Skip to yearly menu bar Skip to main content


Poster

Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models

Alexander Neitz · Giambattista Parascandolo · Stefan Bauer · Bernhard Schölkopf

Room 517 AB #150

Keywords: [ Predictive Models ] [ Model-Based RL ]


Abstract:

We introduce a method which enables a recurrent dynamics model to be temporally abstract. Our approach, which we call Adaptive Skip Intervals (ASI), is based on the observation that in many sequential prediction tasks, the exact time at which events occur is irrelevant to the underlying objective. Moreover, in many situations, there exist prediction intervals which result in particularly easy-to-predict transitions. We show that there are prediction tasks for which we gain both computational efficiency and prediction accuracy by allowing the model to make predictions at a sampling rate which it can choose itself.

Live content is unavailable. Log in and register to view live content