We present context-sensitive Multiple Task Learning, or csMTL as a method of inductive transfer. It uses additional contextual inputs along with other input features when learning ...
The central problem of designing intelligent robot systems which learn by demonstrations of desired behaviour has been largely studied within the field of robotics. Numerous archi...
This paper describes a new approach on how to teach a robot everyday manipulation tasks under the “Learning from Observation” framework. Most of the approaches so far assume t...
Koichi Ogawara, Jun Takamatsu, Hiroshi Kimura, Kat...
For robots to become prevalent in human environments, the robots need to be able to perform complex tasks often involving sequential repetition of actions. In this work, we presen...
We contribute an approach for interactive policy learning through expert demonstration that allows an agent to actively request and effectively represent demonstration examples. I...