Search Results for author: Martin Zaefferer

Found 17 papers, 6 papers with code

Behavior-based Neuroevolutionary Training in Reinforcement Learning

1 code implementation17 May 2021 Jörg Stork, Martin Zaefferer, Nils Eisler, Patrick Tichelmann, Thomas Bartz-Beielstein, A. E. Eiben

In addition to their undisputed success in solving classical optimization problems, neuroevolutionary and population-based algorithms have become an alternative to standard reinforcement learning methods.

Evolutionary Algorithms reinforcement-learning +1

Continuous Optimization Benchmarks by Simulation

2 code implementations14 Aug 2020 Martin Zaefferer, Frederik Rehbach

However, predictions from data-driven models tend to be smoother than the ground-truth from which the training data is derived.

Benchmarking Gaussian Processes

Expected Improvement versus Predicted Value in Surrogate-Based Optimization

1 code implementation9 Jan 2020 Frederik Rehbach, Martin Zaefferer, Boris Naujoks, Thomas Bartz-Beielstein

Few results from the literature show evidence, that under certain conditions, expected improvement may perform worse than something as simple as the predicted value of the surrogate model.

Bayesian Optimization

Surrogate Models for Enhancing the Efficiency of Neuroevolution in Reinforcement Learning

no code implementations22 Jul 2019 Jörg Stork, Martin Zaefferer, Thomas Bartz-Beielstein, A. E. Eiben

In detail, we investigate a) the potential of SMB-NE with respect to evaluation efficiency and b) how to select adequate input sets for the phenotypic distance measure in a reinforcement learning problem.

Evolutionary Algorithms reinforcement-learning +1

Prediction of neural network performance by phenotypic modeling

no code implementations16 Jul 2019 Alexander Hagg, Martin Zaefferer, Jörg Stork, Adam Gaier

This difference, the phenotypic distance, can then be used to situate these networks into a common input space, allowing us to produce surrogate models which can predict the performance of neural networks regardless of topology.

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

no code implementations9 Feb 2019 Jörg Stork, Martin Zaefferer, Thomas Bartz-Beielstein

For these expensive optimization tasks, surrogate model-based optimization is frequently applied as it features a good evaluation efficiency.

Evolutionary Algorithms

Distance-based Kernels for Surrogate Model-based Neuroevolution

no code implementations20 Jul 2018 Jörg Stork, Martin Zaefferer, Thomas Bartz-Beielstein

The topology optimization of artificial neural networks can be particularly difficult if the fitness evaluations require expensive experiments or simulations.

An Empirical Approach For Probing the Definiteness of Kernels

no code implementations10 Jul 2018 Martin Zaefferer, Thomas Bartz-Beielstein, Günter Rudolph

We provide a proof-of-concept with 16 different distance measures for permutations.

Linear Combination of Distance Measures for Surrogate Models in Genetic Programming

no code implementations3 Jul 2018 Martin Zaefferer, Jörg Stork, Oliver Flasch, Thomas Bartz-Beielstein

We investigate how different genotypic and phenotypic distance measures can be used to learn Kriging models as surrogates.

Symbolic Regression

A First Analysis of Kernels for Kriging-based Optimization in Hierarchical Search Spaces

no code implementations3 Jul 2018 Martin Zaefferer, Daniel Horn

Many real-world optimization problems require significant resources for objective function evaluations.

Evolutionary Algorithms

In a Nutshell -- The Sequential Parameter Optimization Toolbox

1 code implementation12 Dec 2017 Thomas Bartz-Beielstein, Martin Zaefferer, Frederik Rehbach

The sequential parameter optimization (SPOT) package for R is a toolbox for tuning and understanding simulation and optimization algorithms.

Cannot find the paper you are looking for? You can Submit a new open access paper.