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

Model based predictions of future trajectories of a dynamical system oftensuffer from inaccuracies, forcing model based control algorithms to re-planoften, thus being computationally expensive, suboptimal and not reliable. Inthis work, we propose a model agnostic method for estimating the uncertainty ofa model?s predictions based on reconstruction error, using it in control andexploration. As our experiments show, this uncertainty estimation can be usedto improve control performance on a wide variety of environments by choosingpredictions of which the model is confident. It can also be used for activelearning to explore more efficiently the environment by planning fortrajectories with high uncertainty, allowing faster model learning.

Improving Model-Based Control and Active Exploration with Reconstruction Uncertainty Optimization