The Incremental Evolution of Attack Agents in Xpilot

In the research presented in this paper, we use incremental evolution to learn multifaceted neural network (NN) controllers for agents operating in the space game Xpilot. Behavioral components specific to the accomplishment of specific tasks, such as bullet-dodging, shooting, and closing on an enemy...

Full description

Saved in:
Bibliographic Details
Published in2006 IEEE International Conference on Evolutionary Computation pp. 969 - 975
Main Authors Parker, G.B., Parker, M.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2006
Subjects
Artificial intelligence
Artificial neural networks
Autonomous agents
Control systems
Genetic algorithms
Humans
Intelligent networks
Neural networks
Open source software
System testing
Online AccessGet full text

Cover

More Information
Summary:In the research presented in this paper, we use incremental evolution to learn multifaceted neural network (NN) controllers for agents operating in the space game Xpilot. Behavioral components specific to the accomplishment of specific tasks, such as bullet-dodging, shooting, and closing on an enemy, are learned in the first increment. These behavioral components are used in the second increment to evolve a NN that prioritizes the output of a two-layer NN depending on that agent's current situation.
ISBN:9780780394872
0780394879
ISSN:1089-778X
1941-0026
DOI:10.1109/CEC.2006.1688415