Skip to search formSkip to main contentSkip to account menu

Illuminating search spaces by mapping elites

The Multi-dimensional Archive of Phenotypic Elites (MAP-Elites) algorithm illuminates search spaces, allowing researchers to understand how interesting attributes of solutions combine to affect performance, either positively or, equally of interest, negatively.
View PDF on arXiv (opens in a new tab)

Robots that can adapt like animals

An intelligent trial-and-error algorithm is introduced that allows robots to adapt to damage in less than two minutes in large search spaces without requiring self-diagnosis or pre-specified contingency plans, and may shed light on the principles that animals use to adaptation to injury.
View on Nature (opens in a new tab)

Encouraging Behavioral Diversity in Evolutionary Robotics: An Empirical Study

Three main published approaches to behavioral diversity are reviewed and compared, showing that fostering behavioral diversity substantially improves the evolutionary process in the investigated experiments, regardless of genotype or task.
View on MIT Press (opens in a new tab)

The evolutionary origins of modularity

It is demonstrated that the ubiquitous, direct selection pressure to reduce the cost of connections between network nodes causes the emergence of modular networks.
View on Royal Society (opens in a new tab)

The Transferability Approach: Crossing the Reality Gap in Evolutionary Robotics

The transferability approach is proposed, a multiobjective formulation of ER in which two main objectives are optimized via a Pareto-based multiobjectives evolutionary algorithm: 1) the fitness; and 2) the transferability, estimated by a simulation-to-reality (STR) disparity measure.
View on IEEE (opens in a new tab)

Novelty-Based Multiobjectivization

Novelty search is a recent and promising approach to evolve neurocontrollers, especially to drive robots. The main idea is to maximize the novelty of behaviors instead of the efficiency. However,…
View via Publisher (opens in a new tab)

Evolutionary Robotics: What, Why, and Where to

The main achievements of evolutionary robotics are considered, focusing particularly on its contributions to both engineering and biology, and some of the most interesting findings are reviewed.
View via Publisher (opens in a new tab)

Using Centroidal Voronoi Tessellations to Scale Up the Multidimensional Archive of Phenotypic Elites Algorithm

This paper introduces a simple extension of MAP-Elites that has a constant, predefined number of regions irrespective of the dimensionality of the feature space, and shows that methods from computational geometry could partition a high-dimensional space into well-spread geometric regions.
View on IEEE (opens in a new tab)

Behavioral diversity measures for Evolutionary Robotics

This work explores generic behavioral similarity measures that only rely on sensori-motor values and reveals to classify behaviors globally as humans did, but with no clear correlation between the closeness to human classification and the efficiency within an evolutionary run.
View on IEEE (opens in a new tab)

Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity

This work introduces an original diversity-preservation mechanism, called behavioral diversity, that relies on a distance between behaviors (instead of genotypes or phenotypes) and multi-objective evolutionary optimization to overcome the bootstrap problem.
View on IEEE (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)