# Differentially Private Policy Gradient

arXiv: https://arxiv.org/abs/2501.19080 · HTML: https://mlsanity.com/paper/2501.19080/

## 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.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Built on by (most cited first, 3 of 3)

- [KL-regularization Itself is Differentially Private in Bandits and RLHF](https://mlsanity.com/paper/2505.18407/) (2025)
- [On the Sample Complexity of Differentially Private Policy Optimization](https://mlsanity.com/paper/2510.21060/) (2025)
- [Reward-Driven Learning under Prompt-Level Differential Privacy](https://mlsanity.com/paper/2610.07212/) (2026)

## 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.