Loading...
Loading...

Go to the content (press return)

Handling high parameter dimensionality in reinforcement learning with dynamic motor primitives

Author
Colomé, A.; Alenyà, G.; Torras, C.
Type of activity
Presentation of work at congresses
Name of edition
2013 ICRA Workshop on Novel Methods for Learning and Optimization of Control Policies and Trajectories for Robotics
Date of publication
2013
Presentation's date
2013
Book of congress proceedings
Proceedings orf the 2013 ICRA Workshop on Novel Methods for Learning and Optimization of Control Policies and Trajectories for Robotics
Project funding
IntellAct: Intelligent observation and execution of Actions and manipulations
Repository
http://hdl.handle.net/2117/25142 Open in new window
URL
http://www.robot-learning.de/Research/ICRA2013 Open in new window
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, ...
Citation
Colomé, A.; Alenyà, G.; Torras, C. Handling high parameter dimensionality in reinforcement learning with dynamic motor primitives. A: ICRA Workshop on Novel Methods for Learning and Optimization of Control Policies and Trajectories for Robotics. "Proceedings orf the 2013 ICRA Workshop on Novel Methods for Learning and Optimization of Control Policies and Trajectories for Robotics". Karlsruhe: 2013.
Keywords
intelligent robots, learning by demonstration, manipulators, robot kinematics, robot programming Author keywords: dynamic motor primitives
Group of research
ROBiri - IRI Robotics Group

Participants

Attachments