Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-27 Thread David Wu
I suspect the reason they were able to reasonably train a value net with multiple komi at the same time was because the training games they used in that paper were generated by a pure policy net, rather than by a MCTS player, where the policy net was trained from human games. Although humans give

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-27 Thread terry mcintyre via Computer-go
I'm sorry, did I miss soemthing here?  On Friday, October 27, 2017, 5:46:19 AM EDT, Gian-Carlo Pascutto wrote: On 27-10-17 00:33, Shawn Ligocki wrote: > But the data should be different for different komi values, right? > Iteratively producing self-play games and

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-27 Thread Gian-Carlo Pascutto
On 27-10-17 00:33, Shawn Ligocki wrote: > But the data should be different for different komi values, right? > Iteratively producing self-play games and training with the goal of > optimizing for komi 7 should converge to a different optimal player > than optimizing for komi 5. For the policy

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-26 Thread Shawn Ligocki
On Thu, Oct 26, 2017 at 2:02 PM, Gian-Carlo Pascutto wrote: > On 26-10-17 15:55, Roel van Engelen wrote: > > @Gian-Carlo Pascutto > > > > Since training uses a ridiculous amount of computing power i wonder > > if it would be useful to make certain changes for future research, > >

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-26 Thread Detlef Schmicker
>> >> >> *From:* Computer-go [mailto:computer-go-boun...@computer-go.org] *On >> Behalf Of *uurtamo . >> *Sent:* Wednesday, October 25, 2017 6:07 PM >> *To:* computer-go <computer-go@computer-go.org> >> *Subject:* Re: [Computer-go] Source code (Was:

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-26 Thread Erik van der Werf
o-boun...@computer-go.org] *On >> Behalf Of *uurtamo . >> *Sent:* Wednesday, October 25, 2017 6:07 PM >> *To:* computer-go <computer-go@computer-go.org> >> *Subject:* Re: [Computer-go] Source code (Was: Reducing network size? >> (Was: AlphaGo Zero)) >> >&

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-26 Thread Roel van Engelen
> > > *From:* Computer-go [mailto:computer-go-boun...@computer-go.org] *On > Behalf Of *uurtamo . > *Sent:* Wednesday, October 25, 2017 6:07 PM > *To:* computer-go <computer-go@computer-go.org> > *Subject:* Re: [Computer-go] Source code (Was: Reducing network size? &g

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-25 Thread Brian Sheppard via Computer-go
, October 25, 2017 6:07 PM To: computer-go <computer-go@computer-go.org> Subject: Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero)) Does the self-play step use the most recent network for each move? On Oct 25, 2017 2:23 PM, "Gian-Carlo Pascutto"

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-25 Thread uurtamo .
I ask because there are (nearly) bus-speed networks that could make multiple evaluation quick, especially if the various versions didn't differ by more than a fixed fraction of nodes. s. On Oct 25, 2017 3:03 PM, uurt...@gmail.com wrote: Does the self-play step use the most recent network for

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-25 Thread uurtamo .
Does the self-play step use the most recent network for each move? On Oct 25, 2017 2:23 PM, "Gian-Carlo Pascutto" wrote: > On 25-10-17 17:57, Xavier Combelle wrote: > > Is there some way to distribute learning of a neural network ? > > Learning as in training the DCNN, not

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-25 Thread Xavier Combelle
Nice to know. I wrongly believe that training such a big neural network would need considerable hardware. Le 25/10/2017 à 19:54, Álvaro Begué a écrit : > There are ways to do it, but it might be messy. However, the vast > majority of the computational effort will be in playing games to > generate

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-25 Thread Shawn Ligocki
My guess is that they want to distribute playing millions of self-play games. Then the learning would be comparatively much faster. Is that right? On Wed, Oct 25, 2017 at 11:57 AM, Xavier Combelle wrote: > Is there some way to distribute learning of a neural network

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-25 Thread Álvaro Begué
There are ways to do it, but it might be messy. However, the vast majority of the computational effort will be in playing games to generate a training database, and that part is trivial to distribute. Testing if the new version is better than the old version is also very easy to distribute.

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-25 Thread Xavier Combelle
Is there some way to distribute learning of a neural network ? Le 25/10/2017 à 05:43, Andy a écrit : > Gian-Carlo, I didn't realize at first that you were planning to create > a crowd-sourced project. I hope this project can get off the ground > and running! > > I'll look into installing this

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-25 Thread Gian-Carlo Pascutto
On 25-10-17 05:43, Andy wrote: > Gian-Carlo, I didn't realize at first that you were planning to create a > crowd-sourced project. I hope this project can get off the ground and > running! > > I'll look into installing this but I always find it hard to get all the > tool chain stuff going. I

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-25 Thread fotland
: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of Gian-Carlo Pascutto Sent: Tuesday, October 24, 2017 1:02 PM To: computer-go@computer-go.org Subject: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero)) On 23-10-17 10:39, Darren Cook wrote: >> The

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-24 Thread Andy
Gian-Carlo, I didn't realize at first that you were planning to create a crowd-sourced project. I hope this project can get off the ground and running! I'll look into installing this but I always find it hard to get all the tool chain stuff going. 2017-10-24 15:02 GMT-05:00 Gian-Carlo Pascutto

[Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

2017-10-24 Thread Gian-Carlo Pascutto
On 23-10-17 10:39, Darren Cook wrote: >> The source of AlphaGo Zero is really of zero interest (pun intended). > > The source code is the first-hand account of how it works, whereas an > academic paper is a second-hand account. So, definitely not zero use. This should be fairly accurate: