mlsanityData to 7 Oct 2026

Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents

arXiv 2406.18062 ↗First posted 26 Jun 2024cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Robustness remains a paramount concern in deep reinforcement learning (DRL), with randomized smoothing emerging as a key technique for enhancing this attribute. However, a notable gap exists in the performance of current smoothed DRL agents, often characterized by significantly low clean rewards and weak robustness. In response to this challenge, our study introduces innovative algorithms aimed at training effective smoothed robust DRL agents. We propose S-DQN and S-PPO, novel approaches that demonstrate remarkable improvements in clean rewards, empirical robustness, and robustness guarantee across standard RL benchmarks. Notably, our S-DQN and S-PPO agents not only significantly outperform existing smoothed agents by an average factor of 2.16× under the strongest attack, but also surpass previous robustly-trained agents by an average factor of 2.13×. This represents a significant leap forward in the field. Furthermore, we introduce Smoothed Attack, which is 1.89× more effective in decreasing the rewards of smoothed agents than existing adversarial attacks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 19 references that are in the map. First posted on arXiv 26 Jun 2024.

Builds on

16 of 19 references.

References · 16

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  2. 2016OpenAI Gymcited by 1,684
  3. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  4. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  5. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
  6. 2017Adversarial Attacks on Neural Network Policiescited by 314
  7. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 235
  8. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 163
  9. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
  10. 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 133
  11. 2020Robust Deep Reinforcement Learning through Adversarial Losscited by 73
  12. 2021Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RLcited by 54
4 more
  1. 2020Detection as Regression: Certified Object Detection by Median Smoothingcited by 47
  2. 2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learningcited by 42
  3. 2021CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothingcited by 41
  4. 2021Policy Smoothing for Provably Robust Reinforcement Learningcited by 39

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025VeriStruct: AI-assisted Automated Verification of Data-Structure Modules in Veruscited by 8
  2. 2025CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximizationcited by 1
  3. 2025Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluationcited by 0
  4. 2025On the Tension Between Optimality and Adversarial Robustness in Policy Optimizationcited by 0