# Neutral Agent-based Adversarial Policy Learning against Deep Reinforcement Learning in Multi-party Open Systems

arXiv: https://arxiv.org/abs/2510.10937 · HTML: https://mlsanity.com/paper/2510.10937/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods.
- Builds on 26 of its 51 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Placed in

- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Builds on (most cited first, 26 of 26)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [Value-Decomposition Networks For Cooperative Multi-Agent Learning](https://mlsanity.com/paper/1706.05296/) (2017)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [Adversarial Policies: Attacking Deep Reinforcement Learning](https://mlsanity.com/paper/1905.10615/) (2019)
- [Real-World Humanoid Locomotion with Reinforcement Learning](https://mlsanity.com/paper/2303.03381/) (2023)
- [Tactics of Adversarial Attack on Deep Reinforcement Learning Agents](https://mlsanity.com/paper/1703.06748/) (2017)
- [Robust Deep Reinforcement Learning with Adversarial Attacks](https://mlsanity.com/paper/1712.03632/) (2017)
- [Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks](https://mlsanity.com/paper/1701.04143/) (2017)
- [Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic](https://mlsanity.com/paper/2105.05701/) (2021)
- [Whatever Does Not Kill Deep Reinforcement Learning, Makes It Stronger](https://mlsanity.com/paper/1712.09344/) (2017)
- [Optimal Attacks on Reinforcement Learning Policies](https://mlsanity.com/paper/1907.13548/) (2019)
- [Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2206.01888/) (2022)
- [Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight](https://mlsanity.com/paper/1710.00814/) (2017)
- [Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence](https://mlsanity.com/paper/2302.03322/) (2023)
- [Online Robust Policy Learning in the Presence of Unknown Adversaries](https://mlsanity.com/paper/1807.06064/) (2018)
- [SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems](https://mlsanity.com/paper/2402.03741/) (2024)
- [CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximization](https://mlsanity.com/paper/2501.17667/) (2025)

## Abstract (arXiv)

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.