[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: [Bug-gnubg] User training of the Neural Nets
From: |
Ian Shaw |
Subject: |
RE: [Bug-gnubg] User training of the Neural Nets |
Date: |
Fri, 25 Aug 2006 12:01:22 +0100 |
Albert Silver wrote on August 2006 20:10
> You see, while scouring the archives, I saw from a discussion
> from not long ago, that Ian Shaw had managed to get the plain
> TD training working, though no one (at least I saw nothing in
> the archives) commented on the effectiveness of his attempts.
> While looking at the CLI version, I saw two functions linked
> to 'train':
>
> Train database - Train the network from a database of
> positions Train td - Train the network from TD(0)
> zero-knowledge self-play
>
The train db function runs from the command line. I've set it running to see
what happens.
Does anyone know how many GHz.days it needs to run to have an effect? I can
send the resulting weights file to someone to benchmark. Better still, I will
run it myself if I can have some help setting up.
Like Øystein, I'm suspicious of the procedure. It reports that the contact and
crashed network have been trained on the same number of positions, which
implies that both networks' weights are being adjusted during td-training,
irrespective of whether positions are contact or crashed.
Frank Berger mentioned that BgBlitz had only received TD training, which
indicates that it is possible to get an expert standard on play using
TD_training alone.
As I understand it, gnubg's training went roughly like this:
TD-training to intermediate level (FIBS 1650).
Supervised training on rolled-out positions to get to advanced stage (FIBS
1800). Positions included some where gnubg was known to err, and others chosen
at random.
Supervised training on positions where 0-ply evaluation differed from 2-ply
evaluation. Gnubg achieved expert level (FIBS 1930).
Since Gnubg is now over the plateau reached by TD training, I wondered if a new
bout of TD training on top of the supervised training might be beneficial.
Øystein and Joseph, are you saying that you have already tried this, to no
avail?
-- Ian
- RE: [Bug-gnubg] User training of the Neural Nets, (continued)
- Réf. : Re: [Bug-gnubg] User training of the Neural Nets, Massimiliano . Maini, 2006/08/25
- RE: Réf. : Re: [Bug-gnubg] User training of the Neural Nets, Ian Shaw, 2006/08/25
- Re: Réf. : Re: [Bug-gnubg] Us er training of the Neural Nets, Christian Anthon, 2006/08/25
- Re: [Bug-gnubg] User training of the Neural Nets, Christian Anthon, 2006/08/27
- RE: [Bug-gnubg] User training of the Neural Nets, Ian Shaw, 2006/08/25
- Re: [Bug-gnubg] User training of the Neural Nets, Øystein Johansen, 2006/08/25
- RE: [Bug-gnubg] User training of the Neural Nets, Albert Silver, 2006/08/23
- RE: [Bug-gnubg] User training of the Neural Nets,
Ian Shaw <=
- RE: [Bug-gnubg] User training of the Neural Nets, Øystein O. Johansen, 2006/08/25
- Re: [Bug-gnubg] User training of the Neural Nets, Christian Anthon, 2006/08/25