688 search results - page 69 / 138 » Using reinforcement learning to adapt an imitation task |
ICONIP
2010
13 years 6 months ago
2010
Abstract. Reservoir computing approaches have been successfully applied to a variety of tasks. An inherent problem of these approaches, is, however, their variation in performance ...
AAMAS
2010
Springer
13 years 8 months ago
2010
Springer
Abstract In this paper, we present a human-robot teaching framework that uses "virtual" games as a means for adapting a robot to its user through natural interaction in a...
CVPR
2005
IEEE
14 years 9 months ago
2005
IEEE
We develop an object classification method that can learn a novel class from a single training example. In this method, experience with already learned classes is used to facilita...
IROS
2009
IEEE
14 years 2 months ago
2009
IEEE
Abstract— We present an adaptive control approach combining forward kinematics model learning methods with the operational space control approach. This combination endows the rob...
DSP
2006
13 years 7 months ago
2006
This paper considers the problem of sensor scheduling for the purposes of detection and tracking of "smart" targets. Smart targets are targets that can detect when they ...