Skill Characterization Based on Betweenness
Abstract
We present a characterization of a useful class of skills based on a graphical representation of an agent's interaction with its environment. Our characterization uses betweenness, a measure of centrality on graphs. It may be used directly to form a set of skills suitable for a given environment. More importantly, it serves as a useful guide for developing online, incremental skill discovery algorithms that do not rely on knowing or representing the environment graph in its entirety.
Cite
Text
Simsek and Barto. "Skill Characterization Based on Betweenness." Neural Information Processing Systems, 2008.Markdown
[Simsek and Barto. "Skill Characterization Based on Betweenness." Neural Information Processing Systems, 2008.](https://mlanthology.org/neurips/2008/simsek2008neurips-skill/)BibTeX
@inproceedings{simsek2008neurips-skill,
title = {{Skill Characterization Based on Betweenness}},
author = {Simsek, Ozgur and Barto, Andrew G.},
booktitle = {Neural Information Processing Systems},
year = {2008},
pages = {1497-1504},
url = {https://mlanthology.org/neurips/2008/simsek2008neurips-skill/}
}