mlsanityData to 14 Oct 2026

PGN: A perturbation generation network against deep reinforcement learning

arXiv 2312.12904 ↗First posted 20 Dec 2023cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep reinforcement learning has advanced greatly and applied in many areas. In this paper, we explore the vulnerability of deep reinforcement learning by proposing a novel generative model for creating effective adversarial examples to attack the agent. Our proposed model can achieve both targeted attacks and untargeted attacks. Considering the specificity of deep reinforcement learning, we propose the action consistency ratio as a measure of stealthiness, and a new measurement index of effectiveness and stealthiness. Experiment results show that our method can ensure the effectiveness and stealthiness of attack compared with other algorithms. Moreover, our methods are considerably faster and thus can achieve rapid and efficient verification of the vulnerability of deep reinforcement learning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 27 references that are in the map. First posted on arXiv 20 Dec 2023.

Builds on

18 of 27 references.

References · 18

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2015Trust Region Policy Optimizationcited by 2,580
  6. 2017Adversarial Attacks on Neural Network Policiescited by 320
  7. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 166
  8. 2017Delving into adversarial attacks on deep policiescited by 104
  9. 2017Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigationcited by 98
  10. 2016Playing FPS Games with Deep Reinforcement Learningcited by 95
  11. 2020Adaptive Reward-Poisoning Attacks against Reinforcement Learningcited by 86
  12. 2020Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learningcited by 63
6 more
  1. 2019Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agentscited by 25
  2. 2023Adversarial Robust Deep Reinforcement Learning Requires Redefining Robustnesscited by 19
  3. 2019Adversarial Exploitation of Policy Imitationcited by 13
  4. 2019Phonetic-enriched Text Representation for Chinese Sentiment Analysis with Reinforcement Learningcited by 5
  5. 2022Deep-Attack over the Deep Reinforcement Learningcited by 5
  6. 2021Cyber Intrusion Detection by Using Deep Neural Networks with Attack-sharing Losscited by 1

Built on by

Not cited yet.