mlsanityData to 14 Oct 2026

Whatever Does Not Kill Deep Reinforcement Learning, Makes It Stronger

arXiv 1712.09344 ↗First posted 23 Dec 2017cs.AIcited by 35

Not on the map. Why?

Abstract (arXiv)

Recent developments have established the vulnerability of deep Reinforcement Learning (RL) to policy manipulation attacks via adversarial perturbations. In this paper, we investigate the robustness and resilience of deep RL to training-time and test-time attacks. Through experimental results, we demonstrate that under noncontiguous training-time attacks, Deep Q-Network (DQN) agents can recover and adapt to the adversarial conditions by reactively adjusting the policy. Our results also show that policies learned under adversarial perturbations are more robust to test-time attacks. Furthermore, we compare the performance of ε-greedy and parameter-space noise exploration methods in terms of robustness and resilience against adversarial perturbations.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 9; 2023: 7; 2024: 4; 2025: 8; 2026: 1.

35 papers.

Sort:

By area:

  1. 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 135
  2. 2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learningcited by 43
  3. 2021CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothingcited by 42
  4. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 36
  5. 2022COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attackscited by 26
  6. 2021Defense Against Reward Poisoning Attacks in Reinforcement Learningcited by 21
  7. 2022Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculumcited by 15
  8. 2023Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attackscited by 14
  9. 2022A Search-Based Testing Approach for Deep Reinforcement Learning Agentscited by 13
  10. 2021Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPScited by 10
  11. 2023Adjustable Robust Reinforcement Learning for Online 3D Bin Packingcited by 10
  12. 2021Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defensescited by 9
23 more
  1. 2022Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learningcited by 9
  2. 2024Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantizationcited by 6
  3. 2022Deep-Attack over the Deep Reinforcement Learningcited by 5
  4. 2023Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learningcited by 5
  5. 2024Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-errorcited by 4
  6. 2023SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learningcited by 3
  7. 2023Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policycited by 3
  8. 2025Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approachcited by 3
  9. 2021On Assessing The Safety of Reinforcement Learning algorithms Using Formal Methodscited by 2
  10. 2025Policy Teaching via Data Poisoning in Learning from Human Preferencescited by 2
  11. 2025A Conceptual Framework for AI-based Decision Systems in Critical Infrastructurescited by 2
  12. 2023Policy Resilience to Environment Poisoning Attacks on Reinforcement Learningcited by 1
  13. 2022Attacking and Defending Deep Reinforcement Learning Policiescited by 0
  14. 2022Explainable and Safe Reinforcement Learning for Autonomous Air Mobilitycited by 0
  15. 2023Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbationscited by 0
  16. 2024On the Perturbed States for Transformed Input-robust Reinforcement Learningcited by 0
  17. 2024Robust off-policy Reinforcement Learning via Soft Constrained Adversarycited by 0
  18. 2025On the Definition of Robustness and Resilience of AI Agents for Real-time Congestion Managementcited by 0
  19. 2025Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluationcited by 0
  20. 2025Meta Policy Switching for Secure UAV Deconfliction in Adversarial Airspacecited by 0
  21. 2025Neutral Agent-based Adversarial Policy Learning against Deep Reinforcement Learning in Multi-party Open Systemscited by 0
  22. 2025On the Tension Between Optimality and Adversarial Robustness in Policy Optimizationcited by 0
  23. 2026Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbationscited by 0