Reptile: a Scalable Metalearning Algorithm
arXiv: Learning, 2018.
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
PPT (Upload PPT)