If you are really interested in the project, and how it worked, you should not 'guess' what Google did, or 'stumble' on the graph they published and just read their paper and the countless articles on it.yanquis1972 wrote: ↑Tue May 15, 2018 9:03 pm did want to add that just after i posted that, i watched a game against rybka 3 that quickly boiled down to an early endgame. rybka evaluated drawish & stayed there, leela +2 or so (ended drawn). i realized the answer there is pretty obvious too; not every game contains an endgame, but most would've, & the large majority probably ended decisively.
also forgot to mention the other hardware aspect to the tactical problem; while we're waiting for millions of games & hoping she stumbles upon the solution often enough to learn it, i'm guessing google used training h/w that could calculate several orders beyond what lc0 does. but i'm hopefully wrong & it was volume-focused.
stumbled on this graph (re strength vs stockfish based on time per move) which is interesting as well
LCZero: Progress and Scaling. Relation to CCRL Elo
Moderators: hgm, Rebel, chrisw
-
- Posts: 3019
- Joined: Wed Mar 08, 2006 9:57 pm
- Location: Rio de Janeiro, Brazil
Re: LCZero: Progress and Scaling. Relation to CCRL Elo
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."
-
- Posts: 1470
- Joined: Mon Apr 23, 2018 7:54 am
Re: LCZero: Progress and Scaling. Relation to CCRL Elo
Good question, though, about generated LC0 training games vs generated AZ training games. (Time/nps per move comparison?)
-
- Posts: 1766
- Joined: Wed Jun 03, 2009 12:14 am
Re: LCZero: Progress and Scaling. Relation to CCRL Elo
then i'm not 'really' interested.Albert Silver wrote: ↑Tue May 15, 2018 10:09 pmIf you are really interested in the project, and how it worked, you should not 'guess' what Google did, or 'stumble' on the graph they published and just read their paper and the countless articles on it.yanquis1972 wrote: ↑Tue May 15, 2018 9:03 pm did want to add that just after i posted that, i watched a game against rybka 3 that quickly boiled down to an early endgame. rybka evaluated drawish & stayed there, leela +2 or so (ended drawn). i realized the answer there is pretty obvious too; not every game contains an endgame, but most would've, & the large majority probably ended decisively.
also forgot to mention the other hardware aspect to the tactical problem; while we're waiting for millions of games & hoping she stumbles upon the solution often enough to learn it, i'm guessing google used training h/w that could calculate several orders beyond what lc0 does. but i'm hopefully wrong & it was volume-focused.
stumbled on this graph (re strength vs stockfish based on time per move) which is interesting as well
-
- Posts: 12038
- Joined: Mon Jul 07, 2008 10:50 pm
Re: LCZero: Progress and Scaling. Relation to CCRL Elo
so this nightmare may soon be over.Laskos wrote:
I just posted in this thread the result for ID292, it is the strongest ever (the standard v0.10 CPU and GPU build on master).
(although perhaps I am taking this too seriously)
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: LCZero: Progress and Scaling. Relation to CCRL Elo
He would also know that particular Figure 2 is totally bogus at least concerning SF's performance.Albert Silver wrote: ↑Tue May 15, 2018 10:09 pm If you are really interested in the project, and how it worked, you should not 'guess' what Google did, or 'stumble' on the graph they published and just read their paper and the countless articles on it.
-
- Posts: 1470
- Joined: Mon Apr 23, 2018 7:54 am
-
- Posts: 1766
- Joined: Wed Jun 03, 2009 12:14 am
Re: LCZero: Progress and Scaling. Relation to CCRL Elo
do they say "this graph is bogus btw" in their own paper, or would i have to read the dozens of articles to find that?
i guess the main problem is, while chess & chess engines fascinate me & are an on/off hobby, i have no knowledge in the sciences. did i miss a forum rule? is there one particular degree i should pursue or will i need a couple? is post-grad at least recommended? would appreciate any further advice on what i need to do before posting on the internet.
i guess the main problem is, while chess & chess engines fascinate me & are an on/off hobby, i have no knowledge in the sciences. did i miss a forum rule? is there one particular degree i should pursue or will i need a couple? is post-grad at least recommended? would appreciate any further advice on what i need to do before posting on the internet.
-
- Posts: 1470
- Joined: Mon Apr 23, 2018 7:54 am
Re: LCZero: Progress and Scaling. Relation to CCRL Elo
That would make the paper worth reading.yanquis1972 wrote: ↑Wed May 16, 2018 11:24 am do they say "this graph is bogus btw" in their own paper, or would i have to read the dozens of articles to find that?
-
- Posts: 52
- Joined: Sat Mar 24, 2018 4:18 pm
Re: LCZero: Progress and Scaling. Relation to CCRL Elo
Then I have a question that I already asked before. Can you show measured numbers of true SF8 scaling on 64 cores for i.e. 1s / move vs 1min / move? Something other than your word that would prove your claim.Milos wrote: ↑Wed May 16, 2018 2:32 amHe would also know that particular Figure 2 is totally bogus at least concerning SF's performance.Albert Silver wrote: ↑Tue May 15, 2018 10:09 pm If you are really interested in the project, and how it worked, you should not 'guess' what Google did, or 'stumble' on the graph they published and just read their paper and the countless articles on it.
-
- Posts: 1346
- Joined: Sat Apr 19, 2014 1:47 pm
Re: LCZero: Progress and Scaling. Relation to CCRL Elo
based on selfplay testing, I see progress are coming back and fast now ! I can raise my hope again.