Closed keven425 closed 6 years ago
https://github.com/openai/baselines/blob/4993286230ac92ead39a66005b7042b56b8598b0/baselines/common/distributions.py#L155
On this line above, it takes log twice on u. Why is that the case? I thought it should only take log once, like this:
return tf.argmax(self.logits -tf.log(u), axis=-1)
@joschu
-log(-log(uniform)) is the Gumbel distribution. This use a Gumbel-Softmax to sample from a uniform distribution.
-log(-log(uniform))
https://github.com/openai/baselines/blob/4993286230ac92ead39a66005b7042b56b8598b0/baselines/common/distributions.py#L155
On this line above, it takes log twice on u. Why is that the case? I thought it should only take log once, like this:
@joschu