Eager and Memory-Based Non-Parametric Stochastic Search Methods for Learning Control

Victor Barbaros; Herke van Hoof; Abbas Abdolmaleki; David Megerl

ICRA 2018poster3 citations

Eager and Memory-Based Non-Parametric Stochastic Search Methods for Learning Control

Victor Barbaros, Herke van Hoof, Abbas Abdolmaleki, David Megerl

Abstract

Direct policy search has shown to be a successful method to optimize robot controller parameters. However, defining a good parametric form for the controller can be challenging for complex problems. Non-parametric methods provide a flexible alternative and are thus a promising tool in robot skill learning. In this paper, we investigate two nonparametric methods based on similar principles but utilizing differing computing schedules: an eager learner and a memory-based learner. We compare the methods experimentally on two different control problems. Furthermore, we define and evaluate a new `hybrid' controller that combines the strong points of both of these methods.

BibTeX

@inproceedings{icra2018_eagerandmemoryba,
  title = {Eager and Memory-Based Non-Parametric Stochastic Search Methods for Learning Control},
  author = {Victor Barbaros and Herke van Hoof and Abbas Abdolmaleki and David Megerl},
  booktitle = {ICRA 2018},
  year = {2018}
}