Results 131 to 140 of about 5,249 (165)

Towards an Adaptive CMA-ES Configurator

2018
Recent work has shown that significant performance gains over state-of-the-art CMA-ES variants can be obtained by a recombination of their algorithmic modules. It seems plausible that further improvements can be realized by an adaptive selection of these configurations.
Sander van Rijn, Carola Doerr, Thomas Bäck   +2 more
openaire   +2 more sources

CMA-ES for one-class constraint synthesis

Proceedings of the 2020 Genetic and Evolutionary Computation Conference, 2020
We propose CMA-ES for One-Class Constraint Synthesis (CMAESOCCS), a method that synthesizes Mixed-Integer Linear Programming (MILP) model from exemplary feasible solutions to this model using Covariance Matrix Adaptation - Evolutionary Strategy (CMA-ES).
Marcin Karmelita, Tomasz P. Pawlak
openaire   +1 more source

Uncertainty handling CMA-ES for reinforcement learning

Proceedings of the 11th Annual conference on Genetic and evolutionary computation, 2009
The covariance matrix adaptation evolution strategy (CMAES) has proven to be a powerful method for reinforcement learning (RL). Recently, the CMA-ES has been augmented with an adaptive uncertainty handling mechanism. Because uncertainty is a typical property of RL problems this new algorithm, termed UH-CMA-ES, is promising for RL.
Verena Heidrich-Meisner, Christian Igel
openaire   +1 more source

A CMA-ES with Multiplicative Covariance Matrix Updates

Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation, 2015
Covariance matrix adaptation (CMA) mechanisms are core building blocks of modern evolution strategies. Despite sharing a common principle, the exact implementation of CMA varies considerably between different algorithms. In this paper, we investigate the benefits of an exponential parametrization of the covariance matrix in the CMA-ES.
Krause, Oswin, Glasmachers, Tobias
openaire   +2 more sources

Learning Step-Size Adaptation in CMA-ES

2020
An algorithm’s parameter setting often affects its ability to solve a given problem, e.g., population-size, mutation-rate or crossover-rate of an evolutionary algorithm. Furthermore, some parameters have to be adjusted dynamically, such as lowering the mutation-strength over time.
Gresa Shala, André Biedenkapp, Noor H. Awad, Steven Adriaensen, Marius Lindauer, Frank Hutter   +5 more
openaire   +1 more source

A note on the CMA-ES for functions with periodic variables

Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2018
In this short paper, we reveal the issue of the covariance matrix adaptation evolution strategy when solving a function with periodic variables. We investigate the effect of a simple modification that the coordinate-wise standard deviation of the sampling distribution is restricts to the one-fourth of the period length.
Takahiro Yamaguchi, Youhei Akimoto
openaire   +1 more source

2D/3D registration with the CMA-ES method

SPIE Proceedings, 2008
In this paper, we propose a new method for 2D/3D registration and report its experimental results. The method employs the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) algorithm to search for an optimal transformation that aligns the 2D and 3D data.
Ren Hui Gong, Purang Abolmaesumi
openaire   +1 more source

Hybrid of PSO and CMA-ES for Global Optimization

2019 IEEE Congress on Evolutionary Computation (CEC), 2019
Both Particle Swarm Optimization (PSO) and Evolution Strategy with Covariance Matrix Adaptation (CMA-ES) exhibit good performance when solving global optimization problems. However, PSO could be misled by historical information and falls into a local optimum. Further, CMA-ES cannot fully utilize global information.
Peilan Xu, Wenjian Luo, Xin Lin 0004, Yingying Qiao, Tao Zhu 0001   +4 more
openaire   +1 more source

Sequential sampling for noisy optimisation with CMA-ES

Proceedings of the Genetic and Evolutionary Computation Conference, 2018
This paper proposes a novel sequential sampling scheme to allocate samples to individuals in order to maximally inform the selection step in Covariance Matrix Adaptation Evolution Strategies (CMA-ES) for noisy function optimisation. More specifically we adopt the well-known Knowledge Gradient (KG) method to minimise the Kullback-Leibler divergence ...
Matthew J. Groves, Jürgen Branke
openaire   +1 more source

Reducing the space-time complexity of the CMA-ES

Proceedings of the 9th annual conference on Genetic and evolutionary computation, 2007
A limited memory version of the covariance matrix adaptation evolution strategy (CMA-ES) is presented. This algorithm, L-CMA-ES, improves the space and time complexity of the CMA-ES algorithm. The L-CMA-ES uses the $m$ eigenvectors and eigenvalues spanning the m-dimensional dominant subspace of the n-dimensional covariance matrix, C, describing the ...
James N. Knight, Monte Lunacek
openaire   +1 more source