Uploaded May 2018 | Updated November 2026, 2 days ago
ICRA 2018 Spotlight Video
Interactive Session Wed PM Pod T.3
Authors: Barbaros, Victor; van Hoof, Herke; Abdolmaleki, Abbas; Meger, David Paul
Title: Eager and Memory-Based Non-Parametric Stochastic Search Methods for Learning Control
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 non- parametric 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.
ICRA 2018 Spotlight Video
Interactive Session Wed PM Pod T.3
Authors: Barbaros, Victor; van Hoof, Herke; Abdolmaleki, Abbas; Meger, David Paul
Title: Eager and Memory-Based Non-Parametric Stochastic Search Methods for Learning Control
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 non- parametric 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.










