A Core Task Abstraction Approach to Hierarchical Reinforcement Learning (Extended Abstract)

Zhuoru Li (National University of Singapore), Akshay Narayan (National University of Singapore), Tze-Yun Leong (National University of Singapore & Singapore Management University)

Abstract

We propose a new, core task abstraction (CTA) approach to learning the relevant transition functions in model-based hierarchical reinforcement learning. CTA exploits contextual independences of the state variables conditional on the taskspecific actions; its promising performance is demonstrated through a set of benchmark problems.