Oh blimey! So it was just that vertical bar from the terminal. Sorry I was
groggy this morning and didn't read your post properly.
You say goal wasn't defined as a noun because it was at the bottom and it
only worked for me cos it was defined from an earlier attempt. But I use =.
everywhere so shouldn't it be a blank slate every time anyway?
I understand that rand =. _1 1 {~ ?@:(2"0) returns a block of 1s and _1s the
same shape as its parameter. What I don't understand is how the parameter
gets though (rand&[) to rand. Roger Stokes says:
(f @: g) y = f (g y)
(f & g) y = (f @: g) " G y
where G is the monadic rank of g , which is infinite in my case. But JfC
says f&g y = f g y. I'm not sure why that's not a contradiction, but I'm
using it in the latter sense so (rand&[) y = rand [ y = rand. When did y hit
rand? Oh I get it. rand is not a constant so it'll use the former case, then
[ ends up being used monadically which is the identity function. So I get
rand y. Correct? Well that was a lucky accident. Why don't I just write
rand? Aha. That works too. But how I make something that's undeniably
constant and would invoke the [ I (wrongly) wanted in the first place?
Speaking of which...
> in. What would I write in weightlearn if learnrate was 0.5&[ ?
Can you expand on these issues a bit? I am confused myself.
In C I'd just write:
learnrate = 0.5;
... learnrate*blahblahblah;
So the * is in the formula, not in the constant. That seems more intuitive
to me. How do I do that?
0 0 ( ; ,: ) 0 0
┌───┬───┐
│0 0│0 0│
└───┴───┘
(0 0 ; (0 0 ,: 0 0) )
┌───┬───┐
│0 0│0 0│
│ │0 0│
└───┴───┘
That was strange. I thought those two should be the same cos it's a dyadic
hook.
Here's the latest then:
goal =: _1 1
reward =: _1 _1
learnrate =: 0.5&*
forgetrate =: 0.5&*
jumblerate =: 0.2&*
rand =: _1 1 {~ ?@:(2"0)
matmul =: +/ .*
avg =: %&2@:+
avgio =: avg &.>
w =: 1&{::
io =: 0&{::
ifio =: 0&{::
ofio =: 1&{::
i =: ifio@io
o =: ofio@io
show =: ([(1!:2&2)@('-+'{~>:&0)@(i,o))
env =: (rand)`(reward&[) @. (-:&goal)
decide =: _1 1 {~ >:&0
think =: w (] ; decide@matmul) env@o
weightlearn =: learnrate@*/~&>/@((avgio io)~)
weightjumble =: (+ jumblerate@rand)
weightnew =: (weightlearn + (weightjumble@forgetrate@w@[))
cycle =: ((] ; weightnew) think)
cycle@show ^:40 (; ; ,:)~ 0 0
Now I'm trying to tidy up that weights business. The new weights matrix is a
sum of three matrices all based on the old weights and the new io, so it
should be written as a sum. I got this working:
r
*&10000 100 1
a
+/@r@(+ , - , *)
10 a 2
120820
a
1 2
3 4
b
5 6
7 8
g
+/@(+ , - , *)"0
a g b
7 16
27 40
a +/@((3 2 1)&*)"2@(+,-,*)"0 b
15 28
43 60
which is correct. So I'm trying to write:
rates = ((0.5 0.2 0.5)&*)"2 NB. remember, jumble, learn
weightnew =: +/@rates@( w@[ , rand@w@[ , (ofio */ ifio)@((avgio io)~ )
Or ( w&[ , w&[ , w&[ ). Doesnt work either way and I'm stumped.
A huge thank you to everyone who's putting so much time into helping me!
Adrian.
----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm
