[ Layered Learning Peter Stonepstone@research.att.com AT&T Labs -- Research, 180 Park Ave. Room A273, Florham Park, NJ 07932 USA Manuela Velosoveloso@cs.cmu.edu Computer Science Department, Carnegie Mellon University, Pittsburgh, PA 15213 USA

In Proceedings of the IJCAI-99 Workshop on Learning About, From, and With Other Agents.

]

Abstract:

This paper presents layered learning, a hierarchical machine learning paradigm. Layered learning applies to tasks for which learning a direct mapping from inputs to outputs is intractable with existing learning algorithms. Given a hierarchical task decomposition into subtasks, layered learning seamlessly integrates separate learning at each subtask layer. The learning of each subtask directly facilitates the learning of the next higher subtask layer by determining at least one of three of its components: (i) the set of training examples; (ii) the input representation; and/or (iii) the output representation. We introduce layered learning in its domain-independent general form. We then present a full implementation in a complex domain, namely simulated robotic soccer.