mlsanityData to 14 Oct 2026

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

arXiv 2510.10937 ↗First posted 13 Oct 2025cs.LG cs.CRcited by 0

On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance

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.

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.

Builds on

26 of 51 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximization29 Jan

Other references · 25

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  6. 2016End to End Learning for Self-Driving Carscited by 1,009
  7. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
  8. 2018Learning Dexterous In-Hand Manipulationcited by 687
  9. 2019The StarCraft Multi-Agent Challengecited by 597
  10. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
  11. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 485
  12. 2017Adversarial Attacks on Neural Network Policiescited by 320
13 more
  1. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 214
  2. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 187
  3. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 166
  4. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 154
  5. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  6. 2021Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Trafficcited by 41
  7. 2017Whatever Does Not Kill Deep Reinforcement Learning, Makes It Strongercited by 35
  8. 2019Optimal Attacks on Reinforcement Learning Policiescited by 21
  9. 2022Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learningcited by 20
  10. 2017Detecting Adversarial Attacks on Neural Network Policies with Visual Foresightcited by 17
  11. 2023Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influencecited by 17
  12. 2018Online Robust Policy Learning in the Presence of Unknown Adversariescited by 15
  13. 2024SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systemscited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey
  2. 2025A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement Learning
  3. 2025Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
  4. 2022Imitating Opponent to Win: Adversarial Policy Imitation Learning in Two-player Competitive Games
  5. 2025Policy Disruption in Reinforcement Learning:Adversarial Attack with Large Language Models and Critical State Identification
  6. 2025Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses
  7. 2025Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks
  8. 2025SAJA: A State-Action Joint Attack Framework on Multi-Agent Deep Reinforcement Learning