It's already in the last version (called move evaluator network). I just haven't ported it to this new version yet, and I suspect it may be responsible for the difference in playing style.Werewolf wrote:Matthew,
A while back you specualted about using NN in the search as well as having a NN evaluation function.
Is this still a realistic goal and would it help you if you had access to more cores?
Carl
New Giraffe
Moderators: hgm, Rebel, chrisw
-
- Posts: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: New Giraffe
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: 12540
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Re: New Giraffe
I do not know much about torch.
Does your current code take advantage of GPU cards?
I would be especially interested to see if it can run on something like Jetson, with integrated memory:
http://www.nvidia.com/object/jetson-tk1 ... v-kit.html
It is a tiny GPU, and the CPU is wimpy, but there is no copying to and from RAM because GPU and CPU can share the same fast memory.
Does your current code take advantage of GPU cards?
I would be especially interested to see if it can run on something like Jetson, with integrated memory:
http://www.nvidia.com/object/jetson-tk1 ... v-kit.html
It is a tiny GPU, and the CPU is wimpy, but there is no copying to and from RAM because GPU and CPU can share the same fast memory.
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: 12540
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Re: New Giraffe
I guess that this is the torch that you used, is that right:
http://torch.ch/
http://torch.ch/
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: 273
- Joined: Wed Aug 24, 2016 9:49 pm
Re: New Giraffe
Is this search-Neural-Network used for moveOrdeirng or does it pick some of the possible moves and disregards everything else ?matthewlai wrote:It's already in the last version (called move evaluator network). I just haven't ported it to this new version yet, and I suspect it may be responsible for the difference in playing style.Werewolf wrote:Matthew,
A while back you specualted about using NN in the search as well as having a NN evaluation function.
Is this still a realistic goal and would it help you if you had access to more cores?
Carl
-
- Posts: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: New Giraffe
It does not use GPUs currently. At play time the CPU-GPU latency is higher than the time it would take to just evaluate on the CPU.Dann Corbit wrote:I do not know much about torch.
Does your current code take advantage of GPU cards?
I would be especially interested to see if it can run on something like Jetson, with integrated memory:
http://www.nvidia.com/object/jetson-tk1 ... v-kit.html
It is a tiny GPU, and the CPU is wimpy, but there is no copying to and from RAM because GPU and CPU can share the same fast memory.
A heterogeneous architecture may change that, but I don't have one to play with (and don't really have time at the moment even if I do).
Yes, torch.ch is the right Torch.
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: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: New Giraffe
It uses the move evaluator network to assign probabilities in a probability-based search. See the paper (chapter 5) for more details: https://arxiv.org/pdf/1509.01549v2.pdfCheckersGuy wrote:Is this search-Neural-Network used for moveOrdeirng or does it pick some of the possible moves and disregards everything else ?matthewlai wrote:It's already in the last version (called move evaluator network). I just haven't ported it to this new version yet, and I suspect it may be responsible for the difference in playing style.Werewolf wrote:Matthew,
A while back you specualted about using NN in the search as well as having a NN evaluation function.
Is this still a realistic goal and would it help you if you had access to more cores?
Carl
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: 4466
- Joined: Fri Apr 21, 2006 4:19 pm
- Location: IASI - the historical capital of MOLDOVA
- Full name: SilvianR
-
- Posts: 41423
- Joined: Sun Feb 26, 2006 10:52 am
- Location: Auckland, NZ
Re: New Giraffe
Hi Matthew,
sent you a message regarding a possible problem.
Graham.
sent you a message regarding a possible problem.
Graham.
gbanksnz at gmail.com
-
- Posts: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: New Giraffe
eval.t7. It doesn't look for or care about *.net anymore. The old format is not supported anymore.SzG wrote:If it finds eval.net and eval.t7 in the same directory, which one will it use?
Also, does it not need a meval file as well?
Move evaluator (will be meval.t7) has not been ported to this new version, yet. That will come later.
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: 793
- Joined: Sun Aug 03, 2014 4:48 am
- Location: London, UK
Re: New Giraffe
I am hoping yes. It seems to be quite a bit stronger at very fast games (0.5s per move), but that difference disappears at longer time controls.SzG wrote:Will it impove playing strength considerably? I ask this because my first test results are rather disappointing, showing no improvement at all over version 2015.09.08.matthewlai wrote: Move evaluator (will be meval.t7) has not been ported to this new version, yet. That will come later.
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.