Abstract | ||
---|---|---|
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 possible in a visually simple environment, using a neural network controller with evolved weights. Two retina layouts are tested, each with the same number of inputs: first, a graduated density retina which focuses near the center of the screen and blurs outward; second, a uniform retina which focuses evenly across the screen. Results show that the graduated density retina learns more successfully than the uniform retina. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/IJCNN.2008.4634348 | 2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8 |
Keywords | Field | DocType |
computational modeling,neural network,visualization,engines,artificial intelligence,layout,games,pixel,artificial neural networks,artificial intelligent,remote control,testing,neural networks,real time | Computer graphics (images),Computer science,Visualization,Quake (series),Artificial intelligence,Pixel,Neural network controller,Artificial neural network,Game engine,Visual control,Machine learning | Conference |
ISSN | Citations | PageRank |
2161-4393 | 7 | 0.55 |
References | Authors | |
9 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Matt Parker | 1 | 56 | 7.28 |
Bobby D. Bryant | 2 | 58 | 6.70 |