Journal
ACM COMPUTING SURVEYS
Volume 54, Issue 5, Pages -Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3453160
Keywords
Hierarchical reinforcement learning; subtask discovery; skill discovery; hierarchical reinforcement learning survey; hierarchical reinforcement learning taxonomy
Categories
Funding
- National Research Foundation, Singapore under its AI Singapore Programme (AISG) [AISG2-RP-2020-019]
- Singapore Ministry of Education (MOE) Academic Research Fund (AcRF) Tier-1 grant [19-C220-SMU-023]
Ask authors/readers for more resources
Hierarchical Reinforcement Learning (HRL) allows for autonomous decomposition of challenging decision-making tasks, with a growing landscape of research approaches. Emphasis is placed on learning strategies, subtask discovery, transfer learning, and multi-agent learning challenges, with proposed open problems and practical application examples highlighted.
Hierarchical Reinforcement Learning (HRL) enables autonomous decomposition of challenging long-horizon decision-making tasks into simpler subtasks. During the past years, the landscape of HRL research has grown profoundly, resulting in copious approaches. A comprehensive overview of this vast landscape is necessary to study HRL in an organized manner. We provide a survey of the diverse HRL approaches concerning the challenges of learning hierarchical policies, subtask discovery, transfer learning, and multi-agent learning using HRL. The survey is presented according to a novel taxonomy of the approaches. Based on the survey, a set of important open problems is proposed to motivate the future research in HRL. Furthermore, we outline a few suitable task domains for evaluating the HRL approaches and a few interesting examples of the practical applications of HRL in the Supplementary Material.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available