Yes and 0 seems to work best. Assumption being that most positions have 1 or at most a few good moves. All other moves are akin to passing or worse. In most equal-ish positions, passing will give the opponent a big advantage.Gian-Carlo Pascutto wrote: ↑Fri Dec 07, 2018 8:48 pm Were other settings ever considered, notably 0.5 or parent?
Alphazero news
Moderators: hgm, Rebel, chrisw
-
- Posts: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: Alphazero news
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: 1243
- Joined: Sat Dec 13, 2008 7:00 pm
Re: Alphazero news
I think this ends up explaining why FPU reductions as implemented by both LZ and lc0 work thoughmatthewlai wrote: ↑Fri Dec 07, 2018 10:24 pmYes and 0 seems to work best. Assumption being that most positions have 1 or at most a few good moves. All other moves are akin to passing or worse. In most equal-ish positions, passing will give the opponent a big advantage.Gian-Carlo Pascutto wrote: ↑Fri Dec 07, 2018 8:48 pm Were other settings ever considered, notably 0.5 or parent?
-
- Posts: 137
- Joined: Sat Dec 04, 2010 5:31 pm
- Location: 223
Re: Alphazero news
Hello Matthew, nice to see you back after so long !!
Does this mean Giraffe will get some updates in the future ?
Does this mean Giraffe will get some updates in the future ?
Judge without bias, or don't judge at all...
-
- Posts: 12604
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Re: Alphazero news
I think giraffe is called "AlphaZero" or "DeepMind" now.glennsamuel32 wrote: ↑Sat Dec 08, 2018 3:21 am Hello Matthew, nice to see you back after so long !!
Does this mean Giraffe will get some updates in the future ?
Taking ideas is not a vice, it is a virtue. We have another word for this. It is called learning.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
-
- Posts: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: Alphazero news
Thanks!glennsamuel32 wrote: ↑Sat Dec 08, 2018 3:21 am Hello Matthew, nice to see you back after so long !!
Does this mean Giraffe will get some updates in the future ?
Afraid not! AlphaZero is taking up all my time these days, and it's a very exciting project with lots of uncharted territory ahead . AlphaZero is basically what I ever wanted Giraffe to become... and then a lot more. I have never been this excited about computer chess my whole life.
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: 3026
- Joined: Wed Mar 08, 2006 9:57 pm
- Location: Rio de Janeiro, Brazil
Re: Alphazero news
Warmest congrats. I find that heartwarming to the extreme.matthewlai wrote: ↑Sat Dec 08, 2018 4:17 amThanks!glennsamuel32 wrote: ↑Sat Dec 08, 2018 3:21 am Hello Matthew, nice to see you back after so long !!
Does this mean Giraffe will get some updates in the future ?
Afraid not! AlphaZero is taking up all my time these days, and it's a very exciting project with lots of uncharted territory ahead . AlphaZero is basically what I ever wanted Giraffe to become... and then a lot more. I have never been this excited about computer chess my whole life.
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."
-
- Posts: 1766
- Joined: Wed Jun 03, 2009 12:14 am
Re: Alphazero news
but have you tried the deepmind openings? it seems clear that the Zeros lose elo playing prescribed openings. Test30 already has excellent results against SF10 in my tests so far (https://lichess.org/study/FHjaPySh) i would expect the strongest test10 net to score better, but i believe it's gotten very close.Laskos wrote: ↑Fri Dec 07, 2018 3:47 pmWhile that's true, Lc0 with the best nets on my powerful GPU and average CPU ("Leela Ratio" of say 2.5) beats heavily SF8, but loses slightly to SF10, from regular openings. Against SF8, it's similar to what happens in this paper. My guess is that this particular "old" A0 in those TCEC conditions is somewhat weaker than SF10.OneTrickPony wrote: ↑Fri Dec 07, 2018 12:13 pm
I am not convinced the newest SF would win against it. The ELO is calculated against a pool of similar engines. It's not clear if 50 or 100 ELO more against this pool is equal to 50-100 ELO more against an opponent of a different type.
Lc0 needs a "Leela Ratio" of 2.5 to have similar results to A0 ("Leela Ratio" 1 by definition), so Lc0 (with the best nets) is still lagging pretty significantly behind A0.
In some games it becomes apparent that they are fairly similar in playing style, strengths and weaknesses.
-
- Posts: 137
- Joined: Sat Dec 04, 2010 5:31 pm
- Location: 223
Re: Alphazero news
Matthew, could you divulge the size of the network file that A0 used ?
Judge without bias, or don't judge at all...
-
- Posts: 2204
- Joined: Sat Jan 18, 2014 10:24 am
- Location: Andorra
Re: Alphazero news
Congratulations!!! I don't understand anything about A0, but I will try that Andscacs finds ways to play better against itmatthewlai wrote: ↑Sat Dec 08, 2018 4:17 amThanks!glennsamuel32 wrote: ↑Sat Dec 08, 2018 3:21 am Hello Matthew, nice to see you back after so long !!
Does this mean Giraffe will get some updates in the future ?
Afraid not! AlphaZero is taking up all my time these days, and it's a very exciting project with lots of uncharted territory ahead . AlphaZero is basically what I ever wanted Giraffe to become... and then a lot more. I have never been this excited about computer chess my whole life.
Daniel José - http://www.andscacs.com
-
- Posts: 1217
- Joined: Thu May 10, 2007 2:49 pm
Re: Alphazero news
I would rather say what we know is:Astatos wrote: ↑Fri Dec 07, 2018 1:01 pm OK what we know :
1) Stockfish is the best engine in the world
2) LC0 guys did manage to reverse engineer A0 successfully
3) LC0 and A0 roughly at the same strength
4) NN are not less resource hungry than Alpha Beta
5) Scalability is about the same in both methods
6) Google has unacceptable behaviour, hiding data, obfuscating opponents and hyping results
1) We have real new kind of chess engines
2) Computer chess enthusiasts should be happy and excited
3) We are at the very beginning of a new age of computer chess, nn will dominate computer chess in the future
4) Google shares the knowledge (what they don't have to do)
5) Some people make us a gift in reproducing the work (what they don't have to do)
6) Instead of saying "thank you" some fanboys of the common engines have an unacceptable behavior.
The only thing I really dislike is, that Google don't want to build AI to solve Chess, Go or whatever games. They want to learn how to use AI for other purposes and I think this will be dangerous for mankind. At the moment an AI decides which commercials we see, which news we read. That leads to radicalization and division of the society. One day an AI will decide if someone goes to jail or not. Maybe people will go to jail because an AI thinks he will someday do a crime. One day autonomous robots will decide which person to kill, on a battlefield or to prevent a possible crime. Maybe one day an AI will press the red button.