Genetic Algorithms in Noisy Environments
Machine Learning
Finding Multimodal Solutions Using Restricted Tournament Selection
Proceedings of the 6th International Conference on Genetic Algorithms
Scheduling of genetic algorithms in a noisy environment
Evolutionary Computation
Accumulative sampling for noisy evolutionary multi-objective optimization
Proceedings of the 13th annual conference on Genetic and evolutionary computation
Multiobjective evolutionary algorithm for the optimization of noisy combustion processes
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
A fast and elitist multiobjective genetic algorithm: NSGA-II
IEEE Transactions on Evolutionary Computation
| Hi-index | 0.00 |
We propose a noise-tolerant genetic algorithm (NTGA) to be used for deriving a policy for container stacking at an automated container terminal. The evaluation of a candidate stacking policy is inevitably noisy because an accurate evaluation requires too expensive simulations of crane operations at the stacking yard under various scenarios. Although the effect of noise can be alleviated by taking multiple samples of fitness by running multiple simulations with different scenarios, the problem is that this intuitive approach is computationally expensive. The idea of NTGA is to give more samples of fitness to some important candidate policies than the others to save the computational cost. We show in this paper that this discriminative sampling can be nicely implemented within the framework of the restricted tournament selection scheme that is usually adopted for maintaining the population diversity. The experimental results with various scenarios reveal that NTGA can derive a robust policy which outperforms those derived by other methods.