Learning problem solving skills from demonstration: an architectural approach

  • Authors:

  • Haris Dindo;Antonio Chella;Giuseppe La Tona;Monica Vitali;Eric Nivel;Kristinn R. Thórisson

  • Affiliations:

  • Computer Science Engineering, University of Palermo, Palermo, Italy;Computer Science Engineering, University of Palermo, Palermo, Italy;Computer Science Engineering, University of Palermo, Palermo, Italy;Computer Science Engineering, University of Palermo, Palermo, Italy;School of Computer Science, Reykjavik University, Reykjavik, Iceland;School of Computer Science, Reykjavik University, Reykjavik and Icelandic Institute for Intelligent Machines, Reykjavik, Iceland

  • Venue:
  • AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present an architectural approach to learning problem solving skills from demonstration, using internal models to represent problem-solving operational knowledge. Internal forward and inverse models are initially learned through active interaction with the environment, and then enhanced and finessed by observing expert teachers. While a single internal model is capable of solving a single goal-oriented task, it is their sequence that enables the system to hierarchically solve more complex task. Activation of models is goal-driven, and internal "mental" simulations are used to predict and anticipate future rewards and perils and to make decisions accordingly. In this approach intelligent system behavior emerges as a coordinated activity of internal models over time governed by sound architectural principles. In this paper we report preliminary results using the game of Sokoban, where the aim is to learn goal-oriented patterns of model activations capable of solving the problem in various contexts.