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) is an agent-based approach for teaching robots tonavigate within the physical world. Gathering data for RL is known to be alaborious task, and real-world experiments can be risky. Simulators facilitatethe collection of training data in a quicker and more cost-effective manner.However, RL frequently requires a significant number of simulation steps for anagent to become skilful at simple tasks. This is a prevalent issue within thefield of RL-based visual quadrotor navigation where state dimensions aretypically very large and dynamic models are complex. Furthermore, renderingimages and obtaining physical properties of the agent can be computationallyexpensive. To solve this, we present a simulation framework, built on AirSim,which provides efficient parallel training. Building on this framework, Ape-Xis modified to incorporate decentralised training of AirSim environments tomake use of numerous networked computers. Through experiments we were able toachieve a reduction in training time from 3.9 hours to 11 minutes using theaforementioned framework and a total of 74 agents and two networked computers.Further details including a github repo and videos about our project,PRL4AirSim, can be found at https://sites.google.com/view/prl4airsim/home

Parallel Reinforcement Learning Simulation for Visual Quadrotor Navigation