mlsanityData to 14 Oct 2026

Online Robustness Training for Deep Reinforcement Learning

arXiv 1911.00887 ↗First posted 3 Nov 2019cs.LG stat.MLcited by 26

Not on the map. Why?

Abstract (arXiv)

In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted states and disrupt training. We propose a system called Robust Student-DQN (RS-DQN), which permits online robustness training alongside Q networks, while preserving competitive performance. We show that RS-DQN can be combined with (i) state-of-the-art adversarial training and (ii) provably robust training to obtain an agent that is resilient to strong attacks during training and evaluation.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). First posted on arXiv 3 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 6; 2023: 5; 2024: 3; 2025: 6; 2026: 1.

26 papers.

Sort:

By area:

  1. 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 135
  2. 2021Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RLcited by 55
  3. 2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learningcited by 43
  4. 2021CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothingcited by 42
  5. 2022COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attackscited by 26
  6. 2023Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigationcited by 19
  7. 2024RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviorscited by 16
  8. 2022Admissible Policy Teaching through Reward Designcited by 12
  9. 2021Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPScited by 10
  10. 2025Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspectivecited by 10
  11. 2022Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systemscited by 7
  12. 2023Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RLcited by 7
14 more
  1. 2023Improve Robustness of Reinforcement Learning against Observation Perturbations via l_∞ Lipschitz Policy Networkscited by 7
  2. 2024Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-errorcited by 4
  3. 2021Improving Robustness of Deep Reinforcement Learning Agents: Environment Attack based on the Critic Networkcited by 3
  4. 2023Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretationcited by 3
  5. 2025Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approachcited by 3
  6. 2022Security of Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 2
  7. 2025Action Robust Reinforcement Learning via Optimal Adversary Aware Policy Optimizationcited by 1
  8. 2026TCRL: Temporal-Coupled Adversarial Training for Robust Constrained Reinforcement Learning in Worst-Case Scenarioscited by 1
  9. 2022Measuring Interventional Robustness in Reinforcement Learningcited by 0
  10. 2023Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbationscited by 0
  11. 2024On the Perturbed States for Transformed Input-robust Reinforcement Learningcited by 0
  12. 2025Towards Robust Deep Reinforcement Learning against Environmental State Perturbationcited by 0
  13. 2025A Dynamical Systems Framework for Reinforcement Learning Safety and Robustness Verificationcited by 0
  14. 2025On the Tension Between Optimality and Adversarial Robustness in Policy Optimizationcited by 0