Google's AlphaGo team has been working on chess

Discussion of chess software programming and technical issues.

Moderators: hgm, Harvey Williamson, bob

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Daniel Shawul
Posts: 3468
Joined: Tue Mar 14, 2006 10:34 am
Location: Ethiopia
Contact:

Re: Google's AlphaGo team has been working on chess

Post by Daniel Shawul » Thu Dec 07, 2017 2:15 am

Uri Blass wrote:
Daniel Shawul wrote:Most of us here suspected that this could happen once Giraffe showed it can beat Stockfish's eval.

Just the fact that the new approch to chess programming worked incredibly well is fantastic even if it didn't beat the best.

Daniel

How do you decide that giraffe's evaluation is better than stockfish?
If the definition is by using fixed number of nodes with the same search function then having a better evaluation than stockfish is easy if you do not care about time.

Evaluation is basically a function that take a position and return a number.

In this case I can define the evaluation of the position to be the result of the search of stockfish when it searches 20 plies forward.

I am sure this evaluation is better than stockfish's evaluation and can beat stockfish's evaluation when you search the same number of nodes(of course you do not count the nodes that you search to calculate the evaluation because they are defined to be part of the evaluation).

Uri
Static evaluation is something done without a lookahead search. Ofcourse, any defintion is right and you can call a 20 plies search evaluation but it doesn't matter as long as improving the eval doesn't bring additional strength (in your example it would be a 21+ plies search :) )

Evaluation in the AlphaGo Zero and AlphaZero is just an evaluation of a deep NN. This wasn't the case with AlphaGo Lee because there they used a combination of an evaluation of a deep NN and playout (rollouts), which are just random games played from the position.

The upper parts of the tree are stored in memory in a MCTS where the moves are selected again with a NN (policy NN). An alpha-beta with LMR + nullmove is probably close to MCTS.

I think the mistake I made when testing MCTS for chess few years ago was that I did the evalution with only rollouts -- and this is very hard to get right with all the tactics in chess. I think now I would have been better off using a standard static eval and converting the score to 1,0,-1 by a logistic function.

Daniel

EvgeniyZh
Posts: 42
Joined: Fri Sep 19, 2014 2:54 pm
Location: Israel
Contact:

Re: Google's AlphaGo team has been working on chess

Post by EvgeniyZh » Thu Dec 07, 2017 3:51 am

Henk wrote:Don't understand that these predictions will be good if it doesn't do a search but only simulation.
That's what I'm asking every time I'm looking on human players)
Dann Corbit wrote:
They used TPU not GPU (I suppose, did not read the paper yet, but TPU were used for Go).

They are special vector processors like GPU in having massive parallel operations.
Anything running on TPU can be ran on GPU. If we want to get to consumer hardware, that'be reasonable choice.

Joerg Oster
Posts: 618
Joined: Fri Mar 10, 2006 3:29 pm
Location: Germany

Re: Google's AlphaGo team has been working on chess

Post by Joerg Oster » Thu Dec 07, 2017 7:53 am

jdart wrote:Stockfish does such heavy pruning that it is throwing away most of the nodes in its search trees. But the ones it does search, it searches very deeply. I see a lot of high-level computer games won by tactics or by endgame play that requires deep search. Shannon Type II (selective search) has never worked well in any of the past 5-6 decades. But maybe this effort is showing that eval is more important than has been thought, and search less important.

--Jon
And quite remarkably it is both, one of its biggest strength but also one of its biggest weakness. :lol:
Jörg Oster

Rein Halbersma
Posts: 675
Joined: Tue May 22, 2007 9:13 am

Re: Google's AlphaGo team has been working on chess

Post by Rein Halbersma » Thu Dec 07, 2017 8:49 am

mar wrote:While this is indeed incredible, show me how it beats SF dev with good book and syzygy on equal hardware in a 1000 game match.

Alternatively winning next TCEC should do :wink:
Equal budget would be a fairer comparison since AlphaZero and Stockfish take advantage of different types of hardware (GPU vs CPU).

If you look at the scaling graph of thinking time vs performance, it suggests that Stockfish is still ahead at fast time controls but that at longer time controls AlphaZero dominates. It would be interesting to see this graph as a function of money resources.

CheckersGuy
Posts: 273
Joined: Wed Aug 24, 2016 7:49 pm

Re: Google's AlphaGo team has been working on chess

Post by CheckersGuy » Thu Dec 07, 2017 2:52 pm

Rein Halbersma wrote:
mar wrote:While this is indeed incredible, show me how it beats SF dev with good book and syzygy on equal hardware in a 1000 game match.

Alternatively winning next TCEC should do :wink:
Equal budget would be a fairer comparison since AlphaZero and Stockfish take advantage of different types of hardware (GPU vs CPU).

If you look at the scaling graph of thinking time vs performance, it suggests that Stockfish is still ahead at fast time controls but that at longer time controls AlphaZero dominates. It would be interesting to see this graph as a function of money resources.
That's the difficult thing with AlphaZero. Comparing two different types of hardware is not that easy. One could use a performance/dollar metric or performance/power-usage.

I personally prefer performance/dollar +performance/power-usage

jdart
Posts: 3554
Joined: Fri Mar 10, 2006 4:23 am
Location: http://www.arasanchess.org

Re: Google's AlphaGo team has been working on chess

Post by jdart » Thu Dec 07, 2017 2:56 pm

Well, probably they should have give same FLOPS budget to both, that seems like the most fair you can get, given the inefficiency of switching hardware for either side.
Here is a scary thought, though: what would be the performance of AlphaZero if they used more of its training cluster for execution?

I don't know how well it scales on more TPUs and it might need tuning for that but throwing even more processors on it could put it even more even with Stockfish, if not above it.

They could possibly enter the WCCC with that.

--Jon

CheckersGuy
Posts: 273
Joined: Wed Aug 24, 2016 7:49 pm

Re: Google's AlphaGo team has been working on chess

Post by CheckersGuy » Thu Dec 07, 2017 3:00 pm

jdart wrote:
Well, probably they should have give same FLOPS budget to both, that seems like the most fair you can get, given the inefficiency of switching hardware for either side.
Here is a scary thought, though: what would be the performance of AlphaZero if they used more of its training cluster for execution?

I don't know how well it scales on more TPUs and it might need tuning for that but throwing even more processors on it could put it even more even with Stockfish, if not above it.

They could possibly enter the WCCC with that.

--Jon
As far as I know the first generation TPU's, which were used for training, are for training only. The second generation TPU'S can do both training and inference.
However, google/deepMind probably has enough hardware to use many many more second generation TPU's. What I am intrested in is, when the AI stop's improving in the training process since they only trained for 4 hours.

Henk
Posts: 5184
Joined: Mon May 27, 2013 8:31 am

Re: Google's AlphaGo team has been working on chess

Post by Henk » Fri Dec 08, 2017 11:46 am

Building neural network software from scratch is much work.

corres
Posts: 572
Joined: Wed Nov 18, 2015 10:41 am
Location: hungary

Re: Google's AlphaGo team has been working on chess

Post by corres » Sat Dec 09, 2017 12:47 pm

[quote="Rein Halbersma"]

[b]Equal budget[/b] would be a fairer comparison since AlphaZero and Stockfish take advantage of different types of hardware (GPU vs CPU).
If you look at the scaling graph of thinking time vs performance, it suggests that Stockfish is still ahead at fast time controls but that at longer time controls AlphaZero dominates. It would be interesting to see this graph as a function of money resources.

[/quote]

I am afraid that Stockfish does not get significant help from a much more expensive hardware than it was used for demonstration of AlphaZero.
Supposing the 64 cores used by them are physical cores and not logical cores the increase of cores number to 128, 256,.. give some ten Elo only.

User avatar
stegemma
Posts: 851
Joined: Mon Aug 10, 2009 8:05 pm
Location: Italy
Contact:

Re: Google's AlphaGo team has been working on chess

Post by stegemma » Sat Dec 09, 2017 1:53 pm

corres wrote:
Rein Halbersma wrote:
Equal budget would be a fairer comparison since AlphaZero and Stockfish take advantage of different types of hardware (GPU vs CPU).
If you look at the scaling graph of thinking time vs performance, it suggests that Stockfish is still ahead at fast time controls but that at longer time controls AlphaZero dominates. It would be interesting to see this graph as a function of money resources.
I am afraid that Stockfish does not get significant help from a much more expensive hardware than it was used for demonstration of AlphaZero.
Supposing the 64 cores used by them are physical cores and not logical cores the increase of cores number to 128, 256,.. give some ten Elo only.
I think that this a limit of alphabeta algorithm, not a limit of Stockfish itself. The limit of alphabeta is derived by the nature of the game, of course, that grows exponentially at any ply. A smarter approach that uses neural networks and/or other AI algorithms could potentially gives better performance than alphabeta (as AphaZero seems to "demonstrate"). of course AI requires more computational power than alphabeta based algorithms but could eventually scale better at time/power increasing.
Author of Drago, Raffaela, Freccia, Satana, Sabrina.
http://www.linformatica.com

Post Reply