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

The ability to use a 2D map to navigate a complex 3D environment is quiteremarkable, and even difficult for many humans. Localization and navigation isalso an important problem in domains such as robotics, and has recently becomea focus of the deep reinforcement learning community. In this paper we teach areinforcement learning agent to read a map in order to find the shortest wayout of a random maze it has never seen before. Our system combines severalstate-of-the-art methods such as A3C and incorporates novel elements such as arecurrent localization cell. Our agent learns to localize itself based on 3Dfirst person images and an approximate orientation angle. The agent generalizeswell to bigger mazes, showing that it learned useful localization andnavigation capabilities.

Teaching a Machine to Read Maps with Deep Reinforcement Learning