Oh my god. Another „is LC0 stronger then Stockfish“ debate.
It’s so boring,
And how to choose the hardware. To make it possible.
Hardware. How boring.
I prefer decreasing the speed of hardware.
I don’t understand that you want faster hardware. Why ?
Lc0 question
Moderators: hgm, Rebel, chrisw
-
- Posts: 18748
- Joined: Thu Mar 09, 2006 6:40 pm
- Location: US of Europe, germany
- Full name: Thorsten Czub
Re: Lc0 question
What seems like a fairy tale today may be reality tomorrow.
Here we have a fairy tale of the day after tomorrow....
Here we have a fairy tale of the day after tomorrow....
-
- Posts: 3546
- Joined: Thu Jun 07, 2012 11:02 pm
Re: Lc0 question
Nay Lin Tun wrote: ↑Sun Jul 07, 2019 3:50 pm
1. CCRL net was using 20x256 which is suitable for stronger cards only. ( I saw in discord chat that they sent 10x128 net for CCRL hardware. Once they test that net , the result may change)
No-one has ever sent us anything to test. They are more interested in the likes of TCEC and CCC and monster hardware.
However at 40/40 (40/15) the 20x256 net should be fine on the GTX1050 I'd have thought.
-
- Posts: 2129
- Joined: Thu May 29, 2008 10:43 am
Re: Lc0 question
For what it's worth, CEGT also has SF on top
(and these are 1 CPU results)
http://www.cegt.net/40_4_Ratinglist/40_ ... liste.html
I suppose there's some confusing explanation...
I tend to just look at the list and use Elo ranking to make a determination.
(and these are 1 CPU results)
http://www.cegt.net/40_4_Ratinglist/40_ ... liste.html
I suppose there's some confusing explanation...
I tend to just look at the list and use Elo ranking to make a determination.
-
- Posts: 1470
- Joined: Mon Apr 23, 2018 7:54 am
Re: Lc0 question
Yes, that's correct. It plays chess that many humans can easily make explanatory stories about, and the humans then attach human qualities to those moves, e.g. "positional", which only makes any sense for how humans think about chess, not engines, which just calculate.
But if we made a test of carefully chosen middlegame sections, probably no one would be able to distinguish which were AB and which were NN moves. Humans' best chance of distinguishing the engines is from their bad opening or endgame play, not their good middlegame play.
-
- Posts: 2129
- Joined: Thu May 29, 2008 10:43 am
Re: Lc0 question
Engines play the openings and endgames badly?
But, playing against the strongest humans, SF and/or LC0 would not lose a single game, and probably give up very few draws, if any...
even against the most 'opening' savvy/prepared GM.
How have some humans determined these engines are playing badly? I don't get it.
Seems a bit pretentious...or some desperate need to remain relevant.
-
- Posts: 4315
- Joined: Tue Apr 03, 2012 4:28 pm
Re: Lc0 question
Well, that looks like a fun classification problem for a net. I don't suppose anyone ever tried it.jp wrote: ↑Sun Jul 07, 2019 5:11 pmYes, that's correct. It plays chess that many humans can easily make explanatory stories about, and the humans then attach human qualities to those moves, e.g. "positional", which only makes any sense for how humans think about chess, not engines, which just calculate.
But if we made a test of carefully chosen middlegame sections, probably no one would be able to distinguish which were AB and which were NN moves. Humans' best chance of distinguishing the engines is from their bad opening or endgame play, not their good middlegame play.
Data requirement - a lot of (human, AB, NNet) PGNs
process moves 15-40 (say) and save for each position
(fen_string, move, player type)
gather up, let's guess, 100 million positions for each type of player. split into a training and a test set.
train on training_set(fen_string, move). Quite possibly using a LC0 type resnet. predict type of player on a test set.
check result against actuality.
I guess, it would partly "learn" on both the type of position, and the "move played". Might work ....
-
- Posts: 3546
- Joined: Thu Jun 07, 2012 11:02 pm
Re: Lc0 question
Well... 32930 is an old net, they have improved maybe +50 Elo or so since thenkranium wrote: ↑Sun Jul 07, 2019 4:39 pm For what it's worth, CEGT also has SF on top
(and these are 1 CPU results)
http://www.cegt.net/40_4_Ratinglist/40_ ... liste.html
I suppose there's some confusing explanation...
I tend to just look at the list and use Elo ranking to make a determination.
-
- Posts: 2129
- Joined: Thu May 29, 2008 10:43 am
Re: Lc0 question
for what it's worth, neither version is recent...Modern Times wrote: ↑Sun Jul 07, 2019 6:10 pmWell... 32930 is an old net, they have improved maybe +50 Elo or so since thenkranium wrote: ↑Sun Jul 07, 2019 4:39 pm For what it's worth, CEGT also has SF on top
(and these are 1 CPU results)
http://www.cegt.net/40_4_Ratinglist/40_ ... liste.html
I suppose there's some confusing explanation...
I tend to just look at the list and use Elo ranking to make a determination.
-
- Posts: 1470
- Joined: Mon Apr 23, 2018 7:54 am
Re: Lc0 question
Yeah, I was thinking of something simpler, just whether humans given a bunch of game fragments can guess whether the players are AB or NN engines. I think the humans would fail.chrisw wrote: ↑Sun Jul 07, 2019 5:53 pmWell, that looks like a fun classification problem for a net. I don't suppose anyone ever tried it.jp wrote: ↑Sun Jul 07, 2019 5:11 pm But if we made a test of carefully chosen middlegame sections, probably no one would be able to distinguish which were AB and which were NN moves. Humans' best chance of distinguishing the engines is from their bad opening or endgame play, not their good middlegame play.
Data requirement - a lot of (human, AB, NNet) PGNs
process moves 15-40 (say) and save for each position
(fen_string, move, player type)
gather up, let's guess, 100 million positions for each type of player. split into a training and a test set.
train on training_set(fen_string, move). Quite possibly using a LC0 type resnet. predict type of player on a test set.
check result against actuality.
I guess, it would partly "learn" on both the type of position, and the "move played". Might work ....
-
- Posts: 991
- Joined: Thu Mar 09, 2006 2:11 pm
Re: Lc0 question
Hi !kranium wrote: ↑Sun Jul 07, 2019 6:22 pmfor what it's worth, neither version is recent...Modern Times wrote: ↑Sun Jul 07, 2019 6:10 pmWell... 32930 is an old net, they have improved maybe +50 Elo or so since thenkranium wrote: ↑Sun Jul 07, 2019 4:39 pm For what it's worth, CEGT also has SF on top
(and these are 1 CPU results)
http://www.cegt.net/40_4_Ratinglist/40_ ... liste.html
I suppose there's some confusing explanation...
I tend to just look at the list and use Elo ranking to make a determination.
http://cegt.forumieren.com/t1152-testin ... da-nw42668
The next update for our 40/4 ratinglist will be online next week, perhaps on Thursday.
Best wishes,
G.S.
(CEGT team)