About update_lr and meta_lr

hi,foolyc.
I have read your Meta-SGD code recently, that's a good project.
But I have some questions about the code and paper.
In the paper, update_lr and meta_lr seem like same item, and used element wise product with network parameters.
The line here seems not conform to the paper?
And set self.meta_lr and self.update same tf.variable?

Meta-SGD/maml.py

Line 64 in 4922a8d

self.update_lr = tf.Variable(0.001, "updatelr")

@luyao777
meta_lr is the meta learning rate for meta update.(outer update).
update_lr stands for the task learning rate for each task(inner update), which can be updated by the meta update(outer update)(this is the the key idea of meta-SGD).