730 search results - page 1 / 146 » Learning for control from multiple demonstrations |
ICML
2008
IEEE
14 years 6 months ago
2008
IEEE
We consider the problem of learning to follow a desired trajectory when given a small number of demonstrations from a sub-optimal expert. We present an algorithm that (i) extracts...
ICRA
2009
IEEE
13 years 12 months ago
2009
IEEE
— Traditional approaches to programming robots are generally inaccessible to non-robotics-experts. A promising exception is the Learning from Demonstration paradigm. Here a polic...
ICRA
2009
IEEE
13 years 12 months ago
2009
IEEE
— We provide a general approach for learning robotic motor skills from human demonstration. To represent an observed movement, a non-linear differential equation is learned such ...
HRI
2007
ACM
13 years 9 months ago
2007
ACM
Learning by demonstration can be a powerful and natural tool for developing robot control policies. That is, instead of tedious hand-coding, a robot may learn a control policy by ...
IROS
2008
IEEE
13 years 11 months ago
2008
IEEE
Abstract— In their interactions with the world robots inevitably face equivalent action choices, situations in which multiple actions are equivalently applicable. In this paper, ...