Development requires learning skills using previously learned skills as building blocks. For maximum flexibility, the developing agent should be able to learn these skills without being provided an explicit task or subtasks. We have developed a method that allows an agent to simultaneously learn hierarchical actions and important distinctions autonomously without being specified a task. This ability to learn new distinctions allows it to work in continuous environments, and allows an agent to learn its first actions from motor primitives. In this paper we demonstrate that our method can use experience from one set of variables to more quickly learn a task that requires additional new variables. It does this by learning actions in a developmental progression. In addition, we demonstrate this developmental progression by showing that actions that are mainly used for exploration when first learned are later used as subactions for other actions.

PDF

In IROS 2009 Workshop: Autonomous Mental Development for Intelligent Robots and Systems, pp. 2009.

@inproceedings{Mugan-irosws-09, title={Skill Reuse in Lifelong Developmental Learning}, author={Jonathan Mugan and Benjamin Kuipers}, booktitle={IROS 2009 Workshop: Autonomous Mental Development for Intelligent Robots and Systems}, pages={ }, url="http://www.cs.utexas.edu/users/ai-lab?Mugan-irosws-09", year={2009} }