To access the full text documents, please follow this link: http://hdl.handle.net/2117/25142
Title: | Handling high parameter dimensionality in reinforcement learning with dynamic motor primitives |
---|---|
Author: | Colomé Figueras, Adrià; Alenyà Ribas, Guillem; Torras, Carme |
Other authors: | Institut de Robòtica i Informàtica Industrial; Universitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI |
Abstract: | Dynamic Motor Primitives (DMP) are nowadays widely used as movement parametrization for learning trajectories, because of their linearity in the parameters, rescalation robustness and continuity. However, when learning a movement with DMP, where a set of gaussians distributed along the trajectory is used to approximate an acceleration excitation function, a very large number of gaussian approximations need to be performed. Adding them up for all joints yields too many parameters to be explored, thus requiring a prohibitive number of experiments/simulations to converge to a solution with an optimal (locally or globally) reward. We propose here two strategies to reduce this dimensionality: the first is to explore only the most significant directions in the parameter space, and the second is to add a reduced second set of gaussians that should only optimize the trajectory after fixing the gaussians that approximate the demonstrated movement. |
Abstract: | Peer Reviewed |
Subject(s): | -Àrees temàtiques de la UPC::Informàtica::Robòtica -Intelligent Robots and Computer Vision -intelligent robots -manipulators -robot kinematics -robot programming Author keywords: dynamic motor primitives -learning by demonstration -Robòtica -Classificació INSPEC::Automation::Robots::Intelligent robots |
Rights: | Attribution-NonCommercial-NoDerivs 3.0 Spain
http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
Document type: | Article - Submitted version Conference Object |
Share: |