Hello Carl,
The version I played was Giraffe version 20150908, so you are correct, must be an older version. Because it is a Winboard engine, I uploaded it into my old Chessmaster 10th edition platform. Of course, I gave it no openings book. Thank you for loading the game into an interface, but unfortunately I can't get it to work correctly!
New Giraffe (Sept 8)
Moderators: hgm, Rebel, chrisw
-
- Posts: 10
- Joined: Tue Sep 15, 2015 3:52 pm
- Location: Ohio
Re: New Giraffe (Sept 8)
"The moment you cease to explore the possibilities of every position, is the moment you fail to progress as a chess player!" (The thoughts of a pawn)
-
- Posts: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: New Giraffe (Sept 8)
It's all described in the paper: http://arxiv.org/abs/1509.01549Henk wrote:How does Giraffe gets its chess knowledge ? Where does it come from ?
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: 10
- Joined: Tue Sep 15, 2015 3:52 pm
- Location: Ohio
Re: New Giraffe (Sept 8)
Hi Matthew,
You're absolutely correct, I am using the current version, but did not include the NN files. I will try this and report back!
You're absolutely correct, I am using the current version, but did not include the NN files. I will try this and report back!
"The moment you cease to explore the possibilities of every position, is the moment you fail to progress as a chess player!" (The thoughts of a pawn)
-
- Posts: 7220
- Joined: Mon May 27, 2013 10:31 am
Re: New Giraffe (Sept 8)
What I understand is that you still have to tell Giraffe that it should use for instance Attack and Defend Maps. If so how do you know that that is right? .
-
- Posts: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: New Giraffe (Sept 8)
Henk wrote:What I understand is that you still have to tell Giraffe that it should use for instance Attack and Defend Maps. If so how do you know that that is right? .
Yes, but that's not required. It just makes the system perform a bit better.
I am actually thinking about removing that since I'm not sure if it's worth the speed lost.
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: 7220
- Joined: Mon May 27, 2013 10:31 am
Re: New Giraffe (Sept 8)
matthewlai wrote:Henk wrote:What I understand is that you still have to tell Giraffe that it should use for instance Attack and Defend Maps. If so how do you know that that is right? .
Yes, but that's not required. It just makes the system perform a bit better.
I am actually thinking about removing that since I'm not sure if it's worth the speed lost.
Sliding piece mobility is the second (and last) redundant extra term you use. But you can not remove it I guess otherwise performance drops. That means or learning method is not quite optimal or input representation is not optimal or network representation is not optimal for ideally it should find all terms itself given position representation as input.
[But might be such optimal solution does not exist or too expensive to search for]
-
- Posts: 7220
- Joined: Mon May 27, 2013 10:31 am
Re: New Giraffe (Sept 8)
Perhaps it might even be that if you use material, side to move, mobility and one cell for network representation you get better performance.
-
- Posts: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: New Giraffe (Sept 8)
Better performance and much worse chess, yes. I don't think I want to do that.Henk wrote:Perhaps it might even be that if you use material, side to move, mobility and one cell for network representation you get better performance.
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: 7220
- Joined: Mon May 27, 2013 10:31 am
Re: New Giraffe (Sept 8)
Might even be better chess. No proof. No test. So I don't know. The less cells the easier to tune.matthewlai wrote:Better performance and much worse chess, yes. I don't think I want to do that.Henk wrote:Perhaps it might even be that if you use material, side to move, mobility and one cell for network representation you get better performance.
-
- Posts: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: New Giraffe (Sept 8)
I have tested extensively. The current network size is optimal.Henk wrote:Might even be better chess. No proof. No test. So I don't know. The less cells the easier to tune.matthewlai wrote:Better performance and much worse chess, yes. I don't think I want to do that.Henk wrote:Perhaps it might even be that if you use material, side to move, mobility and one cell for network representation you get better performance.
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.