NIPS Proceedingsβ

Constructing Skill Trees for Reinforcement Learning Agents from Demonstration Trajectories

Part of: Advances in Neural Information Processing Systems 23 (NIPS 2010)

[PDF] [BibTeX] [Supplemental]



We introduce CST, an algorithm for constructing skill trees from demonstration trajectories in continuous reinforcement learning domains. CST uses a changepoint detection method to segment each trajectory into a skill chain by detecting a change of appropriate abstraction, or that a segment is too complex to model as a single skill. The skill chains from each trajectory are then merged to form a skill tree. We demonstrate that CST constructs an appropriate skill tree that can be further refined through learning in a challenging continuous domain, and that it can be used to segment demonstration trajectories on a mobile manipulator into chains of skills where each skill is assigned an appropriate abstraction.