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 shoot an enemy opponent in a semi-visually complex environment using only raw visual inputs. A comparison is made between using normal neuroevolution and using neuroevolution combined with backpropagation for Lamarckian adaptation. The supervised backpropagation imitates a handcoded controller that uses non-visual inputs. Results show that using backpropagation in combination with neuroevolution trains the visual neural network controller much faster and more successfully. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/CEC.2009.4983272 | IEEE Congress on Evolutionary Computation |
Keywords | Field | DocType |
quake ii environment,lamarckian neuroevolution,raw visual input,handcoded controller,semi-visually complex environment,neural network,visual controller,neuroevolution train,supervised backpropagation,normal neuroevolution,visual neural network controller,gray scale,backpropagation,computational modeling,neural networks,visualization,computer science,robots,artificial neural networks,games | Control theory,Visualization,Computer science,Quake (series),Artificial intelligence,Neural network controller,Backpropagation,Artificial neural network,Neuroevolution,Machine learning,Visual control | Conference |
Citations | PageRank | References |
3 | 0.40 | 14 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Matt Parker | 1 | 56 | 7.28 |
Bobby D. Bryant | 2 | 58 | 6.70 |