An efficient approach to model-based hierarchical reinforcement learning

We propose a model-based approach to hierarchical reinforcement learning that exploits shared knowledge and selective execution at different levels of abstraction, to efficiently solve large, complex problems. Our framework adopts a new transition dynamics learning algorithm that identifies the comm...

Full description

Saved in:

Bibliographic Details
Main Authors:	LI, Zhuoru, NARAYAN, Akshay, LEONG, Tze-Yun
Format:	text
Language:	English
Published:	Institutional Knowledge at Singapore Management University 2017
Subjects:	Reinforcement learning hierarchical reinforcement learning MAXQ R-MAX model-based reinforcement learning Bench-mark problems Feature combination Hierarchical reinforcement learning Levels of abstraction Model based approach Problem characterization Robotic environments State-of-the-art algorithms Artificial Intelligence and Robotics Operations Research, Systems Engineering and Industrial Engineering Theory and Algorithms
Online Access:	https://ink.library.smu.edu.sg/sis_research/4398 https://ink.library.smu.edu.sg/context/sis_research/article/5401/viewcontent/14771_66644_1_PB.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Singapore Management University
Language:	English

id	sg-smu-ink.sis_research-5401
record_format	dspace
spelling	sg-smu-ink.sis_research-54012020-03-25T03:26:25Z An efficient approach to model-based hierarchical reinforcement learning LI, Zhuoru NARAYAN, Akshay LEONG, Tze-Yun We propose a model-based approach to hierarchical reinforcement learning that exploits shared knowledge and selective execution at different levels of abstraction, to efficiently solve large, complex problems. Our framework adopts a new transition dynamics learning algorithm that identifies the common action-feature combinations of the subtasks, and evaluates the subtask execution choices through simulation. The framework is sample efficient, and tolerates uncertain and incomplete problem characterization of the subtasks. We test the framework on common benchmark problems and complex simulated robotic environments. It compares favorably against the stateof-the-art algorithms, and scales well in very large problems. 2017-02-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4398 https://ink.library.smu.edu.sg/context/sis_research/article/5401/viewcontent/14771_66644_1_PB.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Reinforcement learning hierarchical reinforcement learning MAXQ R-MAX model-based reinforcement learning Bench-mark problems Feature combination Hierarchical reinforcement learning Levels of abstraction Model based approach Problem characterization Robotic environments State-of-the-art algorithms Artificial Intelligence and Robotics Operations Research, Systems Engineering and Industrial Engineering Theory and Algorithms
institution	Singapore Management University
building	SMU Libraries
continent	Asia
country	Singapore Singapore
content_provider	SMU Libraries
collection	InK@SMU
language	English
topic	Reinforcement learning hierarchical reinforcement learning MAXQ R-MAX model-based reinforcement learning Bench-mark problems Feature combination Hierarchical reinforcement learning Levels of abstraction Model based approach Problem characterization Robotic environments State-of-the-art algorithms Artificial Intelligence and Robotics Operations Research, Systems Engineering and Industrial Engineering Theory and Algorithms
spellingShingle	Reinforcement learning hierarchical reinforcement learning MAXQ R-MAX model-based reinforcement learning Bench-mark problems Feature combination Hierarchical reinforcement learning Levels of abstraction Model based approach Problem characterization Robotic environments State-of-the-art algorithms Artificial Intelligence and Robotics Operations Research, Systems Engineering and Industrial Engineering Theory and Algorithms LI, Zhuoru NARAYAN, Akshay LEONG, Tze-Yun An efficient approach to model-based hierarchical reinforcement learning
description	We propose a model-based approach to hierarchical reinforcement learning that exploits shared knowledge and selective execution at different levels of abstraction, to efficiently solve large, complex problems. Our framework adopts a new transition dynamics learning algorithm that identifies the common action-feature combinations of the subtasks, and evaluates the subtask execution choices through simulation. The framework is sample efficient, and tolerates uncertain and incomplete problem characterization of the subtasks. We test the framework on common benchmark problems and complex simulated robotic environments. It compares favorably against the stateof-the-art algorithms, and scales well in very large problems.
format	text
author	LI, Zhuoru NARAYAN, Akshay LEONG, Tze-Yun
author_facet	LI, Zhuoru NARAYAN, Akshay LEONG, Tze-Yun
author_sort	LI, Zhuoru
title	An efficient approach to model-based hierarchical reinforcement learning
title_short	An efficient approach to model-based hierarchical reinforcement learning
title_full	An efficient approach to model-based hierarchical reinforcement learning
title_fullStr	An efficient approach to model-based hierarchical reinforcement learning
title_full_unstemmed	An efficient approach to model-based hierarchical reinforcement learning
title_sort	efficient approach to model-based hierarchical reinforcement learning
publisher	Institutional Knowledge at Singapore Management University
publishDate	2017
url	https://ink.library.smu.edu.sg/sis_research/4398 https://ink.library.smu.edu.sg/context/sis_research/article/5401/viewcontent/14771_66644_1_PB.pdf
_version_	1770574697419767808

An efficient approach to model-based hierarchical reinforcement learning

Similar Items