Latent Learning and Action Planning in Robots with Anticipatory Classifier Systems

  • Authors:
  • Wolfgang Stolzmann;Martin Butz

  • Affiliations:
  • -;-

  • Venue:
  • Learning Classifier Systems, From Foundations to Applications
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

Two applications of Anticipatory Classifier Systems (ACS) in robotics are discussed. The first one is a simulation of an experiment about latent learning in rats with a mobile robot. It shows that an ACS is able to learn latently, i.e. in the absence of environmental reward and that ACS can do action planning. The second one is about learning of the hand-eye coordination of a robot arm in conjunction with a camera. Goal-directed learning will be introduced. This combination of action planning and latent learning leads to a substantial reduction of the number of trials which are required to learn a complete model of a prototypical environment.