Access the full text.
Sign up today, get DeepDyve free for 14 days.
Trey Smith, R. Simmons (2004)
Heuristic Search Value Iteration for POMDPsArXiv, abs/1207.4166
Thomas Dietterich (1999)
Hierarchical Reinforcement Learning with the MAXQ Value Function DecompositionArXiv, cs.LG/9905014
Anders Jonsson, A. Barto (2005)
A causal approach to hierarchical decomposition of factored MDPsProceedings of the 22nd international conference on Machine learning
Craig Boutilier, R. Dearden, M. Goldszmidt (1995)
Exploiting Structure in Policy Construction
B. Hengst (2002)
Discovering Hierarchy in Reinforcement Learning with HEXQ
E. Hansen, R. Zhou (2003)
Synthesis of Hierarchical Finite-State Controllers for POMDPs
D. Potts, B. Hengst (2004)
Discovering multiple levels of a task hierarchy concurrentlyRobotics Auton. Syst., 49
Joelle Pineau, N. Roy, S. Thrun (2004)
A Hierarchical Approach to POMDP Planning and Execution
Thomas Dietterich (1998)
The MAXQ Method for Hierarchical Reinforcement Learning
F. Deák, A. Kovács, J. Váncza, T. Dobrowiecki (2001)
Hierarchical Knowledge-Based Process Planning in Manufacturing
R. Sutton, Doina Precup, Satinder Singh (1999)
Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement LearningArtif. Intell., 112
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.
Artificial Intelligence Review – Springer Journals
Published: Feb 17, 2011
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.