AN EXHAUSTIVE SURVEY OF REINFORCEMENT LEARNING WITH HIERARCHICAL STRUCTURE

Anshul Chaturvedi, Nidhi Mishra

Abstract: Today reinforcement learning (RL) is holding the attention in research area under Machine Learning and AI. Hierarchical Reinforcement Learning (HRL) that break down the RL problem into sub-problems where solving of each sub-problem will be more powerful than solving the whole problem will be present in this paper. A review of the characteristics of HRL has been investigated as well as different domains have been highlighted those are based on HRL. Different domains must have different problems; some proposed solutions have been addressed. It has been discovered that HRL has not yet been that much discussed in the current existing research; the reason that motivated to work on this scenario. Some ideas have been come out into view during the work on this research and have been proposed for follow in future research

Keywords: Hierarchical Reinforcement Learning; Q-learning; Reinforcement Learning

DOI: https://doi.org/10.15623/ijret.2016.0502047