TCEC Question
Moderators: hgm, Rebel, chrisw
-
- Posts: 1080
- Joined: Fri Sep 16, 2016 6:55 pm
- Location: USA/Minnesota
- Full name: Leo Anger
-
- Posts: 12542
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Re: TCEC Question
In less than 1000 games practically any outcome is possible amongst approximate equals.
I guess that they are very close to equal, but SF had some fortunate outcomes.
And if SF is stronger, it is not by an enormous margain, as evidenced by the draw count.
I guess that they are very close to equal, but SF had some fortunate outcomes.
And if SF is stronger, it is not by an enormous margain, as evidenced by the draw count.
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.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
-
- Posts: 1080
- Joined: Fri Sep 16, 2016 6:55 pm
- Location: USA/Minnesota
- Full name: Leo Anger
-
- Posts: 2041
- Joined: Wed Mar 08, 2006 8:30 pm
Re: TCEC Question
Any idea if TCEC-hardware wise, the current Lc0-Stockfish contest is "fair" ?Dann Corbit wrote: ↑Sun Jun 28, 2020 4:16 am And if SF is stronger, it is not by an enormous margain, as evidenced by the draw count.
Looking for some LeelaRatio clues, I noticed that going out of book, the Stockfish Knodes/sec were more than 2000 times those of Lc0. Isn't that a bit much (for fairness...) ?
-
- Posts: 1080
- Joined: Fri Sep 16, 2016 6:55 pm
- Location: USA/Minnesota
- Full name: Leo Anger
Re: TCEC Question
I haven't heard anyone complaining about the fairness for a long time. I think they have it set up fair myself.ernest wrote: ↑Mon Jun 29, 2020 2:08 amAny idea if TCEC-hardware wise, the current Lc0-Stockfish contest is "fair" ?Dann Corbit wrote: ↑Sun Jun 28, 2020 4:16 am And if SF is stronger, it is not by an enormous margain, as evidenced by the draw count.
Looking for some LeelaRatio clues, I noticed that going out of book, the Stockfish Knodes/sec were more than 2000 times those of Lc0. Isn't that a bit much (for fairness...) ?
"The hardware for CPU engines was doubled to 88 cores, while the hardware for GPU engines was raised to 4 RTX 2080 Ti's."
Advanced Micro Devices fan.
-
- Posts: 511
- Joined: Sun Apr 26, 2020 11:40 pm
- Full name: Brian D. Smith
Re: TCEC Question
I think the proverbial 'sample size' answer just kind of begs the question.Dann Corbit wrote: ↑Sun Jun 28, 2020 4:16 am In less than 1000 games practically any outcome is possible amongst approximate equals.
I guess that they are very close to equal, but SF had some fortunate outcomes.
And if SF is stronger, it is not by an enormous margain, as evidenced by the draw count.
What does "fortunate" mean? Did LZ0 stay out late partying the night before?
After 71 games SF leads 37.5 vs 33.5 (and game 72 looks like it will end in the Fish's favor as well...). A 4 to 5 pt lead at this point is actually reasonably significant. That said, there are more games to be played and Game 72 has LCZero defending the Latvian Counter Gambit...which is bad. Has SF yet to defend it? I don't know. The Devil is in the details.
EDIT: It has, the game before and SF lost...just as LCZero looks to at the moment.
-
- Posts: 2041
- Joined: Wed Mar 08, 2006 8:30 pm
-
- Posts: 4556
- Joined: Tue Jul 03, 2007 4:30 am
Re: TCEC Question
The "nodes" of Lc0 have absolutely nothing to do with the "nodes" of Stockfish because the architectures of both programs are completely different. Note the definition of NPS:
Nodes per second, including NNCache hits and terminal node hits, but excluding nodes carried over from tree reuse. In other words, total playouts generated per second.
Leela nodes = playouts (Stockfish doesn't do playouts at all)
-
- Posts: 2041
- Joined: Wed Mar 08, 2006 8:30 pm
Re: TCEC Question
Yes, but LeelaRatio (one of the tools for "fairness") is precisely based on ratio of Knodes/sec...Ovyron wrote: ↑Mon Jun 29, 2020 2:53 amThe "nodes" of Lc0 have absolutely nothing to do with the "nodes" of Stockfish because the architectures of both programs are completely different. Note the definition of NPS:
Nodes per second, including NNCache hits and terminal node hits, but excluding nodes carried over from tree reuse. In other words, total playouts generated per second.
Leela nodes = playouts (Stockfish doesn't do playouts at all)
Admittedly, not everybody likes LeelaRatio...
-
- Posts: 4556
- Joined: Tue Jul 03, 2007 4:30 am
Re: TCEC Question
Yeah, we can't even have these discussions without putting quotes around the word "fairness."
It's like trying to make a Megahertz battle against a Megabyte "fair." People have to get into their heads these are different things.
It's like trying to make a Megahertz battle against a Megabyte "fair." People have to get into their heads these are different things.