Matthew, I have one last question regarding the implementation details that aren't explicit in the paper.
Normally, an MCTS search would do "tree reuse" from move to move, carrying forward the subtree that was actually chosen. But during the training, there is noise added to the root. If one does tree reuse, the effect of the noise is lessened. Leela Chess Zero decided to disable tree reuse because of that. Leela Zero has kept it enabled.
Could you clarify how it was done in DeepMind's version?
Alphazero news
Moderators: hgm, Rebel, chrisw
-
- Posts: 10948
- Joined: Wed Jul 26, 2006 10:21 pm
- Full name: Kai Laskos
Re: Alphazero news
I don't understand a word of what you wrote. Top journals ("Nature" and "Science" are the top journals in sciences) want to be relevant, and their content to have high significance for current science and its development.noobpwnftw wrote: ↑Tue Dec 11, 2018 3:30 pm I find it interesting that the purpose of such journals are for people to have a place to share their discoveries among others, when they have no ability to reach the audience on their own. Why would anyone want to 'bar' their own papers from getting published anyway? If you don't want to get it published, don't even bother writing a paper on it.
Barring is what the journals supposed to do, ifthen the problem is not with the researchers.many, many very solid researchers never in their life get to have a "Nature" or a "Science" paper.
I do not see any necessity to have my emotions attached to such titles, but maybe that's not for everyone.
The simple fact that ML, especially reinforcement learning using deep networks proved above-human-capabilities first in Go and IIRC only later, with more involved techniques, in Pac-Man, is very noteworthy even for me, a complete amateur in this field. We are closer to understanding what humans are up to in daily life, Pac-Man being an ultra-simplified caricature of the daily life. Deep Mind paper on Go and this more generalized AlphaZero paper ARE significant, absolutely the level to be published in "Nature" and "Science". That Google/DeepMind have it easy to get such feats, that it's a PR stunt, marketing trick and so on, is not the business of these journals, as long as corruption is not involved. These journals, if they want to preserve their stature and authority, have to inform from specialists to amateurs in this field like me how the significant progress in this important research domain is going.
-
- Posts: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: Alphazero news
It is enabled at all times unless we are testing something specific that will be affected by it. We introduce diversity in two ways - dirichlet noise and visit count sampling.Gian-Carlo Pascutto wrote: ↑Tue Dec 11, 2018 4:12 pm Matthew, I have one last question regarding the implementation details that aren't explicit in the paper.
Normally, an MCTS search would do "tree reuse" from move to move, carrying forward the subtree that was actually chosen. But during the training, there is noise added to the root. If one does tree reuse, the effect of the noise is lessened. Leela Chess Zero decided to disable tree reuse because of that. Leela Zero has kept it enabled.
Could you clarify how it was done in DeepMind's version?
Dirichlet noise is used to modify prior at the root node before each search (if it's enabled). So if a subtree is reused, when the next search starts it will be added to the node that is now the root node.
Visit count sampling isn't really affected.
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.
-
- Posts: 27796
- Joined: Fri Mar 10, 2006 10:06 am
- Location: Amsterdam
- Full name: H G Muller
Re: Alphazero news
Oh yeah? How many Science or Nature papers do you have to your name that did not have the approval of the referees?
That you even mention 'double blind' here shows that you have no clue whatsoever how the peer-review system works, and are just shooting off your mouth as usual. Of course it is not double blind. I have refereed hundreds of papers for Journals like Science, Nature, Pys. Rev. Lett., Phys. Rev. A, J. Phys. B etc, and I always got to see the full title and author list as a referee. 'Anonymous referee' just means that the authors who submitted the paper don't know the referee. So that it would be impossible to affect their decision by threats or bribes, without actually bribing everyone in the field.
-
- Posts: 1470
- Joined: Mon Apr 23, 2018 7:54 am
Re: Alphazero news
Yes, yeah. The reviewers can be in disagreement. It happens. Depends how much the unhappy reviewer wants to fight.
This discussion of Nature & Science is sorta off topic, but if everyone wants to talk about it that's ok.
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: Alphazero news
It seems with age you are becoming dyslexic. Kind of missed the whole part of the sentence starting with "even when" (or "all being happy" in jp's comment). There is quite bunch of journals that have a double blind policy. That fact you didn't hear about it reflects more on your lack of actual experience outside of your small self-centric world and the need of empty bragging than anything else.hgm wrote: ↑Tue Dec 11, 2018 5:13 pmOh yeah? How many Science or Nature papers do you have to your name that did not have the approval of the referees?
That you even mention 'double blind' here shows that you have no clue whatsoever how the peer-review system works, and are just shooting off your mouth as usual. Of course it is not double blind. I have refereed hundreds of papers for Journals like Science, Nature, Pys. Rev. Lett., Phys. Rev. A, J. Phys. B etc, and I always got to see the full title and author list as a referee. 'Anonymous referee' just means that the authors who submitted the paper don't know the referee. So that it would be impossible to affect their decision by threats or bribes, without actually bribing everyone in the field.
-
- Posts: 27796
- Joined: Fri Mar 10, 2006 10:06 am
- Location: Amsterdam
- Full name: H G Muller
-
- Posts: 186
- Joined: Fri Oct 10, 2014 10:05 pm
- Location: Berkeley, CA
Re: Alphazero news
This is an important question. Matthew, can you confirm whether Brainfish was used, or merely Stockfish with the Cerebellum polyglot book? It's my understanding that the Brainfish binary will use the stored evaluations in search, whereas SF + polyglot will not.
-Carl
-
- Posts: 186
- Joined: Fri Oct 10, 2014 10:05 pm
- Location: Berkeley, CA
Re: Alphazero news
Oh no!matthewlai wrote: ↑Tue Dec 11, 2018 1:54 pm We used the BrainFish player for the book moves, and switch to SF8 (for consistency with other results) once out of book. We did that to make sure we were using the opening book correctly, and we weren't aware of the BF UCI option for diversity, so we only tried enforcing diversity from the AZ side.
-Carl
-
- Posts: 1339
- Joined: Fri Nov 02, 2012 9:43 am
- Location: New Delhi, India
Re: Alphazero news
Your simple Statement is open to different interpretations.
But fair enough.
i7 5960X @ 4.1 Ghz, 64 GB G.Skill RipJaws RAM, Twin Asus ROG Strix OC 11 GB Geforce 2080 Tis