Projective Visualization: Acting from Experience

Marc Goodman

This paper describes Projective Visualization, which uses previous observation of a process or activity to project the results of an agent’s actions into the future. Actions which seem likely to succeed are selected and applied. Actions which seem likely to fail are rejected, and other actions can be generated and evaluated. This paper presents a description of the architecture for Projective Visualization, preliminary results on learning to act from observations of a reactive system, and a comparison of two types of Case Projection (how situations are projected into the future).

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.