Cogprints

Evolving robust and specialized car racing skills

Togelius, Julian and Lucas, Simon M. (2006) Evolving robust and specialized car racing skills. [Conference Paper]

Full text available as:

[img]
Preview
PDF
273Kb

Abstract

Neural network-based controllers are evolved for racing simulated R/C cars around several tracks of varying difficulty. The transferability of driving skills acquired when evolving for a single track is evaluated, and different ways of evolving controllers able to perform well on many different tracks are investigated. It is further shown that such generally proficient controllers can reliably be developed into specialized controllers for individual tracks. Evolution of sensor parameters together with network weights is shown to lead to higher final fitness, but only if turned on after a general controller is developed, otherwise it hinders evolution. It is argued that simulated car racing is a scalable and relevant testbed for evolutionary robotics research, and that the results of this research can be useful for commercial computer games.

Item Type:Conference Paper
Subjects:Computer Science > Machine Learning
Computer Science > Neural Nets
Computer Science > Artificial Intelligence
ID Code:5219
Deposited By:Togelius, Julian
Deposited On:15 Oct 2006
Last Modified:11 Mar 2011 08:56

Metadata

Repository Staff Only: item control page