Data-efficient Neuroevolution with Kernel-Based Surrogate Models - Archive ouverte HAL Access content directly
Conference Papers Year :

Data-efficient Neuroevolution with Kernel-Based Surrogate Models

(1, 2) , (1) , (2)


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.
Fichier principal
Vignette du fichier
1804.05364.pdf (1.86 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01768248 , version 1 (17-04-2018)



Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret. Data-efficient Neuroevolution with Kernel-Based Surrogate Models. GECCO 2018 - Genetic and Evolutionary Computation Conference, Jul 2018, Kyoto, Japan. ⟨10.1145/3205455.3205510⟩. ⟨hal-01768248⟩
199 View
244 Download



Gmail Facebook Twitter LinkedIn More