Robustness Testing for Multi-Agent Reinforcement Learning: State Perturbations on Critical Agents

Abstract

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.

References in corpus (21)

• Explaining and Harnessing Adversarial Examples
• One pixel attack for fooling deep neural networks
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games
• Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
• Actor-Attention-Critic for Multi-Agent Reinforcement Learning
• QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning
• Robust Deep Reinforcement Learning with Adversarial Attacks
• Adversarial Attacks on Neural Network Policies
• Robust Reinforcement Learning on State Observations with Learned Optimal Adversary
• Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations
• RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states
• Partially Observable Mean Field Multi-Agent Reinforcement Learning Based on Graph-Attention
• Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
• On the Robustness of Cooperative Multi-Agent Reinforcement Learning
• What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?
• Multi-Agent Deep Reinforcement Learning Based Trajectory Planning for Multi-UAV Assisted Mobile Edge Computing
• Distributed Distributionally Robust Optimization with Non-Convex Objectives
• Attacking c-MARL More Effectively: A Data Driven Approach
• Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence

Cited by in corpus (2)

• Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges
• Partially Observable Mean Field Multi-Agent Reinforcement Learning Based on Graph-Attention