Timezone: »

Skill Characterization Based on Betweenness
Özgür Şimşek · Andrew G Barto

Mon Dec 08 08:45 PM -- 12:00 AM (PST) @ None #None

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.

Author Information

Özgür Şimşek (Max Planck Institute for Human Development)
Andrew G Barto (University of Massachusetts)

More from the Same Authors