Learning domain knowledge for teaching procedural skills

  • Authors:

  • Richard Angros, Jr.;W. Lewis Johnson;Jeff Rickel;Andrew Scholer

  • Affiliations:

  • USC Information Sciences Institute and Computer Science Department, Marina del Rey, CA;USC Information Sciences Institute and Computer Science Department, Marina del Rey, CA;USC Information Sciences Institute and Computer Science Department, Marina del Rey, CA;USC Information Sciences Institute and Computer Science Department, Marina del Rey, CA

  • Venue:
  • Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 3
  • Year:
  • 2002

Quantified Score

Hi-index 0.01

Visualization

Abstract

This paper describes a method for acquiring procedural knowledge for use by pedagogical agents in interactive simulation-based learning environments. Such agents need to be able to adapt their behavior to the changing conditions of the simulated world, and respond appropriately in mixed-initiative interactions with learners. This requires a good understanding of the goals and causal dependencies in the procedures being taught. Our method, inspired by human tutorial dialog, combines direct specification, demonstration, and experimentation. The human instructor demonstrates the skill being taught, while the agent observes the effects of the procedure on the simulated world. The agent then autonomously experiments with the procedure, making modifications to it, in order to understand the role of each step in the procedure. At various points the instructor can provide clarifications, and modify the developing procedural description as needed. This method is realized in a system called Diligent, which acquires procedural knowledge for the STEVE animated pedagogical agent.