Robust Communicative Multi-Agent Reinforcement Learning with Active Defense

2023-12-16 · Lebin Yu, Yunbo Qiu, Quanming Yao, Yuan Shen, Xudong Zhang, Jian Wang

Communication in multi-agent reinforcement learning (MARL) has been proven to effectively promote cooperation among agents recently. Since communication in real-world scenarios is vulnerable to noises and adversarial attacks, it is crucial to develop robust communicative MARL technique. However, existing research in this domain has predominantly focused on passive defense strategies, where agents receive all messages equally, making it hard to balance performance and robustness. We propose an active defense strategy, where agents automatically reduce the impact of potentially harmful messages on the final decision. There are two challenges to implement this strategy, that are defining unreliable messages and adjusting the unreliable messages' impact on the final decision properly. To address them, we design an Active Defense Multi-Agent Communication framework (ADMAC), which estimates the reliability of received messages and adjusts their impact on the final decision accordingly with the help of a decomposable decision structure. The superiority of ADMAC over existing methods is validated by experiments in three communication-critical tasks under four types of attacks.

📄 PDF Abstract BibTeX arXiv:2312.11545

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems

2022-06-21 · Yanchao Sun, Ruijie Zheng, Parisa Hassanzadeh, Yongyuan Liang 외

Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to share information and make good decisions. However, when deploying trained communicative agents in a real-world applicat…

Multi-agent Reinforcement Learning

Communicative Reinforcement Learning Agents for Landmark Detection in Brain Images

2020-08-18 · Guy Leroy, Daniel Rueckert, Amir Alansary

Accurate detection of anatomical landmarks is an essential step in several medical imaging tasks. We propose a novel communicative multi-agent reinforcement learning (C-MARL) system to automatically detect landmarks in 3…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

In-Context Reinforcement Learning via Communicative World Models

2025-08-08 · Fernando Martinez-Lopez, Tao Li, Yingdong Lu, Juntao Chen arxiv

Reinforcement learning (RL) agents often struggle to generalize to new tasks and contexts without updating their parameters, mainly because their learned representations and policies are overfit to the specifics of their…

Representation Learning Reinforcement Learning

Contextualized Privacy Defense for LLM Agents

2026-03-03 · Yule Wen, Yanzhe Zhang, Jianxun Lian, Xiaoyuan Yi 외 arxiv

LLM agents increasingly act on users' personal information, yet existing privacy defenses remain limited in both design and adaptability. Most prior approaches rely on static or passive defenses, such as prompting and gu…

Reinforcement Learning

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

2021-08-09 · Wanqi Xue, Wei Qiu, Bo An, Zinovi Rabinovich 외

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 …