DMCA
Discovering hierarchy in reinforcement learning with hexq (2002)
Cached
Download Links
- [jmvidal.cse.sc.edu]
- [www.eecs.berkeley.edu]
- [www.cs.berkeley.edu]
- [www.cs.berkeley.edu]
- [www.demo.cs.brandeis.edu]
- DBLP
Other Repositories/Bibliography
by
Bernhard Hengst
| Venue: | In Nineteenth International Conference on Machine Learning |
| Citations: | 94 - 5 self |
BibTeX
@INPROCEEDINGS{Hengst02discoveringhierarchy,
author = {Bernhard Hengst},
title = {Discovering hierarchy in reinforcement learning with hexq},
booktitle = {In Nineteenth International Conference on Machine Learning},
year = {2002}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
An open problem in reinforcement learning is discovering hierarchical structure. HEXQ, an algorithm which automatically attempts to decompose and solve a model-free factored MDP hierarchically is described. By searching for aliased Markov sub-space regions based on the state variables the algorithm uses temporal and state abstraction to construct a hierarchy of interlinked smaller MDPs. 1.
