Official Release of Ethereal 12.50
Moderators: hgm, Rebel, chrisw
-
- Posts: 38
- Joined: Tue Jan 01, 2019 9:34 am
- Full name: Siddhartha Chaudhary
Re: Official Release of Ethereal 12.50
great work ,wish this could be no. 1 chess engine in future ,thanks for andorid version.
-
- Posts: 178
- Joined: Wed Nov 13, 2019 1:36 am
- Full name: Jonathan Kreuzer
Re: Official Release of Ethereal 12.50
In a quick FRC bullet test, Ethereal 12.50 performed 34 elo better than Ethereal 12.25 against SlowChess 2.3, so FRC play looks clearly improved for this version (though my error bars are high, I only did the 1920 games for 12.50)
I like testing FRC but also always get higher gains there. I tried the 8-moves book and it does seem most drawish, then 2-moves book, then FRC shows largest difference. Possibly I should concentrate on standard more now to have one less performance skew to worry about. (Although with 2-moves book I started to worry that I was partially just arranging the eval to randomly end up reaching good positions in self-play from those positions.)
I like testing FRC but also always get higher gains there. I tried the 8-moves book and it does seem most drawish, then 2-moves book, then FRC shows largest difference. Possibly I should concentrate on standard more now to have one less performance skew to worry about. (Although with 2-moves book I started to worry that I was partially just arranging the eval to randomly end up reaching good positions in self-play from those positions.)
-
- Posts: 991
- Joined: Thu Mar 09, 2006 2:11 pm
Re: Official Release of Ethereal 12.50
AndrewGrant wrote: ↑Tue Sep 08, 2020 2:10 pm Note that I use a book called 8moves_v3 for Regression Testing. This book is typically very conservative. For the last few releases, (aside from some Contempt nonsense) I have under estimated the performance via this testing. This is likely due to the drawish nature of the opening book. I could be wrong, but +17 elo is a painful amount at this level, so even the lower end would make me happy.
Test for Standard ChessTest for Fischer Random ChessCode: Select all
ELO | 16.97 +- 3.41 (95%) CONF | 60.0+0.6s Threads=1 Hash=64MB Games | N: 11269 W: 1873 L: 1323 D: 8073
Code: Select all
ELO | 40.77 +- 4.62 (95%) CONF | 60.0+0.6s Threads=1 Hash=64MB Games | N: 8432 W: 2139 L: 1154 D: 5139
At the moment +11 for our 40/4 + ... list.
But only ~ 600 games are played so far.
https://cegt.forumieren.com/t1354-testi ... -12-50-x64
Best wishes,
G.S.
(CEGT team)
-
- Posts: 3546
- Joined: Thu Jun 07, 2012 11:02 pm
Re: Official Release of Ethereal 12.50
We're showing more than +50 Elo so far at FRC compared to 12.00 which was the last one tested. A few more opponents to come.
-
- Posts: 991
- Joined: Thu Mar 09, 2006 2:11 pm
Re: Official Release of Ethereal 12.50
@ CEGT 40/4 (no FRC) so far:
Best wishes,
G.S.
(CEGT team)
Code: Select all
Ethereal 12.50 x64 1CPU 3291 (1000 games) + 9 / +38
Ethereal 12.25 x64 1CPU 3282 (1500 games) +29
Ethereal 12.00 x64 1CPU 3253 (3800 games)
G.S.
(CEGT team)
-
- Posts: 1754
- Joined: Tue Apr 19, 2016 6:08 am
- Location: U.S.A
- Full name: Andrew Grant
Re: Official Release of Ethereal 12.50
I'm disappointed that you are still testing Houdini. You essentially have 3x sets of games between Stockfish and Ethereal :/ThatsIt wrote: ↑Fri Sep 11, 2020 9:53 am @ CEGT 40/4 (no FRC) so far:
Best wishes,Code: Select all
Ethereal 12.50 x64 1CPU 3291 (1000 games) + 9 / +38 Ethereal 12.25 x64 1CPU 3282 (1500 games) +29 Ethereal 12.00 x64 1CPU 3253 (3800 games)
G.S.
(CEGT team)
#WeAreAllDraude #JusticeForDraude #RememberDraude #LeptirBigUltra
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )
-
- Posts: 991
- Joined: Thu Mar 09, 2006 2:11 pm
Re: Official Release of Ethereal 12.50
AndrewGrant wrote: ↑Fri Sep 11, 2020 9:58 am I'm disappointed that you are still testing Houdini. You essentially have 3x sets of games between Stockfish and Ethereal :/
3x sets?
Whom do you have in the suspicion too?
Best wishes,
G.S.
(CEGT team)
-
- Posts: 1754
- Joined: Tue Apr 19, 2016 6:08 am
- Location: U.S.A
- Full name: Andrew Grant
Re: Official Release of Ethereal 12.50
Time will tellThatsIt wrote: ↑Fri Sep 11, 2020 10:15 amAndrewGrant wrote: ↑Fri Sep 11, 2020 9:58 am I'm disappointed that you are still testing Houdini. You essentially have 3x sets of games between Stockfish and Ethereal :/
3x sets?
Whom do you have in the suspicion too?
#WeAreAllDraude #JusticeForDraude #RememberDraude #LeptirBigUltra
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )
-
- Posts: 10948
- Joined: Wed Jul 26, 2006 10:21 pm
- Full name: Kai Laskos
Re: Official Release of Ethereal 12.50
You specifically coded the eval for FRC or the openings are generally better?AndrewGrant wrote: ↑Tue Sep 08, 2020 2:10 pm Note that I use a book called 8moves_v3 for Regression Testing. This book is typically very conservative. For the last few releases, (aside from some Contempt nonsense) I have under estimated the performance via this testing. This is likely due to the drawish nature of the opening book. I could be wrong, but +17 elo is a painful amount at this level, so even the lower end would make me happy.
Test for Standard ChessTest for Fischer Random ChessCode: Select all
ELO | 16.97 +- 3.41 (95%) CONF | 60.0+0.6s Threads=1 Hash=64MB Games | N: 11269 W: 1873 L: 1323 D: 8073
Code: Select all
ELO | 40.77 +- 4.62 (95%) CONF | 60.0+0.6s Threads=1 Hash=64MB Games | N: 8432 W: 2139 L: 1154 D: 5139
I guess your 17 Elo points from 8moves_v3 would be some 25 Elo points on 2moves_v1 of the SF testing framework
-
- Posts: 1754
- Joined: Tue Apr 19, 2016 6:08 am
- Location: U.S.A
- Full name: Andrew Grant
Re: Official Release of Ethereal 12.50
The evaluation was tuned using a ~66% ~33% mix of Standard games and FRC games.Laskos wrote: ↑Fri Sep 11, 2020 10:41 amYou specifically coded the eval for FRC or the openings are generally better?AndrewGrant wrote: ↑Tue Sep 08, 2020 2:10 pm Note that I use a book called 8moves_v3 for Regression Testing. This book is typically very conservative. For the last few releases, (aside from some Contempt nonsense) I have under estimated the performance via this testing. This is likely due to the drawish nature of the opening book. I could be wrong, but +17 elo is a painful amount at this level, so even the lower end would make me happy.
Test for Standard ChessTest for Fischer Random ChessCode: Select all
ELO | 16.97 +- 3.41 (95%) CONF | 60.0+0.6s Threads=1 Hash=64MB Games | N: 11269 W: 1873 L: 1323 D: 8073
Code: Select all
ELO | 40.77 +- 4.62 (95%) CONF | 60.0+0.6s Threads=1 Hash=64MB Games | N: 8432 W: 2139 L: 1154 D: 5139
I guess your 17 Elo points from 8moves_v3 would be some 25 Elo points on 2moves_v1 of the SF testing framework
Although the Fischer book does inflate elo more than 8moves_v3 does.
#WeAreAllDraude #JusticeForDraude #RememberDraude #LeptirBigUltra
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )