Title :
Visual control in quake II with a cyclic controller
Author :
Parker, Matt ; Bryant, Bobby D.
Author_Institution :
Dept. of Comput. Sci. & Eng., Univ. of Nevada, Reno, NV
Abstract :
A cyclic controller is evolved in the first person shooter computer game Quake II, to learn to attack a randomly moving enemy in a simple room by using only visual inputs. The chromosome of a genetic algorithm represents a cyclical controller that reads grayscale information from the gameplay screen to determine how far to jump forward in the program and what actions to perform. The cyclic controller learns to effectively find and shoot the enemy, and outperforms our previously published neural network solution for the same problem.
Keywords :
computer games; genetic algorithms; neural nets; spatial variables control; Quake II; computer game; cyclic controller; genetic algorithm; neural network; visual control; Backpropagation; Cameras; Computational modeling; Computer science; Gray-scale; Humans; Navigation; Neural networks; Remotely operated vehicles; Robot vision systems;
Conference_Titel :
Computational Intelligence and Games, 2008. CIG '08. IEEE Symposium On
Conference_Location :
Perth, WA
Print_ISBN :
978-1-4244-2973-8
Electronic_ISBN :
978-1-4244-2974-5
DOI :
10.1109/CIG.2008.5035634