AAAI Publications, Fifteenth AAAI/SIGART Doctoral Consortium

Font Size: 
Hierarchical Skill Learning for High-Level Planning
James MacGlashan

Last modified: 2010-07-05


I present skill bootstrapping, a proposed new research direction for agent learning and planning that allows an agent to start with low-level primitive actions, and develop skills that can be used for higher-level planning. Skills are developed over the course of solving many different problems in a domain, using reinforcement learning techniques to complement the benefits and disadvantages of heuristic-search planning. I describe the overall architecture of the proposed approach and discuss how it relates to other work.



Full Text: PDF