Constructing Skill Trees for Reinforcement Learning Agents from Demonstration Trajectories

  • Konidaris G
  • Kuindersma S
  • Barto A
  • et al.
37Citations
Citations of this article
140Readers
Mendeley users who have this article in their library.
Get full text

Abstract

We introduce CST, an algorithm for constructing skill trees from demonstration trajectories in continuous reinforcement learning domains. CST uses a change- point 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.

Cite

CITATION STYLE

APA

Konidaris, G., Kuindersma, S., Barto, A., & Grupen, R. (2010). Constructing Skill Trees for Reinforcement Learning Agents from Demonstration Trajectories. In Advances in Neural Information Processing Systems 23 (pp. 1162–1170). https://doi.org/10.1002/mds.25567

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free