Alphazero news

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

Moderators: bob, hgm, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
jorose
Posts: 268
Joined: Thu Jan 22, 2015 2:21 pm
Location: Zurich, Switzerland
Full name: Jonathan Rosenthal

Re: Alphazero news

Post by jorose » Tue Dec 11, 2018 9:56 am

matthewlai wrote:
Tue Dec 11, 2018 3:20 am

Hi Matthew,

Nice to see you on the forum again!
I was a big fan of your probability based search. In fact, shortly after you published your thesis I read it and my only confusion was why you did it in chess and not Go, so I wrote my B.Sc. thesis doing exactly that. Naturally, I was wondering whether you got to try your probability based search further in AlphaZero or any other project?

With best regards,
Jonathan Rosenthal
-Jonathan

Thomas A. Anderson
Posts: 18
Joined: Tue Feb 23, 2016 5:57 pm

Re: Alphazero news

Post by Thomas A. Anderson » Tue Dec 11, 2018 10:24 am

Matthew, thank you very much for participating in this thread! Everyone here should be grateful, that we are now getting the answers that were missing so much after releasing of the preliminary paper last December. Let's keep this discussion a technical one. With regards to this, I have a question, that came up while I was greedily digging through the papers. One number seems to be very odd to me: In the match against the SF with opening book (Brainfish), when AZ play black, it gets ~2/4 % wins against SF8/SF9, but ~18% wins when playing against the supposedly stronger Brainfish ?! Beside a docu bug, I can imagine two possible reasons: Either the number of games in this match has been very low or AZ discovered some poor opening book lines. The latter would be very interesting, especially how many and which lines are affected. While getting the game notation from these matches would be perfect, knowing how many games have been played in these tests would also be helpful.
Thanks again for your contribution, Matthew!
cu

noobpwnftw
Posts: 360
Joined: Sun Nov 08, 2015 10:10 pm

Re: Alphazero news

Post by noobpwnftw » Tue Dec 11, 2018 11:06 am

Over the course of 2 years since the first appearance there must have been numerous cases that people asked those "technical" questions, then I got the feeling that it is either they aren't going to answer you anyway or there is simply no study about them after all.

If they do care about academics then how they would come up with that half-decent paper in the first place? For most of the things you find useful actually appears in "supplementary data" which I guess was as per peer-reviewer's request. Makes the whole thing look like a giant advertisement sheet where you find all the specifics in a tiny "terms and conditions" block at the corner on the back of the page.

User avatar
hgm
Posts: 23723
Joined: Fri Mar 10, 2006 9:06 am
Location: Amsterdam
Full name: H G Muller
Contact:

Re: Alphazero news

Post by hgm » Tue Dec 11, 2018 11:16 am

You don't seem to have much experience with publishing papers in Science (the journal). My experience is that it is very difficult even to get 'fully decent' papers published there.

noobpwnftw
Posts: 360
Joined: Sun Nov 08, 2015 10:10 pm

Re: Alphazero news

Post by noobpwnftw » Tue Dec 11, 2018 11:26 am

Is it because people who wrote those 'fully decent' papers are not Google-branded?

But in my view a 'decent paper' is still a decent paper even if it is published on a morning newspaper.

User avatar
Laskos
Posts: 9456
Joined: Wed Jul 26, 2006 8:21 pm
Full name: Kai Laskos

Re: Alphazero news

Post by Laskos » Tue Dec 11, 2018 11:48 am

noobpwnftw wrote:
Tue Dec 11, 2018 11:26 am
Is it because people who wrote those 'fully decent' papers are not Google-branded?

But in my view a 'decent paper' is still a decent paper even if it is published on a morning newspaper.
You have no idea how is to publish in "Nature" and "Science" (Deep Mind publishing in both on this same theme). HGM has a "Nature" paper. I don't have, although I do have (few) papers in the best journals of physics (Phys. Rev. Letters, for example). I don't know about morning newspapers, not exactly my field of expertise. Many, many very solid researchers never in their life get to have a "Nature" or a "Science" paper.
Last edited by Laskos on Tue Dec 11, 2018 11:53 am, edited 2 times in total.

matthewlai
Posts: 793
Joined: Sun Aug 03, 2014 2:48 am
Location: London, UK
Contact:

Re: Alphazero news

Post by matthewlai » Tue Dec 11, 2018 11:50 am

glennsamuel32 wrote:
Tue Dec 11, 2018 5:04 am
@Matthew

IBM had a "whole series of GM's" training Deep Blue, for the Kasparov matchup.
AlphaGo had one Go player as a consultant, I think.

Has DeepMind used the services of any past or present GMs or IMs while creating A0 ?
If yes, could we know who ? :D
Yes we did have Fan Hui as a consultant for AlphaGo.

There wasn't one for AlphaZero during development of this Science version, but we did have GM Matthew Sadler look at the games in the paper and to pick the ones he thought was most interesting. We also collaborated with him later on the World Chess Championship commentary [1][2], and their upcoming book [3]. We obviously learned a few things about AlphaZero in the process.

[1]: https://chess24.com/en/read/news/alphaz ... -games-1-8
[2]: https://chess24.com/en/read/news/alphaz ... games-9-12
[3]: https://www.newinchess.com/game-changer
Disclosure: I work for DeepMind on the AlphaZero project, but everything I say here is personal opinion and does not reflect the views of DeepMind / Alphabet.

matthewlai
Posts: 793
Joined: Sun Aug 03, 2014 2:48 am
Location: London, UK
Contact:

Re: Alphazero news

Post by matthewlai » Tue Dec 11, 2018 11:56 am

jorose wrote:
Tue Dec 11, 2018 9:56 am
matthewlai wrote:
Tue Dec 11, 2018 3:20 am

Hi Matthew,

Nice to see you on the forum again!
I was a big fan of your probability based search. In fact, shortly after you published your thesis I read it and my only confusion was why you did it in chess and not Go, so I wrote my B.Sc. thesis doing exactly that. Naturally, I was wondering whether you got to try your probability based search further in AlphaZero or any other project?

With best regards,
Jonathan Rosenthal
Thanks! I am glad you found the idea interesting. It's something I wish I had time to explore further, because I really felt it makes more sense than depth-limited alpha-beta.

It wasn't used in AZ because AZ is based on MCTS, and my goal of the probability-based search was to basically "make alpha-beta more MCTS". MCTS already naturally shapes the tree the way a probability-based search would. It also makes incorporating prior much simpler. The only reason I didn't actually use MCTS was because, like everyone at the time, I didn't think it would be possible to use MCTS on a game that has so much sharp tactics. In fact, we weren't sure about that either until we actually tried AlphaZero on chess.
Disclosure: I work for DeepMind on the AlphaZero project, but everything I say here is personal opinion and does not reflect the views of DeepMind / Alphabet.

matthewlai
Posts: 793
Joined: Sun Aug 03, 2014 2:48 am
Location: London, UK
Contact:

Re: Alphazero news

Post by matthewlai » Tue Dec 11, 2018 12:13 pm

Thomas A. Anderson wrote:
Tue Dec 11, 2018 10:24 am
Matthew, thank you very much for participating in this thread! Everyone here should be grateful, that we are now getting the answers that were missing so much after releasing of the preliminary paper last December. Let's keep this discussion a technical one. With regards to this, I have a question, that came up while I was greedily digging through the papers. One number seems to be very odd to me: In the match against the SF with opening book (Brainfish), when AZ play black, it gets ~2/4 % wins against SF8/SF9, but ~18% wins when playing against the supposedly stronger Brainfish ?! Beside a docu bug, I can imagine two possible reasons: Either the number of games in this match has been very low or AZ discovered some poor opening book lines. The latter would be very interesting, especially how many and which lines are affected. While getting the game notation from these matches would be perfect, knowing how many games have been played in these tests would also be helpful.
Thanks again for your contribution, Matthew!
It's hard to say and I don't want to speculate much beyond what we have data to support, but my guess (and I can very well be wrong) is that there's much less diversity when SF uses the BF opening book. We already didn't have a lot of diversity from start position, but start position at least has several variations that are roughly equal and both AZ and SF have enough non-determinism (through multi-threaded scheduling mostly) that we still got reasonably diverse games. With the BF games we took out most of SF's non-determinism, and it's possible that SF just ends up playing a line that's not very good often, or something like that. In fact, we found that as we explained in the paper, if we force AZ to play some sub-optimal moves (in its opinion) to enforce diversity, we win even more games! I realise there's a lot of hand-waving here, but there are just too many possibilities.

I don't remember the number of games played, but it was more than high enough that the result is statistically significant.

We decided to release games from the start position and TCEC positions as the main result of the chess part of the paper because start position is more scientifically pure (they were actually playing the game of chess, not a game that's just like chess except you are forced to start from these positions), and from TCEC openings we show that we can play well even in openings that it wouldn't normally play.
Disclosure: I work for DeepMind on the AlphaZero project, but everything I say here is personal opinion and does not reflect the views of DeepMind / Alphabet.

duncan
Posts: 10362
Joined: Mon Jul 07, 2008 8:50 pm

Re: Alphazero news

Post by duncan » Tue Dec 11, 2018 12:18 pm

Laskos wrote:
Tue Dec 11, 2018 11:48 am

You have no idea how is to publish in "Nature" and "Science" (Deep Mind publishing in both on this same theme). HGM has a "Nature" paper. I don't have, although I do have (few) papers in the best journals of physics (Phys. Rev. Letters, for example).
Do you have a link ?

Post Reply