A quantitative approach to the analysis of memory requirements for autonomous agent behaviours using evolutionary computation
When building controllers for autonomous agents, such as real or simulated robots, there is very little theoretical guidance on how complex the controller must be in terms of internal state to be able to achieve good performance in a particular task. The underlying problem is that it is hard to quan...
Main Author: | |
---|---|
Published: |
University of Edinburgh
2002
|
Subjects: | |
Online Access: | http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.649067 |