Publications:Lamarckian Neuroevolution for Visual Control in the Quake II Environment
From NEBL
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 hand-coded controller that uses non-visual inputs. Results show that using backpropatation in combination with neuroevolution trains the visual neural network controller much faster and more successfully.
Matt Parker and Bobby D. Bryant (2009). Lamarckian Neuroevolution for Visual Control in the Quake II Environment. Proceedings of the 2009 IEEE Congress on Evolutionary Computation (CEC 2009), pp. 2630-2637. Piscataway, NJ: IEEE Press.
- Self-archived PDF
- Download the software.
![[Main Page]](http://nebl.cse.unr.edu/logo.png){kind=logo}