Comment or code problem. about minigo HOT 7 CLOSED

raising to an exponent < 1 will still 'squash' the numbers closer together, compressing their ratios.

from minigo.

The confusion is over the comment: "exponentiate the probabilities by a temperature slightly larger than unity". But the code is hiding the true value of T. T = 1/0.95, not 0.95.

from minigo.

@killerducky Can you point me to the code where the true value of T is calculated? I just see this

from minigo.

They just wrote it in a different form. It's the same as this:

temp = 1.0/0.95
probs = probs ** (1/temp)

from minigo.

@amj yes, if the number is > 1 otherwise it does the opposite.

from minigo.

@marcocalignano not sure what you're saying. If the concern is that we are raising the raw visit counts to an exponent < 1, that has the effect of 'squashing' the numbers.

i.e., [1, 10, 100] ** 0.9 = [1, 7.9, 63]

This is also true for numbers < 1
[0.01, 0.1, 1] ** .9 = [.02, .13, 1]

the arithmetic ratios are smaller.

from minigo.

@amj Ok sorry if the arithmetic ratios is what count you are right I was just a bit disturbed by the fact that ifthe count is less that 1 you increase the number, if it it bigger than 1 you decrease it.

from minigo.