Sciweavers

69 search results - page 3 / 14
» Policy Learning for Motor Skills
Sort
View
ICAD
2004
13 years 8 months ago
Interaction Sound Feedback in a Haptic Virtual Environment to Improve Motor Skill Acquisition
This paper describes the concept and the realisation of a research prototype of a haptic environment that is enhanced with sound feedback to impart implicit knowledge and to teach...
Christian Müller-Tomfelde
IROS
2006
IEEE
113views Robotics» more  IROS 2006»
14 years 1 months ago
Policy Gradient Methods for Robotics
— The aquisition and improvement of motor skills and control policies for robotics from trial and error is of essential importance if robots should ever leave precisely pre-struc...
Jan Peters, Stefan Schaal
ICRA
2009
IEEE
125views Robotics» more  ICRA 2009»
14 years 1 months ago
Learning motor primitives for robotics
— The acquisition and self-improvement of novel motor skills is among the most important problems in robotics. Motor primitives offer one of the most promising frameworks for the...
Jens Kober, Jan Peters
IROS
2008
IEEE
111views Robotics» more  IROS 2008»
14 years 1 months ago
Learning perceptual coupling for motor primitives
—Dynamic system-based motor primitives [1] have enabled robots to learn complex tasks ranging from Tennisswings to locomotion. However, to date there have been only few extension...
Jens Kober, Betty J. Mohler, Jan Peters
IJCNN
2006
IEEE
14 years 1 months ago
Reinforcement Learning for Parameterized Motor Primitives
Abstract— One of the major challenges in both action generation for robotics and in the understanding of human motor control is to learn the “building blocks of movement genera...
Jan Peters, Stefan Schaal