Evolving neural network ensembles for control problems

Authors:
David Pardoe;Michael Ryoo;Risto Miikkulainen
Affiliations:
University of Texas at Austin, Austin, TX;University of Texas at Austin, Austin, TX;University of Texas at Austin, Austin, TX
Venue:
GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Year:
2005

Citing 6
Cited 7

Bagging predictors

Machine Learning
Evolving neural networks through augmenting topologies

Evolutionary Computation
Towards Designing Neural Network Ensembles by Evolution

PPSN V Proceedings of the 5th International Conference on Parallel Problem Solving from Nature
Recent Advances in Hierarchical Reinforcement Learning

Discrete Event Dynamic Systems
Cooperative coevolution of artificial neural network ensembles for pattern classification

IEEE Transactions on Evolutionary Computation
Making use of population information in evolutionary artificialneural networks

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Evolving neural networks

Proceedings of the 9th annual conference companion on Genetic and evolutionary computation
Evolving neural networks

Proceedings of the 10th annual conference companion on Genetic and evolutionary computation
Evolving neural networks

Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers
Evolving multi-modal behavior in NPCs

CIG'09 Proceedings of the 5th international conference on Computational Intelligence and Games
Evolving neural networks

Proceedings of the 12th annual conference companion on Genetic and evolutionary computation
Evolving neural networks

Proceedings of the 13th annual conference companion on Genetic and evolutionary computation
Evolving neural networks

Proceedings of the 15th annual conference companion on Genetic and evolutionary computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In neuroevolution, a genetic algorithm is used to evolve a neural network to perform a particular task. The standard approach is to evolve a population over a number of generations, and then select the final generation's champion as the end result. However, it is possible that there is valuable information present in the population that is not captured by the champion. The standard approach ignores all such information. One possible solution to this problem is to combine multiple individuals from the final population into an ensemble. This approach has been successful in supervised classification tasks, and in this paper, it is extended to evolutionary reinforcement learning in control problems. The method is evaluated on a challenging extension of the classic pole balancing task, demonstrating that an ensemble can achieve significantly better performance than the champion alone.