Reptile: a Scalable Metalearning Algorithm

Alex Nichol
Alex Nichol

arXiv: Learning, 2018.

Cited by: 113|Bibtex|Views17
Other Links: academic.microsoft.com

Abstract:

This paper considers metalearning problems, where there is a distribution of tasks, and we would like to obtain an agent that performs well (i.e., learns quickly) when presented with a previously unseen task sampled from this distribution. We present a remarkably simple metalearning algorithm called Reptile, which learns a parameter initi...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments