The evolution of memory and mental models using genetic programming
Scott Brave · 1996
This paper applies genetic programming to the evolution of intelligent agents that gradually build internal representations of their surroundings for later use in planning. The method used allows for the creation of dynamically determined representations that are not pre-designed by the human creator of the system. In an illustrative path-planning problem, evolved programs learn a model of their world and use this internal representation to plan their successive actions. The results show that the proposed method is successful in evolving programs that solve the planning problem and is thus a worthy basis for further investigation. 1. Introduction Intelligent behavior depends on the ability to learn and retain information about the world for later use. Though many tasks are solvable by purely reactive systems, more complex tasks require the creation and utilization of mental models. If genetic programming is to be applied to produce agents capable of building and using stored represent...