Learning parameterized skills

Journal Article

We introduce a method for constructing skills capable of solving tasks drawn from a distribution of parameterized reinforcement learning problems. The method draws example tasks from a distribution of interest and uses the corresponding learned policies to estimate the topology of the lower-dimensional piecewise-smooth manifold on which the skill policies lie. This manifold models how policy parameters change as task parameters vary. The method identifies the number of charts that compose the manifold and then applies non-linear regression in each chart to construct a parameterized skill by predicting policy parameters from task parameters. We evaluate our method on an underactuated simulated robotic arm tasked with learning to accurately throw darts at a parameterized target location. Copyright 2012 by the author(s)/owner(s).

Duke Authors

Cited Authors

  • Da Silva, BC; Konidaris, G; Barto, AG

Published Date

  • October 10, 2012

Published In

  • Proceedings of the 29th International Conference on Machine Learning, ICML 2012

Volume / Issue

  • 2 /

Start / End Page

  • 1679 - 1686

Citation Source

  • Scopus