TalkChess.com

I have an even simpler modification, but with a scoring modification in addition. Only Black is not allowed to castle and the Draws are adjudicated as Black wins. You have an even simpler modification? That is my NBC-Armageddon openings idea . Not yours. I released it in August 2019, with 4 opening...

My test of lc0 0.23.0 with Leelenstein net 12.1 (for Patreons of josh: https://www.patreon.com/jjosh/posts) for my NN-ratinglist (https://www.sp-cc.de/lc0-testing.htm) is running. After 1000 of 3000 games (4 days left to finish...) the result is pretty amazing. Looks like we will get a new world num...

NN-testrun of Lc0 0.22.0 49921 (only net, which is listed in the CCRL-ratinglist, time to check, how strong it really is (tested here with a non-ridiculous Leela-Ratio of 1.3)) finished.

https://www.sp-cc.de

(Perhaps you have to clear your browsercache or reload the website)

AB-testrun of Stockfish 191121 finished.

https://www.sp-cc.de

(Perhaps you have to clear your browsercache or reload the website)

To be fair, Ray is correct, the ratio is irrelevant for a ratings list. That is complete nonsense. It is the benchmark. Otherwise you can test lc0 on 1 CPU-core vs Stockfish and other opponents on a Threadripper and say: Oh, look. Stockfish crushes lc0 and lc0 is so bad, only 2700 Elo Or Stockfish ...

Anyone who conscientiously tests Lc0 against AB Engines knows, there is a Lc0 Ratio for reliable results. And CCRL knows that too. Nevertheless, CCRL does not release any information about it. Agreed. Any testing of NN-engine vs AB-engines without information about the Leela-Ratio makes the results...

https://lczero.org/networks/ 49921 3 4fd54df8 3355.00 105274 20 256 2019-07-29 17:02:08 +00:00 3355 Thanks. Why did you choose this net for test and why did you not choose other well-known net like 42850, T40B.4-160 or -260, 40.T8.610, etc? In the latter case we can make comparison more easily to e...

Anyone who conscientiously tests Lc0 against AB Engines knows, there is a Lc0 Ratio for reliable results. And CCRL knows that too. Nevertheless, CCRL does not release any information about it. Agreed. Any testing of NN-engine vs AB-engines without information about the Leela-Ratio makes the results...

What is the Leela ratio of the Fat Fritz games? That it the question... I would guess around 1.85. Which is much too high. I will do a testrun of Lc0 0.22.0 49921 for my ratinglist, now. Because it is the only lc0 net, which was tested in the CCRL. Lets see, how strong this one really is. Result no...

NN-testrun of Lc0 0.22.0 Net 61211 finished.

https://www.sp-cc.de

(Perhaps you have to clear your browsercache or reload the website)