Interactive Task Learning

This article presents a new research area called interactive task learning (ITL), in which an agent actively tries to learn not just how to perform a task better but the actual definition of a task through natural interaction with a human instructor while attempting to perform the task. The authors provide an analysis of desiderata for ITL systems, a review of related work, and a discussion of possible application areas for ITL systems.

Authors

• John E. Laird Center for Integrated Cognition
• Kevin Gluck
• John Anderson University of Manitob
• Kenneth D. Forbus Northwestern University
• Odest Chadwicke Jenkins
• Christian Lebiere
• Dario Salvucci
• Matthias Scheutz
• Andrea Thomaz Georgia Institute of Technology
• Greg Trafton
• Robert E. Wray Center for Integrated Cognition
• Shiwali Mohan SRI
• James R. Kirk Center for Integrated Cognition

Keywords

• Games
• Cognitive systems
• Learning systems
• Intelligent systems
• Software engineering
• Natural language processing
• Software architecture
• artificial intelligence
• task learning
• natural language understanding
• learning by instruction
• learning by demonstration
• learning by observation
• cognitive architecture