RE: [Bug-gnubg] TD(lambda) training for neural networks -- a question

[Ian Shaw]

> -----Original Message-----
> From: Øystein Johansen
> Sent: 21 May 2009 09:19
> 
> Our experience is: TD is nice for kickstarting the training 
> process. But supervised training is the real thing. Make a 
> big database of positions and the rollout results according 
> to these positions and train supervised.
> 
> If you still would like to do TD training with your system, I 
> really recommend looking at Sutton/Barto.
> 

It's probably worth noting that Frank Berger has had a different experience. If 
I recall correctly, Frank used only TD training for BgBlitz, with no supervised 
training. (This was some years ago, so I may be out of data or just wrong.)

With the increase in processing power since the current gnubg net was 
developed, I wonder if there is some merit in having another crack at it. Are 
you doing any work on the NN side of things, Øystein? I think Joseph has 
stopped.

-- Ian