Page 6 of 9
Re: Leela has a new version
Posted: Wed Feb 22, 2017 1:00 pm
by Garf
Code: Select all
50 Leela-0.9-1c1g 3320 107 107 154 67% 2935 0%
62 Zen-11.4n-1c 3244 40 40 633 71% 2861 0%
76 ELO ahead of the commercial Zen
So Leela (with GPU) is between half a stone and a stone stronger than Zenith Go 6. johnsmith called it, Gomoto was wrong.
Re: Leela has a new version
Posted: Wed Feb 22, 2017 1:17 pm
by goame
Garf wrote:Code: Select all
50 Leela-0.9-1c1g 3320 107 107 154 67% 2935 0%
62 Zen-11.4n-1c 3244 40 40 633 71% 2861 0%
76 ELO ahead of the commercial Zen
So Leela (with GPU) is between half a stone and a stone stronger than Zenith Go 6. johnsmith called it, Gomoto was wrong.
Is it possiple to use 4x nvidia geforce gtx 1080 ti with Leela?
And how big is the benefit from 1 to 2 to 4 gpus?
Re: Leela has a new version
Posted: Wed Feb 22, 2017 1:19 pm
by Garf
goame wrote:
Is it possiple to use 4x nvidia geforce gtx 1080 ti with Leela?
No, because you cannot buy those yet
Re: Leela has a new version
Posted: Wed Feb 22, 2017 6:30 pm
by pookpooi
It's hard to compare between Zen 6 (11.4) and Leela 0.9 in cgos, While Leela 1c1g is above Zen 1c by 76 elo, it's below Zen 2c by 77 elo. We need Leela without GPU (maybe 1 or 2 c or both) to have a better comparison.
Re: Leela has a new version
Posted: Wed Feb 22, 2017 7:31 pm
by yoyoma
I saw somewhere (compgo?) that the Leela author said he is not running Leela on CGOS. So it is an unofficial test by someone else.
Re: Leela has a new version
Posted: Thu Feb 23, 2017 1:49 am
by Garf
yoyoma wrote:I saw somewhere (compgo?) that the Leela author said he is not running Leela on CGOS. So it is an unofficial test by someone else.
I think it's a test by pookpooi actually.
The most interesting would probably be to run Leela with 1 cpu and no GPU. Then we know how much the GPU is worth. I'm not sure it affects the conclusion vs Zenith because Zenith can't use the GPU anyway, but that is not Leela's fault.
Zen 14.0 is now also on CGOS!
Re: Leela has a new version
Posted: Thu Feb 23, 2017 2:13 am
by pookpooi
If it was test by me I wouldn't use gpu in the first place
Re: Leela has a new version
Posted: Thu Feb 23, 2017 5:18 am
by Gomoto
Gomoto was wrong.
not true, he
was right
(Leela 0.8 was not stronger than Zenith 6)
Re: Leela has a new version
Posted: Thu Feb 23, 2017 7:28 am
by Gomoto
Leela 0.9.0 defeats Zen again (this time without pondering, still using much more time than Zen)
Zenit Go 6 [setting: 20 seconds per move]
Leela 0.9.0 GPU [setting: 20 minutes for the game] (used more than 40 minutes)
CPU Intel 2500K GPU Nvidia GTX 970
Leela's advice towards Zen: Move 91 should have been at J10. Zen looses with an empty triangle
(52% => 47% win)
Zen was still quite sure to win the game at this time (60% win)
Re: Leela has a new version
Posted: Thu Feb 23, 2017 1:28 pm
by Pippen
This is a typical diagramm of an opening I play with pretty good success. After analyzing it for 20 minutes, Leela gives it only about 41.5% for White with the slow 'a' as best continuation for White.
I am interested in what CS or Zen say to this position, and how they would continue for White. I usually continue with 'b' or 'c'.
$$B
$$ +---------------------------------------+
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . O . . O . . . X . . . . . |
$$ | . . . X . . . . . , . . . . . X . a . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . O . . |
$$ | . . X . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . , . . . . . , . . . . . b . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . c . . |
$$ | . . X . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . X . . . . . , . . . . . O . . . |
$$ | . . . . . O . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ +---------------------------------------+
- Click Here To Show Diagram Code
[go]$$B
$$ +---------------------------------------+
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . O . . O . . . X . . . . . |
$$ | . . . X . . . . . , . . . . . X . a . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . O . . |
$$ | . . X . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . , . . . . . , . . . . . b . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . c . . |
$$ | . . X . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . X . . . . . , . . . . . O . . . |
$$ | . . . . . O . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ +---------------------------------------+[/go]
Re: Leela has a new version
Posted: Fri Feb 24, 2017 3:36 am
by Garf
Given that you are 5D, can't you just play this out vs Leela, and see what happens after a bunch of moves? Either it'll show you a refutation, or its score will go towards 50%.
Re: Leela has a new version
Posted: Fri Feb 24, 2017 6:24 am
by johnsmith
Pippen wrote:This is a typical diagramm of an opening I play with pretty good success. After analyzing it for 20 minutes, Leela gives it only about 41.5% for White with the slow 'a' as best continuation for White.
I am interested in what CS or Zen say to this position, and how they would continue for White. I usually continue with 'b' or 'c'.
$$B
$$ +---------------------------------------+
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . O . . O . . . X . . . . . |
$$ | . . . X . . . . . , . . . . . X . a . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . O . . |
$$ | . . X . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . , . . . . . , . . . . . b . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . c . . |
$$ | . . X . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . X . . . . . , . . . . . O . . . |
$$ | . . . . . O . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ +---------------------------------------+
- Click Here To Show Diagram Code
[go]$$B
$$ +---------------------------------------+
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . O . . O . . . X . . . . . |
$$ | . . . X . . . . . , . . . . . X . a . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . O . . |
$$ | . . X . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . , . . . . . , . . . . . b . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . c . . |
$$ | . . X . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . X . . . . . , . . . . . O . . . |
$$ | . . . . . O . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ +---------------------------------------+[/go]
Zen suggest k4 with 53% for white. But I'd rather trust Leela. If you look more closely at its Net Win %, it says w is winning by 28% (i.e. losing the game) which is, I believe, more accurate than Win %. At least that's what those Deep Mind guys were looking at when they were testing AlphaGo.
Re: Leela has a new version
Posted: Fri Feb 24, 2017 7:42 am
by Pippen
Zen suggest k4 with 53% for white. But I'd rather trust Leela. If you look more closely at its Net Win %, it says w is winning by 28% (i.e. losing the game) which is, I believe, more accurate than Win %. At least that's what those Deep Mind guys were looking at when they were testing AlphaGo.
Interesting. How can there be such a difference between the two probabilities?
I rechecked and here is what Leela says in detail: D2(best move): Win% 42, MC win% 51.7, Net win% 31.8, Net prob% 29. What is the meaning of all these numbers anyway? I always thought that win% matters, the rest not so much.
Re: Leela has a new version
Posted: Fri Feb 24, 2017 7:49 am
by Uberdude
Did everyone set the same komi, and ensure the different bots all respect it?
Re: Leela has a new version
Posted: Fri Feb 24, 2017 9:22 am
by Bill Spight
Pippen wrote:This is a typical diagramm of an opening I play with pretty good success. After analyzing it for 20 minutes, Leela gives it only about 41.5% for White with the slow 'a' as best continuation for White.
I am interested in what CS or Zen say to this position, and how they would continue for White. I usually continue with 'b' or 'c'.
$$B
$$ +---------------------------------------+
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . O . . O . . . X . . . . . |
$$ | . . . X . . . . . , . . . . . X . a . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . O . . |
$$ | . . X . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . , . . . . . , . . . . . b . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . c . . |
$$ | . . X . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . X . . . . . , . . . . . O . . . |
$$ | . . . . . O . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ +---------------------------------------+
- Click Here To Show Diagram Code
[go]$$B
$$ +---------------------------------------+
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . O . . O . . . X . . . . . |
$$ | . . . X . . . . . , . . . . . X . a . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . O . . |
$$ | . . X . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . , . . . . . , . . . . . b . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . c . . |
$$ | . . X . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . X . . . . . , . . . . . O . . . |
$$ | . . . . . O . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ +---------------------------------------+[/go]
BTW, I like "a". It is pretty much sente, and after White "b", instead, it is a good point for Black.