Or better...Werewolf wrote:
So with a fraction of the processing power Stockfish is almost as good as Alpha Zero. Interesting...
AlphaZero vs Stockfish
Moderators: hgm, Rebel, chrisw
-
- Posts: 545
- Joined: Tue Jun 06, 2017 4:49 pm
- Location: Italy
Re: AlphaZero vs Stockfish
F.S.I. Chess Teacher
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: AlphaZero vs Stockfish
Wouldn't help much if Kasparov would only make first 10 moves, you'd almost equally suck at it.hgm wrote:It is rather funny to see how the notion had Stockfish would be better if it was using a book seems to prevale. Imagine how strong a Chess player I would be, if I could make Kasparov do the moves for me...
-
- Posts: 3293
- Joined: Wed Mar 08, 2006 8:15 pm
Re: AlphaZero vs Stockfish
From fishcooking:
SF8 (1/1 minute and limited hash) against SFlatest (40/40 minutes)
Score of sf8_1in1 vs sf_master: 2 - 26 - 72 [0.380] 100
Elo difference: -85.04 +/- 34.16
And book is additional +50 Elo.
SF8 (1/1 minute and limited hash) against SFlatest (40/40 minutes)
Score of sf8_1in1 vs sf_master: 2 - 26 - 72 [0.380] 100
Elo difference: -85.04 +/- 34.16
And book is additional +50 Elo.
Jouni
-
- Posts: 10316
- Joined: Thu Mar 09, 2006 12:37 am
- Location: Tel-Aviv Israel
Re: AlphaZero vs Stockfish
This is at 1 minute per move on 1 core.Jouni wrote:From fishcooking:
SF8 (1/1 minute and limited hash) against SFlatest (40/40 minutes)
Score of sf8_1in1 vs sf_master: 2 - 26 - 72 [0.380] 100
Elo difference: -85.04 +/- 34.16
And book is additional +50 Elo.
The difference is going to be clearly smaller with 64 cores and
I see no evidence that book at that time control is additional +50 elo.
Maybe book does not give much at long time control because the program can often find better moves by itself.
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: AlphaZero vs Stockfish
Smaller yes, but not 1/5 of it, maybe 1/2 of it.Uri Blass wrote:This is at 1 minute per move on 1 core.
The difference is going to be clearly smaller with 64 cores and
I see no evidence that book at that time control is additional +50 elo.
Maybe book does not give much at long time control because the program can often find better moves by itself.
How I see it on 64 cores (we also don't know if these are cores or threads, since they don't say which machine they used, if it is cores Numa was not used, Large Pages were also not used):
SFdev vs SF8 at least 30Elo, hash up to 10ELO, EGTBs up to 10 ELO, large pages 5-10Elo, better SMP implementation of SFdev compared to SF8 for large number of cores (>32) 5-10Elo, Cerebellum book 30Elo against conventional engine, but against A0 most probably more, coz A0 is well trained for only small amount of openings, and good book would help SF a lot to get much more draws with black.
If you add all this together it is easy 100Elo if not even more.
Last edited by Milos on Thu Dec 14, 2017 6:20 pm, edited 1 time in total.
-
- Posts: 1080
- Joined: Fri Sep 16, 2016 6:55 pm
- Location: USA/Minnesota
- Full name: Leo Anger
Re: AlphaZero vs Stockfish
Deep Mind Google weakened SF terribly. Yes, they have a new impressive self learning machine, but if its so great lets see it play SF when its at full power. Then it would be impressive. Not now with flawed conditions.Jouni wrote:From fishcooking:
SF8 (1/1 minute and limited hash) against SFlatest (40/40 minutes)
Score of sf8_1in1 vs sf_master: 2 - 26 - 72 [0.380] 100
Elo difference: -85.04 +/- 34.16
And book is additional +50 Elo.
Advanced Micro Devices fan.
-
- Posts: 1080
- Joined: Fri Sep 16, 2016 6:55 pm
- Location: USA/Minnesota
- Full name: Leo Anger
Re: AlphaZero vs Stockfish
I am beginning to think the Alpha team was afraid the results would have been a lot less impressive if they had beefed things up for SF.Milos wrote:Smaller yes, but not 1/5 of it, maybe 1/2 of it.Uri Blass wrote:This is at 1 minute per move on 1 core.
The difference is going to be clearly smaller with 64 cores and
I see no evidence that book at that time control is additional +50 elo.
Maybe book does not give much at long time control because the program can often find better moves by itself.
How I see it on 64 cores (we also don't know if these are cores or threads, since they don't say which machine they used, if it is cores Numa was not used, Large Pages were also not used):
SFdev vs SF8 at least 30Elo, hash up to 10ELO, EGTBs up to 10 ELO, large pages 5-10Elo, better SMP implementation of SFdev compared to SF8 for large number of cores (>32) 5-10Elo, Cerebellum book 30Elo against conventional engine, but against A0 most probably more, coz A0 is well trained for only small amount of openings, and good book would help SF a lot to get much more draws with black.
If you add all this together it is easy 100Elo if not even more.
Advanced Micro Devices fan.
-
- Posts: 117
- Joined: Wed Aug 22, 2007 4:39 pm
Re: AlphaZero vs Stockfish
Alpha Zero can prob give a GM two minor odds and do favorably.
-
- Posts: 545
- Joined: Tue Jun 06, 2017 4:49 pm
- Location: Italy
Re: AlphaZero vs Stockfish
The graph here show difference between SF8 and latest SF dev is more than 100 ELO.Leo wrote:I am beginning to think the Alpha team was afraid the results would have been a lot less impressive if they had beefed things up for SF.Milos wrote:Smaller yes, but not 1/5 of it, maybe 1/2 of it.Uri Blass wrote:This is at 1 minute per move on 1 core.
The difference is going to be clearly smaller with 64 cores and
I see no evidence that book at that time control is additional +50 elo.
Maybe book does not give much at long time control because the program can often find better moves by itself.
How I see it on 64 cores (we also don't know if these are cores or threads, since they don't say which machine they used, if it is cores Numa was not used, Large Pages were also not used):
SFdev vs SF8 at least 30Elo, hash up to 10ELO, EGTBs up to 10 ELO, large pages 5-10Elo, better SMP implementation of SFdev compared to SF8 for large number of cores (>32) 5-10Elo, Cerebellum book 30Elo against conventional engine, but against A0 most probably more, coz A0 is well trained for only small amount of openings, and good book would help SF a lot to get much more draws with black.
If you add all this together it is easy 100Elo if not even more.
https://nextchessmove.com/dev-builds
F.S.I. Chess Teacher
-
- Posts: 379
- Joined: Fri Sep 28, 2012 5:53 pm
- Location: Sweden
Re: AlphaZero vs Stockfish
Rodolfo Leoni wrote:The graph here show difference between SF8 and latest SF dev is more than 100 ELO.Leo wrote:I am beginning to think the Alpha team was afraid the results would have been a lot less impressive if they had beefed things up for SF.Milos wrote:Smaller yes, but not 1/5 of it, maybe 1/2 of it.Uri Blass wrote:This is at 1 minute per move on 1 core.
The difference is going to be clearly smaller with 64 cores and
I see no evidence that book at that time control is additional +50 elo.
Maybe book does not give much at long time control because the program can often find better moves by itself.
How I see it on 64 cores (we also don't know if these are cores or threads, since they don't say which machine they used, if it is cores Numa was not used, Large Pages were also not used):
SFdev vs SF8 at least 30Elo, hash up to 10ELO, EGTBs up to 10 ELO, large pages 5-10Elo, better SMP implementation of SFdev compared to SF8 for large number of cores (>32) 5-10Elo, Cerebellum book 30Elo against conventional engine, but against A0 most probably more, coz A0 is well trained for only small amount of openings, and good book would help SF a lot to get much more draws with black.
If you add all this together it is easy 100Elo if not even more.
https://nextchessmove.com/dev-builds
No it doesn't, read again.
/John