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

End-to-end reinforcement learning on images showed significant progress inthe recent years. Data-based approach leverage data augmentation and domainrandomization while representation learning methods use auxiliary losses tolearn task-relevant features. Yet, reinforcement still struggles in visuallydiverse environments full of distractions and spurious noise. In this work, wetackle the problem of robust visual control at its core and present VIBR(View-Invariant Bellman Residuals), a method that combines multi-view trainingand invariant prediction to reduce out-of-distribution (OOD) generalization gapfor RL based visuomotor control. Our model-free approach improve baselinesperformances without the need of additional representation learning objectivesand with limited additional computational cost. We show that VIBR outperformsexisting methods on complex visuo-motor control environment with high visualperturbation. Our approach achieves state-of the-art results on the DistractingControl Suite benchmark, a challenging benchmark still not solved by currentmethods, where we evaluate the robustness to a number of visual perturbators,as well as OOD generalization and extrapolation capabilities.

VIBR: Learning View-Invariant Value Functions for Robust Visual Control