Evaluation of techniques for a learning-driven modeling methodology in multiagent simulation
MATES'10 Proceedings of the 8th German conference on Multiagent system technologies
Evolution for modeling: a genetic programming framework for sesam
Proceedings of the 13th annual conference companion on Genetic and evolutionary computation
Generating inspiration for agent design by reinforcement learning
Information and Software Technology
Hi-index | 0.00 |
A performance of two learning mechanisms for small mobile robots is performed in this paper.Relational reinforcement learning, and radial basis function neural network learned by evolutionary algorithm are trained to perform the same maze explorationtask and the results were compared in terms learning speed, accuracy and compactness of the resulting control mechanisms. Advantages of the chosen methods are discussed.