Lc0 question

Discussion of anything and everything relating to chess playing software and machines.

Moderators: hgm, Harvey Williamson, bob

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
User avatar
mclane
Posts: 15706
Joined: Thu Mar 09, 2006 5:40 pm
Location: US of Europe, germany
Full name: Thorsten Czub
Contact:

Re: Lc0 question

Post by mclane » Sun Jul 07, 2019 2:00 pm

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 ?
What seems like a fairy tale today may be reality tomorrow.
Here we have a fairy tale of the day after tomorrow....

Modern Times
Posts: 2326
Joined: Thu Jun 07, 2012 9:02 pm

Re: Lc0 question

Post by Modern Times » Sun Jul 07, 2019 2:04 pm

Nay Lin Tun wrote:
Sun Jul 07, 2019 1:50 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.
.

Opinions expressed here are my own, and not necessarily those of the CCRL Group.

User avatar
kranium
Posts: 1824
Joined: Thu May 29, 2008 8:43 am

Re: Lc0 question

Post by kranium » Sun Jul 07, 2019 2:39 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.

jp
Posts: 603
Joined: Mon Apr 23, 2018 5:54 am

Re: Lc0 question

Post by jp » Sun Jul 07, 2019 3:11 pm

chrisw wrote:
Sun Jul 07, 2019 8:25 am
mclane wrote:
Sun Jul 07, 2019 6:56 am
Stockfish plays machine chess, although developed by humans.
LC0 plays human chess, although developed by a machine.

The philosophical impact of this cannot be underestimated.
Dispute that LCZero plays human chess. It plays chess in a way that humans would like to imagine they play chess.
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.

User avatar
kranium
Posts: 1824
Joined: Thu May 29, 2008 8:43 am

Re: Lc0 question

Post by kranium » Sun Jul 07, 2019 3:43 pm

jp wrote:
Sun Jul 07, 2019 3:11 pm
Humans' best chance of distinguishing the engines is from their bad opening or endgame play, not their good middlegame play.
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.

chrisw
Posts: 1584
Joined: Tue Apr 03, 2012 2:28 pm

Re: Lc0 question

Post by chrisw » Sun Jul 07, 2019 3:53 pm

jp wrote:
Sun Jul 07, 2019 3:11 pm
chrisw wrote:
Sun Jul 07, 2019 8:25 am
mclane wrote:
Sun Jul 07, 2019 6:56 am
Stockfish plays machine chess, although developed by humans.
LC0 plays human chess, although developed by a machine.

The philosophical impact of this cannot be underestimated.
Dispute that LCZero plays human chess. It plays chess in a way that humans would like to imagine they play chess.
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.
Well, that looks like a fun classification problem for a net. I don't suppose anyone ever tried it.
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 ....

Modern Times
Posts: 2326
Joined: Thu Jun 07, 2012 9:02 pm

Re: Lc0 question

Post by Modern Times » Sun Jul 07, 2019 4:10 pm

kranium wrote:
Sun Jul 07, 2019 2:39 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.
Well... 32930 is an old net, they have improved maybe +50 Elo or so since then
.

Opinions expressed here are my own, and not necessarily those of the CCRL Group.

User avatar
kranium
Posts: 1824
Joined: Thu May 29, 2008 8:43 am

Re: Lc0 question

Post by kranium » Sun Jul 07, 2019 4:22 pm

Modern Times wrote:
Sun Jul 07, 2019 4:10 pm
kranium wrote:
Sun Jul 07, 2019 2:39 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.
Well... 32930 is an old net, they have improved maybe +50 Elo or so since then
for what it's worth, neither version is recent...

jp
Posts: 603
Joined: Mon Apr 23, 2018 5:54 am

Re: Lc0 question

Post by jp » Sun Jul 07, 2019 4:31 pm

chrisw wrote:
Sun Jul 07, 2019 3:53 pm
jp wrote:
Sun Jul 07, 2019 3:11 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.
Well, that looks like a fun classification problem for a net. I don't suppose anyone ever tried it.
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 ....
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.

ThatsIt
Posts: 895
Joined: Thu Mar 09, 2006 1:11 pm
Contact:

Re: Lc0 question

Post by ThatsIt » Sun Jul 07, 2019 4:38 pm

kranium wrote:
Sun Jul 07, 2019 4:22 pm
Modern Times wrote:
Sun Jul 07, 2019 4:10 pm
kranium wrote:
Sun Jul 07, 2019 2:39 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.
Well... 32930 is an old net, they have improved maybe +50 Elo or so since then
for what it's worth, neither version is recent...
Hi !

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)

Post Reply