Genetic neural networks on MIMD computers
Genetic neural networks on MIMD computers
Automatic definition of modular neural networks
Adaptive Behavior
Efficient Reinforcement Learning Through Evolving Neural Network Topologies
GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
Forming neural networks through efficient and adaptive coevolution
Evolutionary Computation
Entropy and mutual information can improve fitness evaluation in coevolution of neural networks
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
| Hi-index | 0.00 |
This paper revisits the evolution of a neural controller for asimulated Personal Satellite Assistant (PSA) using the En-forced Sub-Populations (ESP) neuroevolutionary algorithm, as described by Sit et al. in 2005 [8].ESP has previously been shown to be a very efficient algo-rithm for neuroevolution. As opposed to the original paper,we are not primarily concerned with the solutions discov-ered by the system, but rather with how ESP performs itsevolutionary search; using the unstable PSA control task asa vehicle for fitness evaluation. We propose several changes to the original ESP algorithm. Our experiments suggest that these improve both the inter-nal consistency, and the success rate of the algorithm.We further analyze the ability of ESP to go beyond classicweight evolution. We compare our evolutionary results with those of a simple hill-climb algorithm, and propose that im-proved heuristics for the modifications of network topologyin ESP may be necessary to evolve increasingly complex androbust controllers.