Hierarchical reinforcement learning: A comprehensive survey

Author

Shubham PATERIA
Budhitama SUBAGDJA, Singapore Management UniversityFollow
Ah-hwee TAN, Singapore Management UniversityFollow
Chai QUEK

Publication Type

Journal Article

Version

acceptedVersion

Publication Date

6-2021

Abstract

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.

Discipline

Databases and Information Systems | Data Storage Systems

Research Areas

Data Science and Engineering

Publication

ACM Computing Surveys

Volume

54

Issue

5

First Page

1

Last Page

35

ISSN

0360-0300

Identifier

10.1145/3453160

Publisher

Association for Computing Machinery (ACM)

Embargo Period

8-3-2021

Citation

PATERIA, Shubham; SUBAGDJA, Budhitama; TAN, Ah-hwee; and QUEK, Chai. Hierarchical reinforcement learning: A comprehensive survey. (2021). ACM Computing Surveys. 54, (5), 1-35.
Available at: https://ink.library.smu.edu.sg/sis_research/6047

Copyright Owner and License

Author

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.