AAAI Publications, Workshops at the Twenty-Seventh AAAI Conference on Artificial Intelligence

Font Size: 
Top-Down Abstraction Learning Using Prediction as a Supervisory Signal
Jonathan Mugan

Last modified: 2013-06-29


We present a top-down approach for learning abstractions whereby a robot begins with a coarse representation of the world and incrementally finds new distinctions as they enable the robot to better predict its environment. The approach has been implemented on a simulated robot that learns new distinctions in the form of variable discretizations through autonomous exploration. This paper discusses how to generalize this approach to learning broader abstractions.


robotics; abstraction learning; machine learning

Full Text: PDF