AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

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.
User avatar
kranium
Posts: 1768
Joined: Thu May 29, 2008 8:43 am

Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

Post by kranium » Wed Dec 06, 2017 5:24 pm

Lyudmil Tsvetkov wrote:
clumma wrote:
Lyudmil Tsvetkov wrote:Alpha had considerable hardware advantage
That comparison is not straightforward, but this claim does not seem to be true. SF had 64 threads. I'm not up on the latest scaling behavior of the engine but that has got to be near saturation.

-Carl
From what I gleaned from hardware comparisons, the advantage is 16/1.
Why would one want to run a similar very unfair match?
Only one thing comes to mind: that the company will want to advertise its colossal breakthrough with TPUs and artificial intelligence and then sell its products.

But then, the achievement is not there.
The fact that Google has created a chess playing entity that crushes SF is notable (and fascinating).

TPUs are not for sale, and (at the moment) are applied only to Googles deep learning and research projects,
except when Google donates them to research for free.

https://techcrunch.com/2017/05/17/the-t ... cientists/

Milos
Posts: 2990
Joined: Wed Nov 25, 2009 12:47 am

Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

Post by Milos » Wed Dec 06, 2017 5:28 pm

Rémi Coulom wrote:
Milos wrote:4 hours my ass (pardon my french). Try training it on state-of-the-art 1080.
Fully trained network requres 12h on 5000 gen1 TPUs for self-games and 64 gen2 TPUs for training itself.
Gen1 TPU is like 30x K80 which is like 5x 1080 in performance.
So you'd need like 375k training days with 1080, which is like 1000 years!!!
Your math is wrong. I think it is doable with a distributed effort smaller than what was used for Stockfish.
Care to elaborate, add any substance beyond your one-liner childish reply?

clumma
Posts: 150
Joined: Fri Oct 10, 2014 8:05 pm
Location: Berkeley, CA

Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

Post by clumma » Wed Dec 06, 2017 5:32 pm

Milos wrote:4 hours my ass (pardon my french).
Far fewer transistors and joules were used training AlphaZero than have been used training Stockfish. You can soon rent those TPUs on Google's cloud, or apply for free access now, so stop complaining. Furthermore it's an experimental project in early days and performance is obviously not optimal, so all the 'but-but-but 30 Elo because they used SF 8 instead of SF 8.00194' sounds really dumb.

Days of alpha-beta engines have come to an abrupt end.

-Carl

Milos
Posts: 2990
Joined: Wed Nov 25, 2009 12:47 am

Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

Post by Milos » Wed Dec 06, 2017 5:39 pm

clumma wrote:
Milos wrote:4 hours my ass (pardon my french).
Far fewer transistors and joules were used training AlphaZero than have been used training Stockfish. You can soon rent those TPUs on Google's cloud, or apply for free access now, so stop complaining. Furthermore it's an experimental project in early days and performance is obviously not optimal, so all the 'but-but-but 30 Elo because they used SF 8 instead of SF 8.00194' sounds really dumb.

Days of alpha-beta engines have come to an abrupt end.

-Carl
Sorry, that is pretty childish rent.
Google is obviously comparing apples and oranges and again doing marketing stunt and ppl are falling for it.
Days of Alpha0 on normal hardware are years away. But keep on dreaming, no one can take that from you.

P.S. Just as a small comparison. leelazero open source project trying to replicate alpha0 in Go, took 1 month to get the same games as AG0 got in 3 hours, that with constant 1000 volunteers.
For chess it would take even more.

Rémi Coulom
Posts: 404
Joined: Mon Apr 24, 2006 6:06 pm
Contact:

Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

Post by Rémi Coulom » Wed Dec 06, 2017 5:43 pm

Milos wrote:
Rémi Coulom wrote:
Milos wrote:4 hours my ass (pardon my french). Try training it on state-of-the-art 1080.
Fully trained network requres 12h on 5000 gen1 TPUs for self-games and 64 gen2 TPUs for training itself.
Gen1 TPU is like 30x K80 which is like 5x 1080 in performance.
So you'd need like 375k training days with 1080, which is like 1000 years!!!
Your math is wrong. I think it is doable with a distributed effort smaller than what was used for Stockfish.
Care to elaborate, add any substance beyond your one-liner childish reply?
5000*5*12/(24*365) = 34.25 years

User avatar
MikeGL
Posts: 694
Joined: Thu Sep 01, 2011 12:49 pm

Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

Post by MikeGL » Wed Dec 06, 2017 5:44 pm

Lyudmil Tsvetkov wrote:
MikeGL wrote:
clumma wrote:
Lyudmil Tsvetkov wrote:Alpha had considerable hardware advantage
... but that has got to be near saturation.

-Carl
Excellent point.

I mean at that hardware, there won't be any fluctuation on the best candidate move by SF8 anyway.
Alpha hardware equivalent was somewhere 1024 standard cores.
How 1024 cores compare with 64 cores?
How scientific is that.

I don't know what saturation you are talking about, from what I read, without fully understanding it, the TPUs are a very different architecture and quite differently affected by general computer chess concepts.
How can you make up such claims when there are not enough data on the PDF file?
TPU instruction set and benchmark was not properly published.
Was only claimed in PDF report that SF8 was on 64 threads (but no clock speed). Was discussed years ago on this forum that clockspeed, including those of the buses,
would trump number of cores.

Would choose a 1-core 4.0 Ghz over 8-cores running at 2.0 GHz with buggy SMP implementation of engine.
Last edited by MikeGL on Wed Dec 06, 2017 5:48 pm, edited 1 time in total.

jdart
Posts: 3504
Joined: Fri Mar 10, 2006 4:23 am
Location: http://www.arasanchess.org

Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

Post by jdart » Wed Dec 06, 2017 5:48 pm

Good point re the book - Alphazero effevtibely has one. But it is still not a small achievement wiining against SF, even with unequal conditions. But many of us would like to see a more equal test.

jhellis3
Posts: 341
Joined: Fri Aug 16, 2013 10:36 pm

Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

Post by jhellis3 » Wed Dec 06, 2017 5:48 pm

As has been mentioned previously, one can not really make direct core count comparisons in this case.

The most "fair" metric I can think of using is system power consumption, and I would guess that SF was at a bit of a disadvantage in this regard. Regardless, the writing is clearly on the wall.....

Milos
Posts: 2990
Joined: Wed Nov 25, 2009 12:47 am

Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

Post by Milos » Wed Dec 06, 2017 5:49 pm

Rémi Coulom wrote:
Milos wrote:
Rémi Coulom wrote:
Milos wrote:4 hours my ass (pardon my french). Try training it on state-of-the-art 1080.
Fully trained network requres 12h on 5000 gen1 TPUs for self-games and 64 gen2 TPUs for training itself.
Gen1 TPU is like 30x K80 which is like 5x 1080 in performance.
So you'd need like 375k training days with 1080, which is like 1000 years!!!
Your math is wrong. I think it is doable with a distributed effort smaller than what was used for Stockfish.
Care to elaborate, add any substance beyond your one-liner childish reply?
5000*5*12/(24*365) = 34.25 years
So you claim single gen1 TPU is just only like 5x stronger than Nvidia 1080 GPU????
Gee, you really have no clue about hardware, do you?
TPU is like 92 TOPS, 1080 is 0.3TFLOPS. Please educate yourself before trying to run discussions with one-liner replies.
Last edited by Milos on Wed Dec 06, 2017 5:51 pm, edited 1 time in total.

clumma
Posts: 150
Joined: Fri Oct 10, 2014 8:05 pm
Location: Berkeley, CA

Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

Post by clumma » Wed Dec 06, 2017 5:51 pm

Milos wrote:Days of Alpha0 on normal hardware are years away.
Sounds like you're conflating model training with running the program.
For chess it would take even more.
For chess it takes less.
But keep on dreaming, no one can take that from you.
Your case isn't advanced by being an asshole.

-Carl

Post Reply