Alphazero news

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.
jp
Posts: 754
Joined: Mon Apr 23, 2018 5:54 am

Re: Alphazero news

Post by jp » Sun Dec 09, 2018 6:42 pm

jhellis3 wrote:
Sun Dec 09, 2018 6:36 pm
EDIT: Or here is a challenge for you if you still don't get it: code a better static eval in less time. I won't hold my breath.
That's not what it means to be efficient in standard software terminology.
No one ever said brute force cannot be effective in some applications.

You wrote "find value in" them. They don't need to be efficient for people to "find value in" them.

You asked by what measure it's inefficient, not by what measure it's valueless.

jhellis3
Posts: 390
Joined: Fri Aug 16, 2013 10:36 pm

Re: Alphazero news

Post by jhellis3 » Sun Dec 09, 2018 6:49 pm

Purposefully obtuse it is.

You are also confusing with the manner in which the eval is derived from its use, which I would wager is far more efficient (Elo / Watt) than any conventional engine.

And I did not ask anything.

jp
Posts: 754
Joined: Mon Apr 23, 2018 5:54 am

Re: Alphazero news

Post by jp » Sun Dec 09, 2018 6:53 pm

jhellis3 wrote:
Sun Dec 09, 2018 6:25 pm
Actually, I would have to disagree with this. Yes, it is "brute forcing" an eval. TBs are brute forced evals and people find plenty of value in them. Ever increasing thread count in conventional engines is brute forcing via search and people find value in that. But as to the efficiency question, by what measure is it inefficient.
jhellis3 wrote:
Sun Dec 09, 2018 6:49 pm
And I did not ask anything.
SInce you were replying to someone else, I should just have let him reply.

jhellis3
Posts: 390
Joined: Fri Aug 16, 2013 10:36 pm

Re: Alphazero news

Post by jhellis3 » Sun Dec 09, 2018 6:55 pm

You may not have noticed; the end of that sentence is concluded with a period and not a question mark.

It is a rhetorical question, not an actual one.

jp
Posts: 754
Joined: Mon Apr 23, 2018 5:54 am

Re: Alphazero news

Post by jp » Sun Dec 09, 2018 7:00 pm

I'll let noobpwnftw reply to you if he wants, since you were replying to him.

It'd be better if you did not resort to personal attacks on people you disagree with, though.

Albert Silver
Posts: 2831
Joined: Wed Mar 08, 2006 8:57 pm
Location: Rio de Janeiro, Brazil

Re: Alphazero news

Post by Albert Silver » Sun Dec 09, 2018 7:08 pm

Milos wrote:
Sun Dec 09, 2018 6:27 pm
Albert Silver wrote:
Sun Dec 09, 2018 6:12 pm
Milos wrote:
Sun Dec 09, 2018 5:37 pm
Albert Silver wrote:
Sun Dec 09, 2018 4:34 pm
I think it goes deeper than that. If someone, even someone whose knowledge and technical savvy you deeply respected, had told you a few years ago that they could get a program that was nearly one thousand times slower in NPS to compete and even beat the best of the day on a PC, I am guessing you would have rolled your eyes a them. I know I would have.

Yet, that is what AlphaZero has done, and we are even able to bring this to the home user's PC thanks to Deep Mind's generosity with their knowledge, as well as the fantatsic Leela Chess community efforts. In other words that is not limited to some absurdly exotic hardware no one could ever hope to obtain. I am not even commenting on the whole self-learning process, which is what has been the focus.

What is more, to achieve this, you are looking at an incredibly evolved eval function (not precisely, but it helps illustrate the point) that has roughly 28 million values compared to a few thousand at most for even the most sophisticated predecessors. In all the years I have seen discussions on the fight between smart searchers and fast searchers, I have never seen anyone come close to imagining that is how enormous a difference it would take, much less realize and prove it.

It is pure genius.
A0 and LC0 success is 90% due to hardware, and 10% due to "smart" software. All things Google used to create A0 existed since decades or at least a 5-10 years ago and are not invented by Google by any mean.
That is not much of an argument. Many many important advances used parts and elements that existed in one form or other before them. This in no way diminished their accomplishments.
Even A0 itself and the way it was presented and put was a marketing effort to advertise CloudTPU service.
Without incredibly fast hardware developed mainly in last 3-4 years A0 wouldn't exist. So if there is one thing ppl should be thankful to Google is that by creating their TPU hardware they created a competition to NVIDIA that pushed NVIDIA to create tremendous ML oriented cards. Those also rendered CloudTPU service obsolete ;).
You didn't get me. What I am saying is that Google is the one that did it because they had hardware resources and 3-4 years ago no one else had resources. So if Google didn't do it, someone else would most probably do it by today.
Google did it because it is something that interested them and because they had the resources. In any case, you know history is full of such tales of several working on a similar goal and the one to get there first is the one who goes into the history books. The other almost-weres are sidenotes for the most part. The phonograph (aka record player), the phone, the airplane, ... the list goes on.
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."

duncan
Posts: 10202
Joined: Mon Jul 07, 2008 8:50 pm

Re: Alphazero news

Post by duncan » Sun Dec 09, 2018 7:10 pm

Albert Silver wrote:
Sun Dec 09, 2018 4:51 pm
duncan wrote:
Sun Dec 09, 2018 4:40 pm
Albert Silver wrote:
Sun Dec 09, 2018 4:34 pm


Yet, that is what AlphaZero has done, and we are even able to bring this to the home user's PC thanks to Deep Mind's generosity with their knowledge, as well as the fantatsic Leela Chess community efforts. In other words that is not limited to some absurdly exotic hardware no one could ever hope to obtain. I am not even commenting on the whole self-learning process, which is what has been the focus.

What is more, to achieve this, you are looking at an incredibly evolved eval function (not precisely, but it helps illustrate the point) that has roughly 28 million values compared to a few thousand at most for even the most sophisticated predecessors. In all the years I have seen discussions on the fight between smart searchers and fast searchers, I have never seen anyone come close to imagining that is how enormous a difference it would take, much less realize and prove it.

It is pure genius.
Playing devil's advocate. Yes it is genius, but the chess community is not looking for genius we are looking to revolutionise chess playing and alpha zero seems to have maxed out at a level not significantly higher than an old version of stockfish without a book.

A dazzling 'toy', but a 'toy' nevertheless.

The future may be different, but that remains to be seen.
Needless to say, I disagree with pretty much every point you made. We will have to agree to disagree.
Needless to say, you are far more likely to be right than I am, as I know nothing about computer chess, but please could you point out any factual errors in my post.

good article here.
https://en.chessbase.com/post/the-full- ... -long-last

noobpwnftw
Posts: 340
Joined: Sun Nov 08, 2015 10:10 pm

Re: Alphazero news

Post by noobpwnftw » Sun Dec 09, 2018 8:05 pm

noobpwnftw wrote:
Sun Dec 09, 2018 5:31 pm
Brute-forcing of those 28 million parameters of a evaluation function in a black-box style is neither efficient nor intelligent.
Isn't it obvious that it is very easy to trick people into certain interpretations of my one liner, if I do not put any emphasis mark. I learned that only recently thanks to the papers.

All your discussions around "brute-force", "efficient" and "intelligent" are pointless without context, which is "what do you get out of such effort?"

Talking about building a tablebase, its efficiency is not important because I think none of you is actually going to re-generate them again, so it does not matter, whether it is intelligent is based on the metric used, some may argue that DTM50 is the most intelligent way and some may argue otherwise. By the end of the day, what you get out of it is a complete and mathematically sound solution to the problem, once and for all.

Hand-crafting an eval function, what you really get form a project like Stockfish is the understanding of how to write code to make sense of all the aspects putting together in a way that is statistically sound in practice.

Approaches like A0, given a black-box of 28 million floating numbers, which is neither perfect nor give much information on how it would come up with such evaluations, is more of a "yet another closed-source chess engine" scenario in practice, where you have to "understand" things by looking at it's output, seems to me neither efficient nor intelligent. I think if you do have such things in hand, it may be better just sleep with those numbers and brag about it all day.

Albert Silver
Posts: 2831
Joined: Wed Mar 08, 2006 8:57 pm
Location: Rio de Janeiro, Brazil

Re: Alphazero news

Post by Albert Silver » Sun Dec 09, 2018 8:14 pm

duncan wrote:
Sun Dec 09, 2018 7:10 pm
Albert Silver wrote:
Sun Dec 09, 2018 4:51 pm
duncan wrote:
Sun Dec 09, 2018 4:40 pm
Albert Silver wrote:
Sun Dec 09, 2018 4:34 pm


Yet, that is what AlphaZero has done, and we are even able to bring this to the home user's PC thanks to Deep Mind's generosity with their knowledge, as well as the fantatsic Leela Chess community efforts. In other words that is not limited to some absurdly exotic hardware no one could ever hope to obtain. I am not even commenting on the whole self-learning process, which is what has been the focus.

What is more, to achieve this, you are looking at an incredibly evolved eval function (not precisely, but it helps illustrate the point) that has roughly 28 million values compared to a few thousand at most for even the most sophisticated predecessors. In all the years I have seen discussions on the fight between smart searchers and fast searchers, I have never seen anyone come close to imagining that is how enormous a difference it would take, much less realize and prove it.

It is pure genius.
Playing devil's advocate. Yes it is genius, but the chess community is not looking for genius we are looking to revolutionise chess playing and alpha zero seems to have maxed out at a level not significantly higher than an old version of stockfish without a book.

A dazzling 'toy', but a 'toy' nevertheless.

The future may be different, but that remains to be seen.
Needless to say, I disagree with pretty much every point you made. We will have to agree to disagree.
Needless to say, you are far more likely to be right than I am, as I know nothing about computer chess, but please could you point out any factual errors in my post.

good article here.
https://en.chessbase.com/post/the-full- ... -long-last
When you say 'toy', it is a comment laced with prejudice, and also suggests this is not a serious thing. If a program can fight with the very best, I find that hard to call a 'toy'. Look at plain Leela right now. It is right up there and has been in development for less than a year. That is nothing short of incredible, and improvements have been coming along all throughout.

Then there is the plain reality that it is using a design no one had ever done before, able to fight with the best even when running a thousand times slower. More than that, it finds moves and ideas that are completely different from Stockfish and Co. It also misses moves that they find, so this is not more of the same, but something new you can complement your analysis and chess with. It can play longterm sacrifices naturally, with no need of artificial levers, as it has developed on a concept of winning chances, and has no real understanding in centipawns. The one Lc0 puts out is a weird translation, but you can see the true winning % if you activate the UCI option.

For me, all this is revolutionary.
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."

noobpwnftw
Posts: 340
Joined: Sun Nov 08, 2015 10:10 pm

Re: Alphazero news

Post by noobpwnftw » Sun Dec 09, 2018 8:20 pm

Albert Silver wrote:
Sun Dec 09, 2018 8:14 pm
it has developed on a concept of winning chances
Concept of winning chances is just as lame as concept of centipawns.

Given a mate-in-X position if it says anything else than 100% then it is wrong, if it says 100% then it will screw up your search.

It have its roots in image recognition NNs, which I also find hilarious, given a picture of a man, it might say "oh that looks 60% like a man, 30% like a dog, 5% like a car and 5% like a tree", very informative, isn't it? :D
Last edited by noobpwnftw on Sun Dec 09, 2018 8:23 pm, edited 1 time in total.

Post Reply