通过对抗性少数影响攻击合作型多智能体强化学习
Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence
AI总结：
针对合作型多智能体强化学习（c-MARL）在白盒攻击假设下的局限性，提出了一种实用的黑盒对抗攻击方法AMI，通过单个对抗智能体单方面误导多数受害者智能体形成最坏合作，首次实现了对真实机器人集群的成功攻击。
摘要：
本研究探究了合作型多智能体强化学习（c-MARL）在对抗攻击下的脆弱性，这是现实部署前决定c-MARL最坏情况性能的关键因素。当前的基于观测的攻击受限于白盒假设，忽视了c-MARL复杂的多智能体交互和合作目标，导致攻击能力不切实际且受限。为解决这些不足，我们提出了Adversarial Minority Influence（AMI），一种针对c-MARL的实用且强大的攻击方法。AMI是一种实用的黑盒攻击，可在不知道受害者参数的情况下发起。AMI同样具有强大威力，它考虑了复杂的多智能体交互和智能体的合作目标，使得单个对抗智能体能够单方面误导多数受害者，形成特定的最坏情况合作。这反映了社会心理学中的少数影响现象。为了在复杂的智能体间交互下实现受害者策略的最大偏差，我们的单边攻击旨在刻画并最大化对抗者对受害者的影响。这通过适配一个源自互信息的单边智能体间关系度量来实现，从而减轻受害者影响对对抗者的不利效应。为将受害者引入联合有害场景，我们的定向攻击通过引导每个受害者走向特定目标，欺骗其陷入长期的合作有害境地，该目标由强化学习智能体执行的试错过程确定。通过AMI，我们实现了对真实世界机器人集群的首次成功攻击，并在Starcraft II和Multi-agent Mujoco等模拟环境中有效欺骗智能体陷入集体最坏情况。源代码和演示可在：https://github.com/DIG-Beihang/AMI 找到。
英文摘要：
This study probes the vulnerabilities of cooperative multi-agent reinforcement learning (c-MARL) under adversarial attacks, a critical determinant of c-MARL's worst-case performance prior to real-world implementation. Current observation-based attacks, constrained by white-box assumptions, overlook c-MARL's complex multi-agent interactions and cooperative objectives, resulting in impractical and limited attack capabilities. To address these shortcomes, we propose Adversarial Minority Influence (AMI), a practical and strong for c-MARL. AMI is a practical black-box attack and can be launched without knowing victim parameters. AMI is also strong by considering the complex multi-agent interaction and the cooperative goal of agents, enabling a single adversarial agent to unilaterally misleads majority victims to form targeted worst-case cooperation. This mirrors minority influence phenomena in social psychology. To achieve maximum deviation in victim policies under complex agent-wise interactions, our unilateral attack aims to characterize and maximize the impact of the adversary on the victims. This is achieved by adapting a unilateral agent-wise relation metric derived from mutual information, thereby mitigating the adverse effects of victim influence on the adversary. To lead the victims into a jointly detrimental scenario, our targeted attack deceives victims into a long-term, cooperatively harmful situation by guiding each victim towards a specific target, determined through a trial-and-error process executed by a reinforcement learning agent. Through AMI, we achieve the first successful attack against real-world robot swarms and effectively fool agents in simulated environments into collectively worst-case scenarios, including Starcraft II and Multi-agent Mujoco. The source code and demonstrations can be found at: https://github.com/DIG-Beihang/AMI.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
