DeepAI AI Chat
Log In Sign Up

Data-efficient Neuroevolution with Kernel-Based Surrogate Models

by   Adam Gaier, et al.
Hochschule Bonn-Rhein-Sieg

Surrogate-assistance approaches have long been used in computationally expensive domains to improve the data-efficiency of optimization algorithms. Neuroevolution, however, has so far resisted the application of these techniques because it requires the surrogate model to make fitness predictions based on variable topologies, instead of a vector of parameters. Our main insight is that we can sidestep this problem by using kernel-based surrogate models, which require only the definition of a distance measure between individuals. Our second insight is that the well-established Neuroevolution of Augmenting Topologies (NEAT) algorithm provides a computationally efficient distance measure between dissimilar networks in the form of "compatibility distance", initially designed to maintain topological diversity. Combining these two ideas, we introduce a surrogate-assisted neuroevolution algorithm that combines NEAT and a surrogate model built using a compatibility distance kernel. We demonstrate the data-efficiency of this new algorithm on the low dimensional cart-pole swing-up problem, as well as the higher dimensional half-cheetah running task. In both tasks the surrogate-assisted variant achieves the same or better results with several times fewer function evaluations as the original NEAT.


page 1

page 3

page 4

page 5

page 7


Improving NeuroEvolution Efficiency by Surrogate Model-based Optimization with Phenotypic Distance Kernels

In NeuroEvolution, the topologies of artificial neural networks are opti...

Distance-based Kernels for Surrogate Model-based Neuroevolution

The topology optimization of artificial neural networks can be particula...

Surrogate Models for Enhancing the Efficiency of Neuroevolution in Reinforcement Learning

In the last years, reinforcement learning received a lot of attention. O...

Data-Efficient Design Exploration through Surrogate-Assisted Illumination

Design optimization techniques are often used at the beginning of the de...

Shapley Computations Using Surrogate Model-Based Trees

Shapley-related techniques have gained attention as both global and loca...