A Hierarchical Approach to POMDP Planning and Execution
Workshop Paper, ICML '01 Workshop on Hierarchy and Memory in Reinforcement Learning, June, 2001
Abstract
This paper presents a hierarchical approach to POMDPs which takes advantage of structure in the problem domain to find modular policies for complex tasks. We use a decomposition based on partitioning the action space into specialized groups of related actions.
BibTeX
@workshop{Pineau-2001-8260,author = {Joelle Pineau and Nicholas Roy and Sebastian Thrun},
title = {A Hierarchical Approach to POMDP Planning and Execution},
booktitle = {Proceedings of ICML '01 Workshop on Hierarchy and Memory in Reinforcement Learning},
year = {2001},
month = {June},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.