Performance Comparison of Relational Reinforcement Learning and RBF Neural Networks for Small Mobile Robots

Authors:
Roman Neruda;Stanislav Slusny;Petra Vidnerova
Affiliations:
-;-;-
Venue:
FGCNS '08 Proceedings of the 2008 Second International Conference on Future Generation Communication and Networking Symposia - Volume 04
Year:
2008

Citing 0
Cited 3

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.