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/

Zendy Plus

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

Zendy Tools

Zendy Open

It is common to implicitly assume access to intelligently captured inputs(e.g., photos from a human photographer), yet autonomously capturing goodobservations is itself a major challenge. We address the problem of learning tolook around: if a visual agent has the ability to voluntarily acquire new viewsto observe its environment, how can it learn efficient exploratory behaviors toacquire informative observations? We propose a reinforcement learning solution,where the agent is rewarded for actions that reduce its uncertainty about theunobserved portions of its environment. Based on this principle, we develop arecurrent neural network-based approach to perform active completion ofpanoramic natural scenes and 3D object shapes. Crucially, the learned policiesare not tied to any recognition task nor to the particular semantic contentseen during training. As a result, 1) the learned "look around" behavior isrelevant even for new tasks in unseen environments, and 2) training dataacquisition involves no manual labeling. Through tests in diverse settings, wedemonstrate that our approach learns useful generic policies that transfer tonew unseen tasks and environments. Completion episodes are shown athttps://goo.gl/BgWX3W.

Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks