A Connectionist Architecture for Learning to Play a Simulated Brio Labyrinth Game

  • Authors:

  • Larbi Abdenebaoui;Elsa A. Kirchner;Yohannes Kassahun;Frank Kirchner

  • Affiliations:

  • Robotics Group, University of Bremen, Robert-Hooke-Str. 5, D-28359, Bremen, Germany;Robotics Group, University of Bremen, Robert-Hooke-Str. 5, D-28359, Bremen, Germany;Robotics Group, University of Bremen, Robert-Hooke-Str. 5, D-28359, Bremen, Germany;Robotics Group, University of Bremen, Robert-Hooke-Str. 5, D-28359, Bremen, Germany and German Research Center for Artificial Intelligence (DFKI), Robert-Hooke-Str. 5, D-28359, Bremen, Germany

  • Venue:
  • KI '07 Proceedings of the 30th annual German conference on Advances in Artificial Intelligence
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

The Brio labyrinth, is a popular game consisting of a board with holes and walls. In addition, the game has knobs which are used to tip the board in two planar directions for controlling the angle of the board. The aim of the game is to maneuver a steel ball along a marked path from a starting position to a final position on the board by tipping it so that the ball moves without falling into any of the holes. The path is partially bordered by the walls. Some of the walls form corners, where the ball can be controlled easily.