GNU bug report logs - #63088
[PATCH 0/3] Add Lc0

Previous Next

Full log

Message #23 received at 63088 <at> debbugs.gnu.org (full text, mbox):

From: Simon Tournier <zimon.toutoune <at> gmail.com>
To: zamfofex <zamfofex <at> twdb.moe>, 宋文武 <iyzsong <at> envs.net>
Cc: 63088 <at> debbugs.gnu.org
Subject: Re: [bug#63088] [PATCH 0/3] Add Lc0
Date: Tue, 16 May 2023 14:16:25 +0200

Hi,

On Thu, 11 May 2023 at 18:25, zamfofex <zamfofex <at> twdb.moe> wrote:
>> Will we able to train a model from source?  And how much will it cost?
>> 
>> As far as I know, guix haven't decided to accept pre-trained models:
>> 
>> https://yhetil.org/guix/xanfHBZT3lYlyrr_OqHHMWkunLeZZlcxzY37_T3TeZo7mfJClD5-OTbkXDH2f3lMTkn94YIFVUj-Z31BP2Wj0W2rISNP6glC2PzXcPdb560=@protonmail.com/
>
> I don’t think it is feasible. Lc0’s approach is based on self‐play
> reinforcement‐learning, which in effect means that training starts
> with no knowledge about chess except for its rules (playing seemingly
> random moves), and going from there to learn increasingly more about
> it. So, in practice, this means it would take multiple months or at
> least several weeks to attain a neural network model that is anywhere
> close to as effective as the ones provided and pre‐trained. Besides, I
> believe training requires a (reasonably decent) GPU.

I concur.


> But the network isn’t prohibitively large and its license is not
> proprietary. I’ll also note that Stockfish (packaged immediately above
> my Lc0 package) *does* itself include a provided pre‐trained network
> and no‐one has really complained about it, so I think it should be
> fine here too.

I will try to dedicate some time for reviewing this patch set.


Cheers,
simon

Previous Next

GNU bug tracking system
Copyright (C) 1999 Darren O. Benham, 1997,2003 nCipher Corporation Ltd, 1994-97 Ian Jackson.