AAAI Publications, Twenty-First International Joint Conference on Artificial Intelligence

Font Size: 
Efficient Skill Learning Using Abstraction Selection
George Konidaris, Andrew Barto

Last modified: 2009-06-26


We present an algorithm for selecting an appropriate abstraction when learning a new skill. We show empirically that it can consistently select an appropriate abstraction using very little sample data, and that it significantly improves skill learning performance in a reasonably large real-valued reinforcement learning domain.


Reinforcement Learning; Options; Skills; Hierarchical Reinforcement Learning

Full Text: PDF