Modular meta-learning in abstract graph networks for combinatorial generalization

12/19/2018
by   Ferran Alet, et al.
0

Modular meta-learning is a new framework that generalizes to unseen datasets by combining a small set of neural modules in different ways. In this work we propose abstract graph networks: using graphs as abstractions of a system's subparts without a fixed assignment of nodes to system subparts, for which we would need supervision. We combine this idea with modular meta-learning to get a flexible framework with combinatorial generalization to new tasks built in. We then use it to model the pushing of arbitrarily shaped objects from little or no training data.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset