Robustness Testing for Multi-Agent Reinforcement Learning: State Perturbations on Critical Agents
This work addresses robustness testing for MARL, which is crucial for applications like smart traffic and unmanned aerial vehicles, but it appears incremental as it builds on existing adversarial perturbation methods.
The paper tackles the vulnerability of Multi-Agent Reinforcement Learning (MARL) algorithms to adversarial state perturbations by proposing a Robustness Testing framework for Critical Agents (RTCA), which uses Differential Evolution to select critical agents and generate worst-case joint actions, resulting in effective destruction of cooperation policies.
Multi-Agent Reinforcement Learning (MARL) has been widely applied in many fields such as smart traffic and unmanned aerial vehicles. However, most MARL algorithms are vulnerable to adversarial perturbations on agent states. Robustness testing for a trained model is an essential step for confirming the trustworthiness of the model against unexpected perturbations. This work proposes a novel Robustness Testing framework for MARL that attacks states of Critical Agents (RTCA). The RTCA has two innovations: 1) a Differential Evolution (DE) based method to select critical agents as victims and to advise the worst-case joint actions on them; and 2) a team cooperation policy evaluation method employed as the objective function for the optimization of DE. Then, adversarial state perturbations of the critical agents are generated based on the worst-case joint actions. This is the first robustness testing framework with varying victim agents. RTCA demonstrates outstanding performance in terms of the number of victim agents and destroying cooperation policies.