python_uct icon indicating copy to clipboard operation
python_uct copied to clipboard

Published 20 hours ago • verified publisher icon brilee

Why is the denominator of Q "1 + self.child_number_visits"?

Open kekmodel opened this issue 7 years ago • 2 comments

https://github.com/brilee/python_uct/blob/7e78e3db012118d661889af66eb78e63137234d0/numpy_impl.py#L33

kekmodel avatar Aug 18 '18 09:08 kekmodel

This is to prevent dividing by Zero.

liuruoze avatar Dec 06 '18 03:12 liuruoze

It is different from the paper.

kekmodel avatar Dec 12 '18 22:12 kekmodel