AlphaZero vs Stockfish

Discussion of anything and everything relating to chess playing software and machines.

Moderators: hgm, Harvey Williamson, bob

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Rodolfo Leoni
Posts: 544
Joined: Tue Jun 06, 2017 2:49 pm
Location: Italy

Re: AlphaZero vs Stockfish

Post by Rodolfo Leoni » Thu Dec 14, 2017 12:07 pm

Werewolf wrote:
So with a fraction of the processing power Stockfish is almost as good as Alpha Zero. Interesting...
Or better... :P
F.S.I. Chess Teacher

Milos
Posts: 3372
Joined: Wed Nov 25, 2009 12:47 am

Re: AlphaZero vs Stockfish

Post by Milos » Thu Dec 14, 2017 4:33 pm

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...
Wouldn't help much if Kasparov would only make first 10 moves, you'd almost equally suck at it. :lol:

Jouni
Posts: 1953
Joined: Wed Mar 08, 2006 7:15 pm

Re: AlphaZero vs Stockfish

Post by Jouni » Thu Dec 14, 2017 4:38 pm

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.
Jouni

Uri Blass
Posts: 8506
Joined: Wed Mar 08, 2006 11:37 pm
Location: Tel-Aviv Israel

Re: AlphaZero vs Stockfish

Post by Uri Blass » Thu Dec 14, 2017 4:53 pm

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.
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.

Milos
Posts: 3372
Joined: Wed Nov 25, 2009 12:47 am

Re: AlphaZero vs Stockfish

Post by Milos » Thu Dec 14, 2017 5:18 pm

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.
Smaller yes, but not 1/5 of it, maybe 1/2 of it.
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 5:20 pm, edited 1 time in total.

Leo
Posts: 789
Joined: Fri Sep 16, 2016 4:55 pm
Location: USA/Minnesota
Full name: Leo

Re: AlphaZero vs Stockfish

Post by Leo » Thu Dec 14, 2017 5:19 pm

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.
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.
BrainFish-2 190310 bmi2 Elo 3576.

Leo
Posts: 789
Joined: Fri Sep 16, 2016 4:55 pm
Location: USA/Minnesota
Full name: Leo

Re: AlphaZero vs Stockfish

Post by Leo » Thu Dec 14, 2017 5:23 pm

Milos wrote:
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.
Smaller yes, but not 1/5 of it, maybe 1/2 of it.
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.
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.
BrainFish-2 190310 bmi2 Elo 3576.

FWCC
Posts: 117
Joined: Wed Aug 22, 2007 2:39 pm

Re: AlphaZero vs Stockfish

Post by FWCC » Thu Dec 14, 2017 5:25 pm

Alpha Zero can prob give a GM two minor odds and do favorably.

Rodolfo Leoni
Posts: 544
Joined: Tue Jun 06, 2017 2:49 pm
Location: Italy

Re: AlphaZero vs Stockfish

Post by Rodolfo Leoni » Thu Dec 14, 2017 5:33 pm

Leo wrote:
Milos wrote:
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.
Smaller yes, but not 1/5 of it, maybe 1/2 of it.
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.
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.
The graph here show difference between SF8 and latest SF dev is more than 100 ELO.

https://nextchessmove.com/dev-builds
F.S.I. Chess Teacher

Tobber
Posts: 379
Joined: Fri Sep 28, 2012 3:53 pm
Location: Sweden

Re: AlphaZero vs Stockfish

Post by Tobber » Thu Dec 14, 2017 7:13 pm

Rodolfo Leoni wrote:
Leo wrote:
Milos wrote:
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.
Smaller yes, but not 1/5 of it, maybe 1/2 of it.
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.
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.
The graph here show difference between SF8 and latest SF dev is more than 100 ELO.

https://nextchessmove.com/dev-builds

No it doesn't, read again.

/John

Post Reply