mlsanityData to 14 Oct 2026

Towards Robust Deep Reinforcement Learning against Environmental State Perturbation

arXiv 2506.08961 ↗First posted 10 Jun 2025cs.LG cs.AIcited by 0

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

Abstract (arXiv)

Adversarial attacks and robustness in Deep Reinforcement Learning (DRL) have been widely studied in various threat models; however, few consider environmental state perturbations, which are natural in embodied scenarios. To improve the robustness of DRL agents, we formulate the problem of environmental state perturbation, introducing a preliminary non-targeted attack method as a calibration adversary, and then propose a defense framework, named Boosted Adversarial Training (BAT), which first tunes the agents via supervised learning to avoid catastrophic failure and subsequently adversarially trains the agent with reinforcement learning. Extensive experimental results substantiate the vulnerability of mainstream agents under environmental state perturbations and the effectiveness of our proposed attack. The defense results demonstrate that while existing robust reinforcement learning algorithms may not be suitable, our BAT framework can significantly enhance the robustness of agents against environmental state perturbations across various situations.

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 34 of its 40 references that are in the map. First posted on arXiv 10 Jun 2025.

Builds on

34 of 40 references.

References · 34

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  5. 2017One pixel attack for fooling deep neural networkscited by 582
  6. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  7. 2017Robust Adversarial Reinforcement Learningcited by 451
  8. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  9. 2017Adversarial Attacks on Neural Network Policiescited by 320
  10. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 238
  11. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 214
  12. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 166
22 more
  1. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 154
  2. 2021Collaborating with Humans without Human Datacited by 142
  3. 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 135
  4. 2021Goal Misgeneralization in Deep Reinforcement Learningcited by 123
  5. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  6. 2018A Dissection of Overfitting and Generalization in Continuous Reinforcement Learningcited by 87
  7. 2020Robust Deep Reinforcement Learning through Adversarial Losscited by 75
  8. 2019Certified Adversarial Robustness for Deep Reinforcement Learningcited by 47
  9. 2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learningcited by 43
  10. 2020On the Robustness of Cooperative Multi-Agent Reinforcement Learningcited by 39
  11. 2023Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biasedcited by 37
  12. 2019Characterizing Attacks on Deep Reinforcement Learningcited by 31
  13. 2019TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agentscited by 30
  14. 2019Online Robustness Training for Deep Reinforcement Learningcited by 26
  15. 2020Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learningcited by 24
  16. 2022Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learningcited by 21
  17. 2022Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculumcited by 15
  18. 2022Coordination with Humans via Strategy Matchingcited by 14
  19. 2021Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patternscited by 13
  20. 2021Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defensescited by 9
  21. 2022Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaborationcited by 8
  22. 2021Improving Robustness of Deep Reinforcement Learning Agents: Environment Attack based on the Critic Networkcited by 3

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. 2024Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
  3. 2025State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning
  4. 2025Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses
  5. 2026Reward-Preserving Attacks For Robust Reinforcement Learning
  6. 2026Robust Adversarial Reinforcement Learning with Risk Sensitivity and Critic Consistency Regularization
  7. 2024Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space
  8. 2026Robust Policy Optimization via Adversarial Importance Sampling