Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Genetic Reinforcement Learning for Neurocontrol Problems
Machine Learning - Special issue on genetic algorithms
Coevolution of active vision and feature selection
Biological Cybernetics
Machine learning techniques for FPS in Q3
Proceedings of the 2004 ACM SIGCHI International Conference on Advances in computer entertainment technology
Evolving a real-world vehicle warning system
Proceedings of the 8th annual conference on Genetic and evolutionary computation
Efficient training of artificial neural networks for autonomous navigation
Neural Computation
Acquiring visibly intelligent behavior with example-guided neuroevolution
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
Lamarckian neuroevolution for visual control in the quake II environment
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
A study of the Lamarckian evolution of recurrent neural networks
IEEE Transactions on Evolutionary Computation
Evolution of an artificial neural network based autonomous landvehicle controller
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
HyperNEAT-GGP: a hyperNEAT-based atari general game player
Proceedings of the 14th annual conference on Genetic and evolutionary computation
Hi-index | 0.00 |
Backpropagation and neuroevolution are used in a Lamarckian evolution process to train a neural network visual controller for agents in the Quake II environment. In previous work, we hand-coded a non-visual controller for supervising in backpropagation, but hand-coding can only be done for problems with known solutions. In this research the problem for the agent is to attack a moving enemy in a visually complex room with a large central pillar. Because we did not know a solution to the problem, we could not hand-code a supervising controller; instead, we evolve a non-visual neural network as supervisor to the visual controller. This setup creates controllers that learn much faster and have a greater fitness than those learning by neuroevolution-only on the same problem in the same amount of time.