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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper proposes adversarial attacks for Reinforcement Learning (RL) andthen improves the robustness of Deep Reinforcement Learning algorithms (DRL) toparameter uncertainties with the help of these attacks. We show that even anaively engineered attack successfully degrades the performance of DRLalgorithm. We further improve the attack using gradient information of anengineered loss function which leads to further degradation in performance.These attacks are then leveraged during training to improve the robustness ofRL within robust control framework. We show that this adversarial training ofDRL algorithms like Deep Double Q learning and Deep Deterministic PolicyGradients leads to significant increase in robustness to parameter variationsfor RL benchmarks such as Cart-pole, Mountain Car, Hopper and Half Cheetahenvironment.

Robust Deep Reinforcement Learning with Adversarial Attacks