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

page 1

page 2

page 3

page 4

research
06/26/2018

Modular meta-learning

Many prediction problems, such as those that arise in the context of rob...
research
08/04/2021

Black-Box and Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks

In this paper, we consider the problem of power control for a wireless n...
research
08/05/2019

Learning to Generalize to Unseen Tasks with Bilevel Optimization

Recent metric-based meta-learning approaches, which learn a metric space...
research
01/30/2021

On Data Efficiency of Meta-learning

Meta-learning has enabled learning statistical models that can be quickl...
research
05/20/2023

Meta Neural Coordination

Meta-learning aims to develop algorithms that can learn from other learn...
research
09/20/2018

Learning Quickly to Plan Quickly Using Modular Meta-Learning

Multi-object manipulation problems in continuous state and action spaces...
research
12/14/2021

How to Learn and Represent Abstractions: An Investigation using Symbolic Alchemy

Alchemy is a new meta-learning environment rich enough to contain intere...

Please sign up or login with your details

Forgot password? Click here to reset