Sciweavers

2 search results - page 1 / 1
» Lamarckian neuroevolution for visual control in the Quake II...
Sort
View
CEC
2009
IEEE
13 years 11 months ago
Lamarckian neuroevolution for visual control in the Quake II environment
Abstract— A combination of backpropagation and neuroevolution is used to train a neural network visual controller for agents in the Quake II environment. The agents must learn to...
Matt Parker, Bobby D. Bryant
IJCNN
2008
IEEE
13 years 11 months ago
Neuro-visual control in the Quake II game engine
— The first-person-shooter Quake II is used as a platform to test neuro-visual control and retina input layouts. Agents are trained to shoot a moving enemy as quickly as possibl...
Matt Parker, Bobby D. Bryant