mlsanityData to 7 Oct 2026

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

arXiv 2003.08938 ↗First posted 19 Mar 2020cs.LG stat.MLcited by 235

Not on the map. Why?

Cited by 24 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

A deep reinforcement learning (DRL) agent observes its states through observations, which may contain natural measurement errors or adversarial noises. Since the observations deviate from the true states, they can mislead the agent into making suboptimal actions. Several works have shown this vulnerability via adversarial attacks, but existing approaches on improving the robustness of DRL under this setting have limited success and lack for theoretical principles. We show that naively applying existing techniques on improving robustness for classification tasks, like adversarial training, is ineffective for many RL tasks. We propose the state-adversarial Markov decision process (SA-MDP) to study the fundamental properties of this problem, and develop a theoretically principled policy regularization which can be applied to a large family of DRL algorithms, including proximal policy optimization (PPO), deep deterministic policy gradient (DDPG) and deep Q networks (DQN), for both discrete and continuous action control problems. We significantly improve the robustness of PPO, DDPG and DQN agents under a suite of strong white box adversarial attacks, including new attacks of our own. Additionally, we find that a robust policy noticeably improves DRL performance even without an adversary in a number of environments. Our code is available at https://github.com/chenhongge/StateAdvDRL.

Key facts. Cited by 235 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 37; 2023: 51; 2024: 40; 2025: 44; 2026: 43.

235 papers.

Sort:

By area:

  1. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 224
  2. 2024DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Modelscited by 143
  3. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  4. 2021Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPscited by 115
  5. 2022Robust Reinforcement Learning using Offline Datacited by 95
  6. 2022Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexitycited by 85
  7. 2022RORL: Robust Offline Reinforcement Learning via Conservative Smoothingcited by 83
  8. 2021Sample Complexity of Robust Reinforcement Learning with a Generative Modelcited by 82
  9. 2021Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RLcited by 54
  10. 2023Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coveragecited by 51
  11. 2023The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Modelcited by 50
  12. 2022Sound Adversarial Audio-Visual Navigationcited by 46
38 more
  1. 2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learningcited by 42
  2. 2021CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothingcited by 41
  3. 2021Boosting Fast Adversarial Training with Learnable Adversarial Initializationcited by 40
  4. 2022Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Riskcited by 40
  5. 2022On the Robustness of Safe Reinforcement Learning under Observational Perturbationscited by 38
  6. 2023Robust Multi-Agent Reinforcement Learning with State Uncertaintycited by 35
  7. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
  8. 2024Reward-Robust RLHF in LLMscited by 32
  9. 2022Distributionally Robust Offline Reinforcement Learning with Linear Function Approximationcited by 31
  10. 2023Corruption-Robust Offline Reinforcement Learning with General Function Approximationcited by 30
  11. 2022COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attackscited by 25
  12. 2023Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlationcited by 25
  13. 2023Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithmscited by 25
  14. 2023Towards Robust Offline Reinforcement Learning under Diverse Data Corruptioncited by 24
  15. 2025RobustVLA: On Robustness of Vision-Language-Action Model against Multi-Modal Perturbationscited by 23
  16. 2022L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learningcited by 22
  17. 2022What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?cited by 21
  18. 2023Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Functioncited by 19
  19. 2021Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learningcited by 18
  20. 2021Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimizationcited by 18
  21. 2023Adversarial Robust Deep Reinforcement Learning Requires Redefining Robustnesscited by 18
  22. 2023Distributionally Robust Model-based Reinforcement Learning with Large State Spacescited by 17
  23. 2024Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learningcited by 17
  24. 2022Robust Policy Learning over Multiple Uncertainty Setscited by 16
  25. 2022RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on statescited by 16
  26. 2022Adversarial Cheap Talkcited by 16
  27. 2023Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influencecited by 16
  28. 2023Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexitycited by 16
  29. 2023Structure in Deep Reinforcement Learning: A Survey and Open Problemscited by 16
  30. 2021Investigating Vulnerabilities of Deep Neural Policiescited by 15
  31. 2022Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculumcited by 15
  32. 2023Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackerscited by 15
  33. 2024Adversarial Safety-Critical Scenario Generation using Naturalistic Human Driving Priorscited by 15
  34. 2022Are AlphaZero-like Agents Robust to Adversarial Perturbations?cited by 14
  35. 2023Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attackscited by 14
  36. 2021Understanding Adversarial Attacks on Observations in Deep Reinforcement Learningcited by 13
  37. 2021Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patternscited by 13
  38. 2022A Search-Based Testing Approach for Deep Reinforcement Learning Agentscited by 12

50 most cited of 235 All 235 (JSON)