Surrogate model-based neuroevolution with phenotypic kernels and dynamic input sets considerably increases evaluation efficiency in reinforcement learning tasks.
Distance-based Kernels for Surrogate Model-based Neuroevolution
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The topology optimization of artificial neural networks can be particularly difficult if the fitness evaluations require expensive experiments or simulations. For that reason, the optimization methods may need to be supported by surrogate models. We propose different distances for a suitable surrogate model, and compare them in a simple numerical test scenario.
fields
cs.NE 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Surrogate Models for Enhancing the Efficiency of Neuroevolution in Reinforcement Learning
Surrogate model-based neuroevolution with phenotypic kernels and dynamic input sets considerably increases evaluation efficiency in reinforcement learning tasks.