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

Reinforcement Learning (RL) has presented an impressive performance in videogames through raw pixel imaging and continuous control tasks. However, RLperforms poorly with high-dimensional observations such as raw pixel images. Itis generally accepted that physical state-based RL policies such as lasersensor measurements give a more sample-efficient result than learning bypixels. This work presents a new approach that extracts information from adepth map estimation to teach an RL agent to perform the mapless navigation ofUnmanned Aerial Vehicle (UAV). We propose the Depth-Imaged ContrastiveUnsupervised Prioritized Representations in Reinforcement Learning(Depth-CUPRL)that estimates the depth of images with a prioritized replay memory. We used acombination of RL and Contrastive Learning to lead with the problem of RL basedon images. From the analysis of the results with Unmanned Aerial Vehicles(UAVs), it is possible to conclude that our Depth-CUPRL approach is effectivefor the decision-making and outperforms state-of-the-art pixel-based approachesin the mapless navigation capability.

Depth-CUPRL: Depth-Imaged Contrastive Unsupervised Prioritized  Representations in Reinforcement Learning for Mapless Navigation of Unmanned  Aerial Vehicles