Re: Ideas

[Heikki Levanto <heikki@xxxxxx>]

Xu, Mousheng <moushengxu@xxxxxxxxxxxxxxxxx> wrote:

> 	Could you educate us a bit on "TD-learning"? Is it Traing with
> Dataset? (I am embarassing myself)

Temporal Difference Learning. There is a good paper on it somewhere on the
net, I found it easily last time I had to reload it by searching
(altavista?) for Temporal Difference Learing. Quite interesting stuff.

> 	Before you go too far too big, just try a little thing -- teach
> it to learn how to play joseki. 

In my opinion, playing joseki is a far cry from a "little thing". My first
goal will be to make the program learn to capture juts one stone, then
multiple stones, then get an idea of when to pass, then play a whole game.

Naturally I will start on a 9x9 board, if not smaller, although my plan may
scale better to larger boards, as I do not feed the board image to the net
at all.

> 	If you get any progress, please let us know. 
Yes I will, but don't hold your breath, it may take a long while - I am busy
with my work and have other interests in my life... Maybe some day during
the next decade or two...


-- 
Heikki Levanto     LSD Levanto Software Development   heikki@xxxxxxxxxxxxxxxxx
               "In Murphy we Turst"