# Local Differential Privacy for Regret Minimization in Reinforcement Learning

arXiv: https://arxiv.org/abs/2010.07778 · HTML: https://mlsanity.com/paper/2010.07778/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2020.

## Built on by (most cited first, 22 of 22)

- [Offline Reinforcement Learning with Differential Privacy](https://mlsanity.com/paper/2206.00810/) (2022)
- [Reinforcement Unlearning](https://mlsanity.com/paper/2312.15910/) (2023)
- [Near-Optimal Differentially Private Reinforcement Learning](https://mlsanity.com/paper/2212.04680/) (2022)
- [Distributed Differential Privacy in Multi-Armed Bandits](https://mlsanity.com/paper/2206.05772/) (2022)
- [Doubly Fair Dynamic Pricing](https://mlsanity.com/paper/2209.11837/) (2022)
- [adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential-Decision Making Human-in-the-Loop Systems](https://mlsanity.com/paper/2303.04257/) (2023)
- [Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards](https://mlsanity.com/paper/2306.01121/) (2023)
- [Privacy Risks in Reinforcement Learning for Household Robots](https://mlsanity.com/paper/2306.09273/) (2023)
- [Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning](https://mlsanity.com/paper/2505.20621/) (2025)
- [SquarechiPO: Differentially Private and Robust chi2-Preference Optimization in Offline Direct Alignment](https://mlsanity.com/paper/2505.21395/) (2025)
- [Differential Privacy in Cooperative Multiagent Planning](https://mlsanity.com/paper/2301.08811/) (2023)
- [Concurrent Shuffle Differential Privacy Under Continual Observation](https://mlsanity.com/paper/2301.12535/) (2023)
- [Privacy-Preserving Reinforcement Learning Beyond Expectation](https://mlsanity.com/paper/2203.10165/) (2022)
- [Locally Differentially Private Distributed Online Learning with Guaranteed Optimality](https://mlsanity.com/paper/2306.14094/) (2023)
- [DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2308.09902/) (2023)
- [Differentially Private Deep Model-Based Reinforcement Learning](https://mlsanity.com/paper/2402.05525/) (2024)
- [Differentially Private Reinforcement Learning with Self-Play](https://mlsanity.com/paper/2404.07559/) (2024)
- [Privacy Preserving Reinforcement Learning for Population Processes](https://mlsanity.com/paper/2406.17649/) (2024)
- [Near-Optimal Reinforcement Learning with Shuffle Differential Privacy](https://mlsanity.com/paper/2411.11647/) (2024)
- [Private Selection with Heterogeneous Sensitivities](https://mlsanity.com/paper/2501.05309/) (2025)
- [Privacy Preserving Reinforcement Learning with One-Sided Feedback](https://mlsanity.com/paper/2605.18246/) (2026)
- [Randomized Least Squares Value Iteration itself is Joint Differentially Private](https://mlsanity.com/paper/2606.01952/) (2026)

## Abstract (arXiv)

Reinforcement learning algorithms are widely used in domains where it is desirable to provide a personalized service. In these domains it is common that user data contains sensitive information that needs to be protected from third parties. Motivated by this, we study privacy in the context of finite-horizon Markov Decision Processes (MDPs) by requiring information to be obfuscated on the user side. We formulate this notion of privacy for RL by leveraging the local differential privacy (LDP) framework. We establish a lower bound for regret minimization in finite-horizon MDPs with LDP guarantees which shows that guaranteeing privacy has a multiplicative effect on the regret. This result shows that while LDP is an appealing notion of privacy, it makes the learning problem significantly more complex. Finally, we present an optimistic algorithm that simultaneously satisfies varepsilon-LDP requirements, and achieves √K/varepsilon regret in any finite-horizon MDP after K episodes, matching the lower bound dependency on the number of episodes K.