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.
|Title of host publication||Advances in Neural Information Processing Systems 21 (NIPS 2008): Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 8-11, 2008|
|Editors||Daphne Koller, Dale Schuurmans, Yoshua Bengio, Léon Bottou|
|Publisher||Curran Associates, Inc.|
|Number of pages||8|
|Publication status||Published - 2009|