This really seems revolutionary !
Beating Stockfish 10-0 is no joke.
I wonder when such a Program would be made available to customers at a reasonable price ?
AlphaZero beats AlphaGo Zero, Stockfish, and Elmo
Moderators: hgm, Rebel, chrisw
-
- Posts: 1339
- Joined: Fri Nov 02, 2012 9:43 am
- Location: New Delhi, India
Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo
i7 5960X @ 4.1 Ghz, 64 GB G.Skill RipJaws RAM, Twin Asus ROG Strix OC 11 GB Geforce 2080 Tis
-
- Posts: 261
- Joined: Sun Nov 13, 2016 10:37 am
Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo
Not 10-0.
Result: +28 =72 -0
Result: +28 =72 -0
-
- Posts: 1339
- Joined: Fri Nov 02, 2012 9:43 am
- Location: New Delhi, India
Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo
Oh, even more awesome !sovaz1997 wrote:Not 10-0.
Result: +28 =72 -0
i7 5960X @ 4.1 Ghz, 64 GB G.Skill RipJaws RAM, Twin Asus ROG Strix OC 11 GB Geforce 2080 Tis
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo
1st gen TPU is 92 TOPS and an OP is an 8bit int multiplication.Rémi Coulom wrote:1080 ti is 11.3 TFLOPS:
https://www.anandtech.com/show/11172/nv ... t-week-699
A TPU is 45 TOPS:
https://arstechnica.com/information-tec ... ute-cloud/
Lets cut this crap of comparing apples and oranges. Please take a look at:
https://arxiv.org/abs/1704.04760
The actual comparison (not apples and oranges stuff you mention) you can see in Table 6 where typical ML application are compared (MLP and CNN).
Factor between first gen TPU and K80 (that is 3-5x faster for ML compared to 1080) is between 15 and 60 averaging around 25x.
-
- Posts: 438
- Joined: Mon Apr 24, 2006 8:06 pm
Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo
The GTX 1080 should be faster than a K80. For instance, this is a deep learning benchmark where it is 4x faster:Milos wrote:1st gen TPU is 92 TOPS and an OP is an 8bit int multiplication.Rémi Coulom wrote:1080 ti is 11.3 TFLOPS:
https://www.anandtech.com/show/11172/nv ... t-week-699
A TPU is 45 TOPS:
https://arstechnica.com/information-tec ... ute-cloud/
Lets cut this crap of comparing apples and oranges. Please take a look at:
https://arxiv.org/abs/1704.04760
The actual comparison (not apples and oranges stuff you mention) you can see in Table 6 where typical ML application are compared (MLP and CNN).
Factor between first gen TPU and K80 (that is 3-5x faster for ML compared to 1080) is between 15 and 60 averaging around 25x.
https://medium.com/initialized-capital/ ... bd85fe5d58
They have roughly the same number of cores, but the clock speed of the 1080 is 3x the clock speed of the K80. 16nm vs 28 nm technology. The 1080 is definitely faster.
The reason I used 5x in my initial formula is that I believed you meant in your message that a 1080 is 5x slower than a TPU (5x slower than a K80 cannot be correct).
Anyway, whether a TPU is 5x or 10x faster than a 1080 does not change much to the fact that the experiment of DeepMind can be replicated in a few months of distributed computation with ~100 participants, which should be less than the effort that was used by Stockfish so far.
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo
It took leelazero 1 month to get the same games as AG0 got in 3 hours, that with constant 1000 volunteers.Rémi Coulom wrote:Anyway, whether a TPU is 5x or 10x faster than a 1080 does not change much to the fact that the experiment of DeepMind can be replicated in a few months of distributed computation with ~100 participants, which should be less than the effort that was used by Stockfish so far.
What makes you think you could do the same in chess with only 100 participants?
Minimum time to train network to SF8 level would be at least a year with constant 100 volunteers.
And in terms of power burned I really don't think it wouldn't be anywhere near to fishtest but much higher. Power per core of modern CPU is 10-15W. 1080 is like 250W.
Most of ppl in fishtest donate just a few cores and most ppl don't have 10 series GTX cards but older which are far less powerful and far more power hungry.
-
- Posts: 6052
- Joined: Tue Jun 12, 2012 12:41 pm
Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo
Never.shrapnel wrote:This really seems revolutionary !
Beating Stockfish 10-0 is no joke.
I wonder when such a Program would be made available to customers at a reasonable price ?
It will go the Deep Blue path, serving just commercial interests.
And is of comparable strength as Deep Blue then, that is, far from the top.
I don't know why it is so difficult to understand it is all hardware.
-
- Posts: 6052
- Joined: Tue Jun 12, 2012 12:41 pm
Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo
Only thing is they are still tuning at a much lower level, quite probably around 2900 or even lower.Rémi Coulom wrote:The GTX 1080 should be faster than a K80. For instance, this is a deep learning benchmark where it is 4x faster:Milos wrote:1st gen TPU is 92 TOPS and an OP is an 8bit int multiplication.Rémi Coulom wrote:1080 ti is 11.3 TFLOPS:
https://www.anandtech.com/show/11172/nv ... t-week-699
A TPU is 45 TOPS:
https://arstechnica.com/information-tec ... ute-cloud/
Lets cut this crap of comparing apples and oranges. Please take a look at:
https://arxiv.org/abs/1704.04760
The actual comparison (not apples and oranges stuff you mention) you can see in Table 6 where typical ML application are compared (MLP and CNN).
Factor between first gen TPU and K80 (that is 3-5x faster for ML compared to 1080) is between 15 and 60 averaging around 25x.
https://medium.com/initialized-capital/ ... bd85fe5d58
They have roughly the same number of cores, but the clock speed of the 1080 is 3x the clock speed of the K80. 16nm vs 28 nm technology. The 1080 is definitely faster.
The reason I used 5x in my initial formula is that I believed you meant in your message that a 1080 is 5x slower than a TPU (5x slower than a K80 cannot be correct).
Anyway, whether a TPU is 5x or 10x faster than a 1080 does not change much to the fact that the experiment of DeepMind can be replicated in a few months of distributed computation with ~100 participants, which should be less than the effort that was used by Stockfish so far.
It will not be that easy going forward, as optimal lines get subtler and subtler.
Stockfish also averaged around 150 elo in the first year.
At that level, it is easy, let's see what they do from now on, and my prediction is: very little.
-
- Posts: 6052
- Joined: Tue Jun 12, 2012 12:41 pm
Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo
Oops, are not they doing alpha-beta too?clumma wrote: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.Milos wrote:4 hours my ass (pardon my french).
Days of alpha-beta engines have come to an abrupt end.
-Carl
There is a single approach to playing chess, picking the best move, and whether you call it alpha-beta, Monte Carlo or Las Vegas does not matter at all.
-
- Posts: 6052
- Joined: Tue Jun 12, 2012 12:41 pm
Re: AlphaZero beats AlphaGo Zero, Stockfish, and Elmo
And I have been wondering why in most games Alpha takes very early advantage.jdart wrote: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.
Stockfish opening play seems normal for its level, but that thing plays like a beast.