Evolving Neural Networks to Play Go
Applied Intelligence
Evolving neural networks through augmenting topologies
Evolutionary Computation
Methods for Competitive Co-Evolution: Finding Opponents Worth Beating
Proceedings of the 6th International Conference on Genetic Algorithms
Applying ESP and Region Specialists to Neuro-Evolution for Go
Applying ESP and Region Specialists to Neuro-Evolution for Go
Forming neural networks through efficient and adaptive coevolution
Evolutionary Computation
Competitive coevolution through evolutionary complexification
Journal of Artificial Intelligence Research
PEEC: evolving efficient connections using Pareto optimality
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Noise and the evolution of neural network modularity
Artificial Life
| Hi-index | 0.00 |
In this paper, we compare two neuroevolutionary algorithms, namely standard NeuroEvolution (NE) and NeuroEvolution of Augmenting Topologies (NEAT), with three neurocoevolutionary algorithms, namely Symbiotic Adaptive Neuro-Evolution (SANE), Enforced Sub-Populations (ESP) and Evolving Efficient Connections (EEC). EEC is a novel neurocoevolutionary algorithm that we propose in this work, where the connection weights and the connection paths of networks are evolved separately. All these methods are applied to evolve players of two different board games. The results of this study indicate that neurocoevolutionary algorithms outperform neuroevolutionary algorithms for both domains. Our new method, especially, demonstrates that fully connected networks could generate noise which results in inefficient learning. The performance of standard NE model has been improved significantly through evolving connection weights and efficient connection paths in parallel in our method.