mlsanityData to 14 Oct 2026

Differentially Private Policy Gradient

arXiv 2501.19080 ↗First posted 31 Jan 2025cs.LGcited by 3

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Motivated by the increasing deployment of reinforcement learning in the real world, involving a large consumption of personal data, we introduce a differentially private (DP) policy gradient algorithm. We show that, in this setting, the introduction of Differential Privacy can be reduced to the computation of appropriate trust regions, thus avoiding the sacrifice of theoretical properties of the DP-less methods. Therefore, we show that it is possible to find the right trade-off between privacy noise and trust-region size to obtain a performant differentially private policy gradient algorithm. We then outline its performance empirically on various benchmarks. Our results and the complexity of the tasks addressed represent a significant improvement over existing DP algorithms in online RL.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. First posted on arXiv 31 Jan 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025KL-regularization Itself is Differentially Private in Bandits and RLHFcited by 3
  2. 2025On the Sample Complexity of Differentially Private Policy Optimizationcited by 3
  3. 2026Reward-Driven Learning under Prompt-Level Differential Privacycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modeling
  2. 2022Offline Reinforcement Learning with Differential Privacy
  3. 2024Near-Optimal Reinforcement Learning with Shuffle Differential Privacy
  4. 2024Preserving Expert-Level Privacy in Offline Reinforcement Learning
  5. 2024Differentially Private Reinforcement Learning with Self-Play
  6. 2024Privacy Preserving Reinforcement Learning for Population Processes
  7. 2025Efficient Differentially Private Fine-Tuning of LLMs via Reinforcement Learning
  8. 2026Privacy Preserving Reinforcement Learning with One-Sided Feedback