Neutral Agent-based Adversarial Policy Learning against Deep Reinforcement Learning in Multi-party Open Systems
Preprint
Abstract
Reinforcement learning (RL) has been an important machine learning paradigm for solving long-horizon sequential decision-making problems under uncertainty. By integrating deep neural networks (DNNs) into the RL framework, deep reinforcement learning (DRL) has emerged, which achieved significant success in various domains. However, the integration of DNNs also makes it vulnerable to adversarial attacks. Existing adversarial attack techniques mainly focus on either directly manipulating the environment with which a victim agent interacts or deploying an adversarial agent that interacts with the victim agent to induce abnormal behaviors. While these techniques achieve promising results, their adoption in multi-party open systems remains limited due to two major reasons: impractical assumption of full control over the environment and dependent on interactions with victim agents. To enable adversarial attacks in multi-party open systems, in this paper, we redesigned an adversarial policy learning approach that can mislead well-trained victim agents without requiring direct interactions with these agents or full control over their environments. Particularly, we propose a neutral agent-based approach across various task scenarios in multi-party open systems. While the neutral agents seemingly are detached from the victim agents, indirectly influence them through the shared environment. We evaluate our proposed method on the SMAC platform based on Starcraft II and the autonomous driving simulation platform Highway-env. The experimental results demonstrate that our method can launch general and effective adversarial attacks in multi-party open systems.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Attacking cooperative multi-agent reinforcement learning by adversarial minority influenceNeural Networks, 2025
- CCMA: A framework for cascading cooperative multi-agent in autonomous driving merging using Large Language ModelsExpert Systems with Applications, 2025
- Multi-Agent Deep Reinforcement Learning for UAVs Navigation in Unknown Complex EnvironmentIEEE Transactions on Intelligent Vehicles, 2023
- Adversarial attacks on cooperative multi-agent deep reinforcement learning: a dynamic group-based adversarial example transferability methodComplex & Intelligent Systems, 2023
- Deep Multi-Agent Reinforcement Learning for Highway On-Ramp Merging in Mixed TrafficIEEE Transactions on Intelligent Transportation Systems, 2023
- Multi-Agent Reinforcement Learning Aided Intelligent UAV Swarm for Target TrackingIEEE Transactions on Vehicular Technology, 2021
- Autonomous Driving Strategies at Intersections: Scenarios, State-of-the-Art, and Future Outlooks2021
- Highly accurate protein structure prediction with AlphaFoldNature, 2021
- Grandmaster level in StarCraft II using multi-agent reinforcement learningNature, 2019
- The Limitations of Deep Learning in Adversarial Settings2016