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

Recent developments have established the vulnerability of deep reinforcementlearning to policy manipulation attacks via intentionally perturbed inputs,known as adversarial examples. In this work, we propose a technique formitigation of such attacks based on addition of noise to the parameter space ofdeep reinforcement learners during training. We experimentally verify theeffect of parameter-space noise in reducing the transferability of adversarialexamples, and demonstrate the promising performance of this technique inmitigating the impact of whitebox and blackbox attacks at both test andtraining times.

Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise