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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Contextual policy search (CPS) is a class of multi-task reinforcementlearning algorithms that is particularly useful for robotic applications. Arecent state-of-the-art method is Contextual Covariance Matrix AdaptationEvolution Strategies (C-CMA-ES). It is based on the standard black-boxoptimization algorithm CMA-ES. There are two useful extensions of CMA-ES thatwe will transfer to C-CMA-ES and evaluate empirically: ACM-ES, which uses acomparison-based surrogate model, and aCMA-ES, which uses an active update ofthe covariance matrix. We will show that improvements with these methods can beimpressive in terms of sample-efficiency, although this is not relevant anymore for the robotic domain.

Empirical Evaluation of Contextual Policy Search with a Comparison-based Surrogate Model and Active Covariance Matrix Adaptation