Learning Feature Relevance Through Step Size Adaptation in Temporal-Difference Learning

There is a long history of using meta learning as representation learning, specifically for determining the relevance of inputs. In this paper, we examine an instance of meta-learning in which feature relevance is learned by adapting step size parameters of stochastic gradient descent---building on...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Kearney, Alex, Veeriah, Vivek, Travnik, Jaden, Pilarski, Patrick M, Sutton, Richard S
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 08.03.2019
Subjects
Algorithms
Artificial neural networks
Linear functions
Machine learning
Online AccessGet full text

Cover

More Information
Summary:There is a long history of using meta learning as representation learning, specifically for determining the relevance of inputs. In this paper, we examine an instance of meta-learning in which feature relevance is learned by adapting step size parameters of stochastic gradient descent---building on a variety of prior work in stochastic approximation, machine learning, and artificial neural networks. In particular, we focus on stochastic meta-descent introduced in the Incremental Delta-Bar-Delta (IDBD) algorithm for setting individual step sizes for each feature of a linear function approximator. Using IDBD, a feature with large or small step sizes will have a large or small impact on generalization from training examples. As a main contribution of this work, we extend IDBD to temporal-difference (TD) learning---a form of learning which is effective in sequential, non i.i.d. problems. We derive a variety of IDBD generalizations for TD learning, demonstrating that they are able to distinguish which features are relevant and which are not. We demonstrate that TD IDBD is effective at learning feature relevance in both an idealized gridworld and a real-world robotic prediction task.
ISSN:2331-8422