Episodic task learning in Markov decision processes |
| |
Authors: | Yong Lin Fillia Makedon Yurong Xu |
| |
Affiliation: | (1) University of New South Wales, Sydney, Australia; |
| |
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. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|