Learning Options from Demonstration using Skill Segmentation
Preprint
Abstract
We present a method for learning options from segmented demonstration trajectories. The trajectories are first segmented into skills using nonparametric Bayesian clustering and a reward function for each segment is then learned using inverse reinforcement learning. From this, a set of inferred trajectories for the demonstration are generated. Option initiation sets and termination conditions are learned from these trajectories using the one-class support vector machine clustering algorithm. We demonstrate our method in the four rooms domain, where an agent is able to autonomously discover usable options from human demonstration. Our results show that these inferred options can then be used to improve learning and planning.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Robot learning from demonstration by constructing skill treesThe International Journal of Robotics Research, 2011
- Estimating the Support of a High-Dimensional DistributionNeural Computation, 2001
- Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learningArtificial Intelligence, 1999
- Information Theory and Statistical MechanicsPhysical Review B, 1957