Genetic algorithms with sharing for multimodal function optimization
Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application
Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
Automatic definition of modular neural networks
Adaptive Behavior
Multi-Objective Optimization Using Evolutionary Algorithms
Multi-Objective Optimization Using Evolutionary Algorithms
Evolving neural networks through augmenting topologies
Evolutionary Computation
Genetic Algorithms for Multiobjective Optimization: FormulationDiscussion and Generalization
Proceedings of the 5th International Conference on Genetic Algorithms
A Survey And Analysis Of Diversity Measures In Genetic Programming
GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
Genetic diversity as an objective in multi-objective evolutionary algorithms
Evolutionary Computation
A fast technique for comparing graph representations with applications to performance evaluation
International Journal on Document Analysis and Recognition
Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Searching under multi-evolutionary pressures
EMO'03 Proceedings of the 2nd international conference on Evolutionary multi-criterion optimization
GbRPR'07 Proceedings of the 6th IAPR-TC-15 international conference on Graph-based representations in pattern recognition
On the Evolutionary Optimization of Many Conflicting Objectives
IEEE Transactions on Evolutionary Computation
Guarding against premature convergence while accelerating evolutionary search
Proceedings of the 12th annual conference on Genetic and evolutionary computation
Crossing the reality gap in evolutionary robotics by promoting transferable controllers
Proceedings of the 12th annual conference on Genetic and evolutionary computation
Evolving agent behavior in multiobjective domains using fitness-based shaping
Proceedings of the 12th annual conference on Genetic and evolutionary computation
Sustaining behavioral diversity in NEAT
Proceedings of the 12th annual conference on Genetic and evolutionary computation
Open-ended evolutionary robotics: an information theoretic approach
PPSN'10 Proceedings of the 11th international conference on Parallel problem solving from nature: Part I
How to promote generalisation in evolutionary robotics: the ProGAb approach
Proceedings of the 13th annual conference on Genetic and evolutionary computation
Why and how to measure exploration in behavioral space
Proceedings of the 13th annual conference on Genetic and evolutionary computation
On the relationships between synaptic plasticity and generative systems
Proceedings of the 13th annual conference on Genetic and evolutionary computation
Encouraging behavioral diversity in evolutionary robotics: An empirical study
Evolutionary Computation
Emergence of memory in neuroevolution: impact of selection pressures
Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
Evolving team behaviors with specialization
Genetic Programming and Evolvable Machines
Hi-index | 0.00 |
Encouraging exploration, typically by preserving the diversity within the population, is one of the most common method to improve the behavior of evolutionary algorithms with deceptive fitness functions. Most of the published approaches to stimulate exploration rely on a distance between genotypes or phenotypes; however, such distances are difficult to compute when evolving neural networks due to (1) the algorithmic complexity of graph similarity measures, (2) the competing conventions problem and (3) the complexity of most neural-network encodings. In this paper, we introduce and compare two conceptually simple, yet efficient methods to improve exploration and avoid premature convergence when evolving both the topology and the parameters of neural networks. The two proposed methods, respectively called behavioral novelty and behavioral diversity, are built on multiobjective evolutionary algorithms and on a user-defined distance between behaviors. They can be employed with any genotype. We benchmarked them on the evolution of a neural network to compute a Boolean function with a deceptive fitness. The results obtained with the two proposed methods are statistically similar to those of NEAT and substantially better than those of the control experiment and of a phenotype-based diversity mechanism.