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

Tomorrow's robots will need to distinguish useful information from noise whenperforming different tasks. A household robot for instance may continuouslyreceive a plethora of information about the home, but needs to focus on just asmall subset to successfully execute its current chore. Filtering distractinginputs that contain irrelevant data has received little attention in thereinforcement learning literature. To start resolving this, we formulate aproblem setting in reinforcement learning called the $\textit{extremely noisyenvironment}$ (ENE), where up to $99\%$ of the input features are pure noise.Agents need to detect which features provide task-relevant information aboutthe state of the environment. Consequently, we propose a new method termed$\textit{Automatic Noise Filtering}$ (ANF), which uses the principles ofdynamic sparse training in synergy with various deep reinforcement learningalgorithms. The sparse input layer learns to focus its connectivity ontask-relevant features, such that ANF-SAC and ANF-TD3 outperform standard SACand TD3 by a large margin, while using up to $95\%$ fewer weights. Furthermore,we devise a transfer learning setting for ENEs, by permuting all features ofthe environment after 1M timesteps to simulate the fact that other informationsources can become relevant as the world evolves. Again, ANF surpasses thebaselines in final performance and sample complexity. Our code is available athttps://github.com/bramgrooten/automatic-noise-filtering

Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning