LCZero is confusing

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.
Jouni
Posts: 1856
Joined: Wed Mar 08, 2006 7:15 pm

LCZero is confusing

Post by Jouni » Sat Mar 24, 2018 5:01 pm

Here people speak about ELO 500, but elsewhere http://162.217.248.187/ I see ELO 3650!?!?
Jouni

mkchan
Posts: 72
Joined: Thu Oct 06, 2016 7:17 pm
Location: India
Contact:

Re: LCZero is confusing

Post by mkchan » Sat Mar 24, 2018 6:03 pm

Jouni wrote:Here people speak about ELO 500, but elsewhere http://162.217.248.187/ I see ELO 3650!?!?
I think here we are referring to a common rating list like CCRL or CEGT etc, but there they have a different pool of players (likely just older versions of LC0) so you see it being 3650 rated in that pool

User avatar
CMCanavessi
Posts: 735
Joined: Thu Dec 28, 2017 3:06 pm
Location: Argentina

Re: LCZero is confusing

Post by CMCanavessi » Sat Mar 24, 2018 6:05 pm

Jouni wrote:Here people speak about ELO 500, but elsewhere http://162.217.248.187/ I see ELO 3650!?!?

That 3000+ number comes from self-play games, with is absolutely useless when compared to any rating list.

Real elo of the current network generation is around 1300-1500 elo, depending on hardware and time control.
Follow my tournament and some Leela gauntlets live at http://twitch.tv/ccls

User avatar
AdminX
Posts: 4948
Joined: Mon Mar 13, 2006 1:34 pm
Location: Acworth, GA
Contact:

Re: LCZero is confusing

Post by AdminX » Sat Mar 24, 2018 6:22 pm

CMCanavessi wrote:
Jouni wrote:Here people speak about ELO 500, but elsewhere http://162.217.248.187/ I see ELO 3650!?!?

That 3000+ number comes from self-play games, with is absolutely useless when compared to any rating list.

Real elo of the current network generation is around 1300-1500 elo, depending on hardware and time control.
Well that makes sense, as there is no way in hell I could have beat a 3000+ computer on my 1st attempt. :D
"Good decisions come from experience, and experience comes from bad decisions."
__________________________________________________________________
Ted Summers

Dann Corbit
Posts: 8965
Joined: Wed Mar 08, 2006 7:57 pm
Location: Redmond, WA USA
Contact:

Re: LCZero is confusing

Post by Dann Corbit » Sat Mar 24, 2018 7:59 pm

The number Elo is meaningless except against the competition in a pool.
The high Elo number is against a random mover.

It will take a long time for LCZero to get to SF level.

The interesting thing is the big, big gains.
We will see if that continues.
I think it is time for a bigger net. Now we see a lot of failures and a slower gain.
Taking ideas is not a vice, it is a virtue. We have another word for this. It is called learning.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.

User avatar
lucasart
Posts: 2995
Joined: Mon May 31, 2010 11:29 am
Full name: lucasart
Contact:

Re: LCZero is confusing

Post by lucasart » Sun Mar 25, 2018 5:45 am

Dann Corbit wrote:The number Elo is meaningless except against the competition in a pool.
The high Elo number is against a random mover.

It will take a long time for LCZero to get to SF level.

The interesting thing is the big, big gains.
We will see if that continues.
I think it is time for a bigger net. Now we see a lot of failures and a slower gain.
I'm not convinced it's possible, even with infinite resources thrown at it. Already we see that lczero progress is showing strongly diminishing returns. Eventually we'll reach an asymptotic elo level, and I'm ready to bet it will be nowhere close to SF.

I don't think people realize just how enormous the gap is between lczero and SF. It seems to be taken for granted that lczero will reach SF level, and that it's only a matter of time. I don't think so.

But let's wait and see
Theory and practice sometimes clash. And when that happens, theory loses. Every single time.

CheckersGuy
Posts: 273
Joined: Wed Aug 24, 2016 7:49 pm

Re: LCZero is confusing

Post by CheckersGuy » Sun Mar 25, 2018 11:27 am

lucasart wrote:
Dann Corbit wrote:The number Elo is meaningless except against the competition in a pool.
The high Elo number is against a random mover.

It will take a long time for LCZero to get to SF level.

The interesting thing is the big, big gains.
We will see if that continues.
I think it is time for a bigger net. Now we see a lot of failures and a slower gain.
I'm not convinced it's possible, even with infinite resources thrown at it. Already we see that lczero progress is showing strongly diminishing returns. Eventually we'll reach an asymptotic elo level, and I'm ready to bet it will be nowhere close to SF.

I don't think people realize just how enormous the gap is between lczero and SF. It seems to be taken for granted that lczero will reach SF level, and that it's only a matter of time. I don't think so.

But let's wait and see
The current net with 6 blocks will eventuall stall that's perty obvious but there is nothing that can stop us from going 10,20 blocks once that happens :D

Henk
Posts: 5262
Joined: Mon May 27, 2013 8:31 am

Re: LCZero is confusing

Post by Henk » Sun Mar 25, 2018 4:24 pm

Were the alpha zero games the most expensive chess games ever played?

User avatar
hgm
Posts: 22588
Joined: Fri Mar 10, 2006 9:06 am
Location: Amsterdam
Full name: H G Muller
Contact:

Re: LCZero is confusing

Post by hgm » Sun Mar 25, 2018 4:37 pm

Stockfish development has been much more expensive, not?

I guess Deep Blue must hold the record, as it used massive hardware that was no good for anything else.

Henk
Posts: 5262
Joined: Mon May 27, 2013 8:31 am

Re: LCZero is confusing

Post by Henk » Sun Mar 25, 2018 4:50 pm

I mean the price per recorded game. The more Stockfish games were recorded the lower the price/value per game.

Post Reply