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

Recent studies in multi-agent communicative reinforcement learning (MACRL)have demonstrated that multi-agent coordination can be greatly improved byallowing communication between agents. Meanwhile, adversarial machine learning(ML) has shown that ML models are vulnerable to attacks. Despite the increasingconcern about the robustness of ML algorithms, how to achieve robustcommunication in multi-agent reinforcement learning has been largely neglected.In this paper, we systematically explore the problem of adversarialcommunication in MACRL. Our main contributions are threefold. First, we proposean effective method to perform attacks in MACRL, by learning a model togenerate optimal malicious messages. Second, we develop a defence method basedon message reconstruction, to maintain multi-agent coordination under messageattacks. Third, we formulate the adversarial communication problem as atwo-player zero-sum game and propose a game-theoretical method R-MACRL toimprove the worst-case defending performance. Empirical results demonstratethat many state-of-the-art MACRL methods are vulnerable to message attacks, andour method can significantly improve their robustness.

Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning