[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: [Bug-gnubg] TD(lambda) training for neural networks -- a question
From: |
Ian Shaw |
Subject: |
RE: [Bug-gnubg] TD(lambda) training for neural networks -- a question |
Date: |
Wed, 10 Jun 2009 17:20:39 +0100 |
> -----Original Message-----
> From: Øystein Johansen [mailto:address@hidden
> Sent: 21 May 2009 10:41
>
> I remember I first tried TD training. (lambda=0), and I made
> the same experience as Joseph reported. TD is slow. However,
> I was able to run 5000 games/minutes. TDG 1.0 was trained
> with 300.000 games, and I'm able to reach that in an hour.
> Maybe TD can be reconsidered.
>
Did you use gnubg itself for the TD training? As I remember, gnubg's training
function is so old that it pre-dates the split to race and contact nets.
Therefore I was under the impression that it would not work.
-- Ian
[Prev in Thread] |
Current Thread |
[Next in Thread] |
- RE: [Bug-gnubg] TD(lambda) training for neural networks -- a question,
Ian Shaw <=