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/

Zendy Plus

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

Zendy Tools

Zendy Open

Neural network policies trained using Deep Reinforcement Learning (DRL) arewell-known to be susceptible to adversarial attacks. In this paper, we considerattacks manifesting as perturbations in the observation space managed by theexternal environment. These attacks have been shown to downgrade policyperformance significantly. We focus our attention on well-trained deterministicand stochastic neural network policies in the context of continuous controlbenchmarks subject to four well-studied observation space adversarial attacks.To defend against these attacks, we propose a novel defense strategy using adetect-and-denoise schema. Unlike previous adversarial training approaches thatsample data in adversarial scenarios, our solution does not require samplingdata in an environment under attack, thereby greatly reducing risk duringtraining. Detailed experimental results show that our technique is comparablewith state-of-the-art adversarial training approaches.

Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising