Constructing Skill Trees for Reinforcement Learning Agents from Demonstration Trajectories

Citation:

G. Konidaris, S. Kuindersma, A. Barto, and R. Grupen, “Constructing Skill Trees for Reinforcement Learning Agents from Demonstration Trajectories,” in Advances in Neural Information Processing Systems 23, 2010, pp. 1162–1170.
cst-nips.pdf842 KB

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.

Last updated on 05/27/2016