Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Episodic task learning in Markov decision processes

Episodic task learning in Markov decision processes Hierarchical algorithms for Markov decision processes have been proved to be useful for the problem domains with multiple subtasks. Although the existing hierarchical approaches are strong in task decomposition, they are weak in task abstraction, which is more important for task analysis and modeling. In this paper, we propose a task-oriented design to strengthen the task abstraction. Our approach learns an episodic task model from the problem domain, with which the planner obtains the same control effect, with concise structure and much improved performance than the original model. According to our analysis and experimental evaluation, our approach has better performance than the existing hierarchical algorithms, such as MAXQ and HEXQ. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Artificial Intelligence Review Springer Journals

Episodic task learning in Markov decision processes

Download PDF
12 pages

Loading next page...
 
/lp/springer-journals/episodic-task-learning-in-markov-decision-processes-yQiUckb3Q2

References (11)

Publisher
Springer Journals
Copyright
Copyright © 2011 by Springer Science+Business Media B.V.
Subject
Computer Science; Computer Science, general; Artificial Intelligence (incl. Robotics)
ISSN
0269-2821
eISSN
1573-7462
DOI
10.1007/s10462-011-9204-3
Publisher site
See Article on Publisher Site

Abstract

Hierarchical algorithms for Markov decision processes have been proved to be useful for the problem domains with multiple subtasks. Although the existing hierarchical approaches are strong in task decomposition, they are weak in task abstraction, which is more important for task analysis and modeling. In this paper, we propose a task-oriented design to strengthen the task abstraction. Our approach learns an episodic task model from the problem domain, with which the planner obtains the same control effect, with concise structure and much improved performance than the original model. According to our analysis and experimental evaluation, our approach has better performance than the existing hierarchical algorithms, such as MAXQ and HEXQ.

Journal

Artificial Intelligence Review – Springer Journals

Published: Feb 17, 2011

There are no references for this article.