English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

A fascinating aspect of nature lies in its ability to produce a collection oforganisms that are all high-performing in their niche. Quality-Diversity (QD)methods are evolutionary algorithms inspired by this observation, that obtainedgreat results in many applications, from wing design to robot adaptation.Recently, several works demonstrated that these methods could be applied toperform neuro-evolution to solve control problems in large search spaces. Insuch problems, diversity can be a target in itself. Diversity can also be a wayto enhance exploration in tasks exhibiting deceptive reward signals. While thefirst aspect has been studied in depth in the QD community, the latter remainsscarcer in the literature. Exploration is at the heart of several domainstrying to solve control problems such as Reinforcement Learning and QD methodsare promising candidates to overcome the challenges associated. Therefore, webelieve that standardized benchmarks exhibiting control problems in highdimension with exploration difficulties are of interest to the QD community. Inthis paper, we highlight three candidate benchmarks and explain why they appearrelevant for systematic evaluation of QD algorithms. We also provideopen-source implementations in Jax allowing practitioners to run fast andnumerous experiments on few compute resources.

Assessing Quality-Diversity Neuro-Evolution Algorithms Performance in Hard Exploration Problems