It is currently Thu Mar 28, 2024 11:12 am

All times are UTC - 8 hours [ DST ]




Post new topic Reply to topic  [ 390 posts ]  Go to page Previous  1 ... 15, 16, 17, 18, 19, 20  Next
Author Message
Offline
 Post subject: Re: Engine Tournament
Post #341 Posted: Sat Dec 21, 2019 6:50 am 
Honinbo

Posts: 10905
Liked others: 3651
Was liked: 3374
q30 wrote:
I use translator only for translation to English of some words while I'm posting message.
So, if You want, that most of people there (who have already written that they aren't native English speakers) understand You right, try to use simple unambiguous terminology without any beautiful, but superfluous words and phrases, please.


Since language appears to be a problem, perhaps it would help to restate what you think the other person said before offering a reply. This can help even when everybody speaks the same language. :)

_________________
The Adkins Principle:
At some point, doesn't thinking have to go on?
— Winona Adkins

Visualize whirled peas.

Everything with love. Stay safe.

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #342 Posted: Sat Dec 28, 2019 6:23 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
The best "heavyweight" neuronet in 2019 year is 14a3a5f70aba55e312af52f97fe44b1376f0b9a966639e8f21ca38333886dd3b details.

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #343 Posted: Sat Dec 28, 2019 6:30 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
Bill Spight wrote:
q30 wrote:
I use translator only for translation to English of some words while I'm posting message.
So, if You want, that most of people there (who have already written that they aren't native English speakers) understand You right, try to use simple unambiguous terminology without any beautiful, but superfluous words and phrases, please.


Since language appears to be a problem, perhaps it would help to restate what you think the other person said before offering a reply. This can help even when everybody speaks the same language. :)

OK, but if restate will be permitted in native language...


Last edited by q30 on Sat Jan 11, 2020 2:17 am, edited 1 time in total.
Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #344 Posted: Sat Jan 11, 2020 2:16 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
The best "middleweight" neuronet in 2019 year is 20b_254_784k_q, but it's obviously weaken, than "welterweight" best nets.
Moreover, the 2019 year winner of "welterweight class" 15b_249a_296k_q overpowered the best of "heavyweight" net (details)...

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #345 Posted: Sat Jan 18, 2020 1:34 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
"Heavyweight" winner of LeelaZero neuronets is stronger, than "middleweight" one (details).

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #346 Posted: Sat Jul 25, 2020 1:23 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
The best "light heavyweight" LeelaZero neuronet in 2019 year was 40b_257a_64k_q (details)

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #347 Posted: Sat Aug 08, 2020 2:03 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
The best LeelaZero "welterweight" file was 15b_257_248k_q in 2019 (details).

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #348 Posted: Sat Aug 15, 2020 2:26 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
The best weight of LeelaZero neuronet was 40b_257a_64k_q in 2019 year (details).
So, the rate of "weight categories" in 2019 was the next:
"bantamweight" <|= 2 ^ 23 B (< 12 MiB) - best_5b.txt;................................................................................(6)
"featherweight" 2 ^ 24 B (12 - 24 MiB) - I haven't;
"lightweight" 2 ^ 25 B (24 - 48 MiB) - LeelaMaster_E08.txt;..........................................................................(5)
"welterweight" 2 ^ 26 B (48 - 96 MiB) - 15b_257_248k_q;.............................................................................(2)
"middleweight" 2 ^ 27 B (96 - 192 MiB) - 20b_254_784k_q;............................................................................(4)
"light heavyweight" 2 ^ 28 B (192 - 384 MiB) - 40b_257a_64k_q;....................................................................(1)
"heavyweight" 2 ^ 29 B (384 - 768 MiB) - 14a3a5f70aba55e312af52f97fe44b1376f0b9a966639e8f21ca38333886dd3b;...(3)
"super heavyweight" >|= 2 ^ 30 B (> 768 MiB) - I haven't.

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #349 Posted: Sat Oct 03, 2020 2:17 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
The rate of Go engines without using GPU after 2019 year was the next (details):

Top level
1) LeelaZero

High level
2) Leela
3) Rayon
4) Hiratuka
5) Zenith

Middle level
6) Pachi_DCNN
7) Ray
8) Pachi
9) MoGo

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #350 Posted: Sat Nov 21, 2020 4:26 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
The rate of "weight category" KataGo winners (details):

"bantamweight"------<|= 2 ^ 23 B (< 12 MiB)-- g170e-b10c128-s1141046784-d204142634.bin----(6);
"featherweight"-----2 ^ 24 B (12 - 24 MiB)--- I haven't;
"lightweight"-------2 ^ 25 B (24 - 48 MiB)--- g170e-b15c192-s1672170752-d466197061.bin----(5);
"welterweight"------2 ^ 26 B (48 - 96 MiB)--- g170e-b20c256x2-s5303129600-d1228401921.bin-(4);
"middleweight"------2 ^ 27 B (96 - 192 MiB)-- g170-b40c256x2-s5095420928-d1229425124.bin--(2);
"light heavyweight"-2 ^ 28 B (192 - 384 MiB)- g170-b30c320x2-s4824661760-d1229536699.bin--(1);
"heavyweight"-------2 ^ 29 B (384 - 768 MiB)- g170e-b40c384x2-s2348692992-d1229892979.bin-(3);
"super heavyweight"->|= 2 ^ 30 B (> 768 MiB)- I haven't.

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #351 Posted: Sat Nov 28, 2020 5:35 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
Katago v1.7.0 isn't stronger, then v1.6.1 (details).

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #352 Posted: Sat Nov 28, 2020 8:38 am 
Lives in sente

Posts: 757
Liked others: 114
Was liked: 916
Rank: maybe 2d
Posted in reply also on github too:

You are right, because v1.7.0 does not add any new features that affect strength, it mostly only adds things like CUDA 11 support and changes to the interface that make analysis tools much more flexible.

However if I understand your link correctly, you are right only by accident, because the number of games you've played is massively far too few to be reliable in determining that one version isn't stronger than another. Please be wary of drawing conclusions from such tiny numbers of games. For example in the past, I have absolutely have had genuinely stronger versions of a bot be losing more than winning even after 50 or 100 games, simply due to getting unlucky with statistical noise, before hundreds and even thousands more games finally showed (almost certainly) that the true winning chance was actually greater than 50% and that the version that was losing more at first was truly the stronger version.

Which of course means that even smaller numbers of games like 8 games, or 4 games, are definitely too few to make any reliable determinations of strength, beyond establishing that neither side is completely outright buggy and disastrously weaker (if the result wasn't entirely lopsided).

---

Also, if the parentheses you have in your weight category list "(1)", "(3)", etc. are meant to be an ordering of equal-compute strength then I think you may have it wrong. From early testing, I recall that that g170-b40c256x2-s5095420928-d1229425124.bin should be stronger than g170-b30c320x2-s4824661760-d1229536699.bin even at equal playouts. It's both faster and smaller and stronger, there's no reason to use the 30-block network.

If you found the 30 block network as stronger, again that might be due to playing too few games to accurately measure. I wouldn't want to give a misleading impression to people picking which network to use based on statistical noise in a tiny sample size.

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #353 Posted: Sat Nov 28, 2020 10:30 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
I'm using equal time on move settings and compute resources (details). With the playouts equal number bigger "end-trained" network must be stronger, than smaller one. But because network with bigger number of blocks (40) has smaller number of somewhat "c" (256), they are almost equal in memory and visits number using in the mentioned conditions. And their strength is equal on practical end user opinion (my tests are doing on this opinion): the score is 5-3. So in this rate (1) and (2) are given formally, for certainty, and the results aren't wrong on mentioned opinion...
But I don't know, are these networks "end-trained" how AlphaZero's one on supercomputer, or they will be upgraded in future, how it's with LeelaZero, whose networks are updated continuously...

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #354 Posted: Sat Feb 13, 2021 3:11 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
The rate of the LeelaZero "weight categories" 2020 year winners (details):
"bantamweight".......<|= 2 ^ 23 B (< 12 MiB) - best_5b.txt..............................................................................(6)
"featherweight"........2 ^ 24 B (12 - 24 MiB) - I haven't
"lightweight"............2 ^ 25 B (24 - 48 MiB) - LeelaMaster_E08.txt....................................................................(5)
"welterweight".........2 ^ 26 B (48 - 96 MiB) - 15b_270_856k_q..........................................................................(2)
"middleweight".........2 ^ 27 B (96 - 192 MiB) -20b_266_168k_q.........................................................................(4)
"light heavyweight"...2 ^ 28 B (192 - 384 MiB)-40b_273d_256k_q.......................................................................(1)
"heavyweight".........2 ^ 29 B (384 - 768 MiB)-14a3a5f70aba55e312af52f97fe44b1376f0b9a966639e8f21ca38333886dd3b.(3)
"super heavyweight".>|= 2 ^ 30 B (> 768 MiB)-I haven't.

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #355 Posted: Tue Feb 16, 2021 11:33 am 
Lives with ko

Posts: 180
Liked others: 15
Was liked: 23
Rank: Beginner
lightvector wrote:
the number of games you've played is massively far too few to be reliable in determining that one version isn't stronger than another.


Don't do that. He won't get it. He has no idea of statistics, but tries to explain the world. To make it even worse he is not able to communicate in english.

Bye, I am off again :lol:

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #356 Posted: Sat Feb 27, 2021 4:52 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
There some has no idea about that for engines end user is not any importance what engine (neuronet) is stronger than another one only in big statistics, because human plays only few (compared with big statistics) games...

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #357 Posted: Sat Feb 27, 2021 4:54 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
KataGo wins LeelaZero in all corresponding (both by "weight" and its rate) categories (details).

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #358 Posted: Sat Mar 06, 2021 4:38 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
KataGo v.1.8.0 improvements doesn't make it stronger for end user opinion (details).

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #359 Posted: Sat Mar 06, 2021 7:28 am 
Lives in sente

Posts: 757
Liked others: 114
Was liked: 916
Rank: maybe 2d
q30 wrote:
There some has no idea about that for engines end user is not any importance what engine (neuronet) is stronger than another one only in big statistics, because human plays only few (compared with big statistics) games...


There is an idea here that you might not be taking into account:
The best way to test what will be better for end users who play few games... is NOT to run few games yourself, but instead is to run "big statistics".

Why? Well for example, if you run only a small-game test and mistakenly think the version that in truth wins 47% is better than the version that in truth wins 52% because your test got unlucky, then out of every 100 users who follow your recommendation and run one game or one analysis, on average 5 of them will get unnecessarily worse results due to your bad luck. Even if it only makes a difference for a few users, better to use enough games so that your own luck is not an issue.

Top
 Profile  
 
Offline
 Post subject: Re: Engine Tournament
Post #360 Posted: Sat Mar 06, 2021 9:13 am 
Lives with ko

Posts: 135
Liked others: 1
Was liked: 1
Rank: 30 kyu
In mentioned case the result is "practically equivalent". So recommendation is: You can download the strongest one in this rate- it will be not any practically noticeable weaker, than other in this rate...

More important is performance*time equivalence of tests to real games, because of the U-shaped score dependence on it, that was given earlier in this topic.

Top
 Profile  
 
Display posts from previous:  Sort by  
Post new topic Reply to topic  [ 390 posts ]  Go to page Previous  1 ... 15, 16, 17, 18, 19, 20  Next

All times are UTC - 8 hours [ DST ]


Who is online

Users browsing this forum: No registered users and 1 guest


You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot post attachments in this forum

Search for:
Jump to:  
Powered by phpBB © 2000, 2002, 2005, 2007 phpBB Group