Meta reinforcement learning as task inference

Jan Humplik
Jan Humplik
Alexandre Galashov
Alexandre Galashov
Leonard Hasenclever
Leonard Hasenclever

arXiv: Learning, 2019.

Cited by: 38|Views24
EI

Abstract:

Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There has been considerable interest in designing reinforcement learning algorithms with similar properties. This includes several proposals to learn the learning algorithm itself, an idea also referred to as meta learning. ...More

Code:

Data:

Your rating :
0

 

Tags
Comments