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

Driving in the dynamic, multi-agent, and complex urban environment is adifficult task requiring a complex decision policy. The learning of such apolicy requires a state representation that can encode the entire environment.Mid-level representations that encode a vehicle's environment as images havebecome a popular choice, but they are quite high-dimensional, which limitstheir use in data-scarce cases such as reinforcement learning. In this article,we propose to learn a low dimensional and rich feature representation of theenvironment by training an encoder-decoder deep neural network to predictmultiple application relevant factors such as trajectories of other agents. Wedemonstrate that the use of the multi-head encoder-decoder neural networkresults in a more informative representation compared to a single-headencoder-decoder model. In particular, the proposed representation learningapproach helps the policy network to learn faster, with increased performanceand with less data, compared to existing approaches using a single-headnetwork.

Efficient Latent Representations using Multiple Tasks for Autonomous Driving