mlsanityData to 7 Oct 2026

Adversarial Robust Deep Reinforcement Learning Requires Redefining Robustness

arXiv 2301.07487 ↗First posted 17 Jan 2023cs.LG cs.AI cs.CRcited by 18

Not on the map. Why?

Abstract (arXiv)

Learning from raw high dimensional data via interaction with a given environment has been effectively achieved through the utilization of deep neural networks. Yet the observed degradation in policy performance caused by imperceptible worst-case policy dependent translations along high sensitivity directions (i.e. adversarial perturbations) raises concerns on the robustness of deep reinforcement learning policies. In our paper, we show that these high sensitivity directions do not lie only along particular worst-case directions, but rather are more abundant in the deep neural policy landscape and can be found via more natural means in a black-box setting. Furthermore, we show that vanilla training techniques intriguingly result in learning more robust policies compared to the policies learnt via the state-of-the-art adversarial training techniques. We believe our work lays out intriguing properties of the deep reinforcement learning policy manifold and our results can help to build robust and generalizable deep reinforcement learning policies.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 17 Jan 2023.

Builds on

25 of 36 references.

References · 25

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2016Adversarial examples in the physical worldcited by 1,762
  9. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  10. 2016OpenAI Gymcited by 1,684
  11. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  12. 2015Prioritized Experience Replaycited by 1,070
13 more
  1. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  2. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  3. 2017Robust Adversarial Reinforcement Learningcited by 439
  4. 2017Adversarial Attacks on Neural Network Policiescited by 314
  5. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 235
  6. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
  7. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 163
  8. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
  9. 2017Delving into adversarial attacks on deep policiescited by 104
  10. 2020Robust Deep Reinforcement Learning through Adversarial Losscited by 73
  11. 2020Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learningcited by 62
  12. 2021Investigating Vulnerabilities of Deep Neural Policiescited by 15
  13. 2021Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 6; 2025: 5; 2026: 4.

18 papers.

Sort:

By area:

  1. 2025Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspectivecited by 10
  2. 2024A Survey Analyzing Generalization in Deep Reinforcement Learningcited by 8
  3. 2023Improve Robustness of Reinforcement Learning against Observation Perturbations via l_∞ Lipschitz Policy Networkscited by 7
  4. 2023Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisionscited by 6
  5. 2024Understanding and Diagnosing Deep Reinforcement Learningcited by 5
  6. 2024Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-errorcited by 4
  7. 2024Benchmarking Deep Reinforcement Learning for Navigation in Denied Sensor Environmentscited by 3
  8. 2026Safety, Security, and Cognitive Risks in World Modelscited by 3
  9. 2024Robust Deep Reinforcement Learning against Adversarial Behavior Manipulationcited by 2
  10. 2024On Minimizing Adversarial Counterfactual Error in Adversarial RLcited by 2
  11. 2025Microservice Deployment in Space Computing Power Networks via Robust Reinforcement Learningcited by 1
  12. 2025CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximizationcited by 1
6 more
  1. 2026Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement Learningcited by 1
  2. 2023PGN: A perturbation generation network against deep reinforcement learningcited by 0
  3. 2025Diffusion Guided Adversarial State Perturbations in Reinforcement Learningcited by 0
  4. 2025On the Tension Between Optimality and Adversarial Robustness in Policy Optimizationcited by 0
  5. 2026CIVA: Critic-Induced Value-Subspace Attacks on Visual World-Model Agentscited by 0
  6. 2026Robust Policy Optimization via Adversarial Importance Samplingcited by 0