pat-coady/trpo

Ocasional NaN's

bernardocortez opened this issue · 0 comments

Hi! Thanks for the great job you did with the implementation.
I was playing a bit with your code and, in some runs, the "kl" that KLEntropy's call outputs is nan. I am not being able to reproduce this error, it only happens sometimes.

Have you experience? Can you guess any cause for it?