669
Joined: Wed Apr 14, 2004 16:04
Contact:

Re: Damage 15.3

Post by Rein Halbersma » Sat Feb 22, 2020 14:16

Krzysztof Grzelak wrote:
Sat Feb 22, 2020 11:21
Rein Halbersma wrote:
Fri Feb 21, 2020 18:30
You do understand that Google/Deepmind used 1700 years worth of computing *in parallel* in order to achieve all that in 4 hours?
You trust too much Google.
The 1700 years of computing comes from Gian-Carlo Pascutto, author of Leela-Zero, the open source program that actually reproduced the Alphazero results. See http://computer-go.org/pipermail/comput ... 10307.html

Sidiki
Posts: 178
Joined: Thu Jan 15, 2015 16:28
Real name: Coulibaly Sidiki

Re: Damage 15.3

Post by Sidiki » Sat Feb 22, 2020 16:39

Rein Halbersma wrote:
Sat Feb 22, 2020 14:16
Krzysztof Grzelak wrote:
Sat Feb 22, 2020 11:21
Rein Halbersma wrote:
Fri Feb 21, 2020 18:30
You do understand that Google/Deepmind used 1700 years worth of computing *in parallel* in order to achieve all that in 4 hours?
You trust too much Google.
The 1700 years of computing comes from Gian-Carlo Pascutto, author of Leela-Zero, the open source program that actually reproduced the Alphazero results. See http://computer-go.org/pipermail/comput ... 10307.html
Good reply Rein,
All this prove again that supercalculators are very very powerfull. I remember a post, sorry i haven't the link that spoken of a french supercalculator, not the best, and they said that the data that this machine calculate in Day, will be reached by all the humans with a calculator per person, in 50 years.
I believe so that this isn't too much for Google neuronal machines.

Sidiki

Krzysztof Grzelak
Posts: 933
Joined: Thu Jun 20, 2013 17:16
Real name: Krzysztof Grzelak

Re: Damage 15.3

Post by Krzysztof Grzelak » Sat Feb 22, 2020 17:23

Sidiki wrote:
Sat Feb 22, 2020 16:39
Good reply Rein,
All this prove again that supercalculators are very very powerfull. I remember a post, sorry i haven't the link that spoken of a french supercalculator, not the best, and they said that the data that this machine calculate in Day, will be reached by all the humans with a calculator per person, in 50 years.
I believe so that this isn't too much for Google neuronal machines.

Sidiki
Unfortunately that is not a good answer Rein.

Sidiki
Posts: 178
Joined: Thu Jan 15, 2015 16:28
Real name: Coulibaly Sidiki

Re: Damage 15.3

Post by Sidiki » Sat Feb 22, 2020 18:51

Krzysztof Grzelak wrote:
Sat Feb 22, 2020 17:23
Sidiki wrote:
Sat Feb 22, 2020 16:39
Good reply Rein,
All this prove again that supercalculators are very very powerfull. I remember a post, sorry i haven't the link that spoken of a french supercalculator, not the best, and they said that the data that this machine calculate in Day, will be reached by all the humans with a calculator per person, in 50 years.
I believe so that this isn't too much for Google neuronal machines.

Sidiki
Unfortunately that is not a good answer Rein.
Why ? We are speaking of neural Network many computer or super computers working together. Do you know what's a petaflop, Krzysztof Grzelak ?

You saw the link of the proof of what Rein said and he confirmed what Bert said about the 1700 years computing of " a standard computer" as i don't know, your 32Go of Ram.
It's Just a calcul that was done to estimate this time. Have you read the message of the link sent by Rein ?
http://computer-go.org/pipermail/comput ... 10307.html

Sidiki

Krzysztof Grzelak
Posts: 933
Joined: Thu Jun 20, 2013 17:16
Real name: Krzysztof Grzelak

Re: Damage 15.3

Post by Krzysztof Grzelak » Sat Feb 22, 2020 19:02

Sidiki wrote:
Sat Feb 22, 2020 18:51
Why ? We are speaking of neural Network many computer or super computers working together. Do you know what's a petaflop, Krzysztof Grzelak ?

You saw the link of the proof of what Rein said and he confirmed what Bert said about the 1700 years computing of " a standard computer" as i don't know, your 32Go of Ram.
It's Just a calcul that was done to estimate this time. Have you read the message of the link sent by Rein ?
http://computer-go.org/pipermail/comput ... 10307.html

Sidiki
I have reason not to believe in such things.

Sidiki
Posts: 178
Joined: Thu Jan 15, 2015 16:28
Real name: Coulibaly Sidiki

Re: Damage 15.3

Post by Sidiki » Sat Feb 22, 2020 21:55

Krzysztof Grzelak wrote:
Sat Feb 22, 2020 19:02
Sidiki wrote:
Sat Feb 22, 2020 18:51
Why ? We are speaking of neural Network many computer or super computers working together. Do you know what's a petaflop, Krzysztof Grzelak ?

You saw the link of the proof of what Rein said and he confirmed what Bert said about the 1700 years computing of " a standard computer" as i don't know, your 32Go of Ram.
It's Just a calcul that was done to estimate this time. Have you read the message of the link sent by Rein ?
http://computer-go.org/pipermail/comput ... 10307.html

Sidiki
I have reason not to believe in such things.
Even now, you don't tell us why to not believe in such things.
It's like someone tell you that a distance reached to a car at 300 Km/h can take 20 heures to a human at legs if we consider that his max speed is 15 km/h. And even with these data you still saying that this calcul it's wrong.

BertTuyt
Posts: 1436
Joined: Wed Sep 01, 2004 19:42

Re: Damage 15.3

Post by BertTuyt » Sun Feb 23, 2020 11:00

Herewith the actual status of the next test.
I still use the same data set, but I skip 2 out of 3 draws, effectively increasing the win/lose ratio (with a factor of 3).
Below the table and graph. The ELO rating indicates how much Scan is better in comparison with Damage 15.3.

Code: Select all

Games	W	D	L	U	T	ELO
10000	31	127	0	0	158	69
20000	11	147	0	0	158	24
40000	7	151	0	0	158	15
80000					 	 
160000	6	148	1	3	158	11
320000					 	 
640000					 	 
1280000					 	 
elo3.png
elo3.png (36.78 KiB) Viewed 2649 times
It is clearly visible (blue line old test, orange line new line) that initial learning is much faster/better, but that the saturation level seems to be the same.

I will complete the test in the next days.
An interesting research question is , if there is further improvement when one further increases the win/lose ratio (for example do not include any draws), or if there is an optimum.
But most likely I will only work hereafter on different evaluation functions, based upon slightly adapted features and/or pattern regions.

Keep you posted,

Bert

Fabien Letouzey
Posts: 299
Joined: Tue Jul 07, 2015 07:48
Real name: Fabien Letouzey

Re: Damage 15.3

Post by Fabien Letouzey » Sun Feb 23, 2020 12:04

Hi Bert,
BertTuyt wrote:
Sun Feb 23, 2020 11:00
An interesting research question is , if there is further improvement when one further increases the win/lose ratio (for example do not include any draws), or if there is an optimum.
I remember trying skipping draws, calling the label target "Wilo" (win/loss), in hope that this component would be comparable between variants. But no, draws are essential. That was likely with killer draughts, but things can only get worse in ID (throwing away even more).

Congrats on your success with patterns, BTW. It's a rite of passage.

Fabien.

BertTuyt
Posts: 1436
Joined: Wed Sep 01, 2004 19:42

Re: Damage 15.3

Post by BertTuyt » Sun Feb 23, 2020 12:30

Fabien ,thanks for your email.

But the suc6 I now have is to a large extend based upon the willingness of you (sharing your ideas and source code), and Ed (sharing his optimization program).
I also believe that you need draws to better balance the value of weights.
But I think that the draw ratio in my set was rather high (around 90%), whereas I'm now closer to 70% (think this is also the number Ed has in his set).

So the interesting question is what is the right quality of games?
If it is too high you have hardly and mistakes , but with only draws, all weights stay at zero.
When the quality of the training set is lower, you have a better win/lose - draw ratio, but maybe too many blunders which might not support the logistic regression.

Or you could have high quality games, but reduce the draw you use for training, so 30% of the games is decisive.
Not sure if this 30% is an optimum though....

Bert

Post Reply