Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning. (arXiv:2108.03803v2 [cs.LG] UPDATED)

Recent studies in multi-agent communicative reinforcement learning (MACRL)
have demonstrated that multi-agent coordination can be greatly improved by
allowing communication between agents. Meanwhile, adversarial machine learning
(ML) has shown that ML models are vulnerable to attacks. Despite the increasing
concern about the robustness of ML algorithms, how to achieve robust
communication in multi-agent reinforcement learning has been largely neglected.
In this paper, we systematically explore the problem of adversarial
communication in MACRL. Our main contributions are threefold. First, we propose …

arxiv learning reinforcement learning