Constructing Skill Trees for Reinforcement Learning Agents from Demonstration Trajectories

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

Bibtex Metadata Paper Supplemental

Authors

George Konidaris, Scott Kuindersma, Roderic Grupen, Andrew Barto

Abstract

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.