1 Downloads (Pure)

Abstract

We show that betweenness centrality, a graph-theoretic measure widely used in social network analysis, provides a sound basis for autonomously forming useful high-level behaviors, or skills, from available primitives— the smallest behavioral units available to an autonomous agent.
Original languageEnglish
PublisherUniversity of Massachusetts Amherst
Publication statusPublished - 12 Apr 2007

Keywords

  • reinforcement learning
  • skill discovery
  • Hierarchical reinforcement learning
  • action hierachy

Fingerprint

Dive into the research topics of 'Betweenness Centrality as a Basis for Forming Skills'. Together they form a unique fingerprint.

Cite this