papers AI Learner
The Github is limit! Click to go to the new site.

Modular meta-learning

2019-05-02
Ferran Alet, Tomás Lozano-Pérez, Leslie P. Kaelbling

Abstract

Many prediction problems, such as those that arise in the context of robotics, have a simplifying underlying structure that, if known, could accelerate learning. In this paper, we present a strategy for learning a set of neural network modules that can be combined in different ways. We train different modular structures on a set of related tasks and generalize to new tasks by composing the learned modules in new ways. By reusing modules to generalize we achieve combinatorial generalization, akin to the “infinite use of finite means” displayed in language. Finally, we show this improves performance in two robotics-related problems.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1806.10166

PDF

http://arxiv.org/pdf/1806.10166


Comments

Content