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...
Saved in:
Published in | 2006 IEEE International Conference on Evolutionary Computation pp. 969 - 975 |
---|---|
Main Authors | , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
2006
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
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 |