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

Although reinforcement learning (RL) is considered the gold standard forpolicy design, it may not always provide a robust solution in variousscenarios. This can result in severe performance degradation when theenvironment is exposed to potential disturbances. Adversarial training using atwo-player max-min game has been proven effective in enhancing the robustnessof RL agents. In this work, we extend the two-player game by introducing anadversarial herd, which involves a group of adversaries, in order to address($\textit{i}$) the difficulty of the inner optimization problem, and($\textit{ii}$) the potential over pessimism caused by the selection of acandidate adversary set that may include unlikely scenarios. We first provethat adversarial herds can efficiently approximate the inner optimizationproblem. Then we address the second issue by replacing the worst-caseperformance in the inner optimization with the average performance over theworst-$k$ adversaries. We evaluate the proposed method on multiple MuJoCoenvironments. Experimental results demonstrate that our approach consistentlygenerates more robust policies.

Robust Reinforcement Learning through Efficient Adversarial Herding