A neural model of hierarchical reinforcement learning

Daniel RasmussenUniversity of Waterloo
Chris EliasmithUniversity of Waterloo

Abstract

We present the first model capable of performing hierarchical reinforcement learning in a general, neurally detailed implementation. We show that this model is able to learn a spatial pickup and delivery task more quickly than one without hierarchical abilities. In addition, we show that this model is able to leverage its hierarchical structure to transfer learned knowledge between related tasks. These results point towards the advantages to be gained by using a hierarchical RL framework to understand the brain's powerful learning ability.

Files

A neural model of hierarchical reinforcement learning (389 KB)



Back to Table of Contents