ES-MAML: Simple Hessian-Free Meta Learning

ICLR, 2020.

Cited by: 18|Views108
EI
Weibo:
Evolution Strategies-Model Agnostic Meta Learning can be paired with nonsmooth adaptation operators such as hill climbing, which we found empirically to yield better exploratory behavior and better performance on sparse-reward environments

Abstract:

We introduce ES-MAML, a new framework for solving the model agnostic meta learning (MAML) problem based on Evolution Strategies (ES). Existing algorithms for MAML are based on policy gradients, and incur significant difficulties when attempting to estimate second derivatives using backpropagation on stochastic policies. We show how ES can...More

Code:

Data:

Your rating :
0

 

Tags
Comments