Hierarchical Reinforcement Learning: A Survey

Abstract

Reinforcement Learning (RL) has been an interesting research area in Machine Learning and AI. Hierarchical Reinforcement Learning (HRL) that decomposes the RL problem into sub-problems where solving each of which will be more powerful than solving the entire problem will be our concern in this paper. A review of the state-of-the-art of HRL has been investigated. Different HRL-based domains have been highlighted. Different problems in such different domains along with some proposed solutions have been addressed. It has been observed that HRL has not yet been surveyed in the current existing research; the reason that motivated us to work on this paper. Concluding remarks are presented. Some ideas have been emerged during the work on this research and have been proposed for pursuing a future research.