Genetic algorithms with sharing for multimodal function optimization
Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application
SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
Efficient Reinforcement Learning Through Evolving Neural Network Topologies
GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
| Hi-index | 0.00 |
Recent works explored the possibility of designing physical robots using evolutionary algorithms. We propose a novel algorithm for the evolution of morphology and control of autonomous robots controlled by artificial neural networks. The proposed algorithm is inspired by NeuroEvolution of Augmenting Topologies (NEAT) which efficiently evolves artificial neural networks. All three main components of NEAT algorithm (protecting evolutionary innovation through speciation, effective crossover of neural networks with different topologies and incremental growth from minimal structure) are applied to the evolution of both morphology and control system of a robot. Large-scale experiments with simulated robots have shown that the proposed algorithm uses significantly less fitness evaluations than a standard genetic algorithm on all four tested fitness functions. Positive contribution of each component of the proposed algorithm has been confirmed with a series of supplementary ablation experiments.