mlsanityData to 14 Oct 2026

Local Differential Privacy for Regret Minimization in Reinforcement Learning

arXiv 2010.07778 ↗First posted 15 Oct 2020cs.LGcited by 22

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 8; 2024: 4; 2025: 3; 2026: 2.

22 papers.

Sort:

By area:

  1. 2022Offline Reinforcement Learning with Differential Privacycited by 20
  2. 2023Reinforcement Unlearningcited by 17
  3. 2022Near-Optimal Differentially Private Reinforcement Learningcited by 16
  4. 2022Distributed Differential Privacy in Multi-Armed Banditscited by 14
  5. 2022Doubly Fair Dynamic Pricingcited by 8
  6. 2023adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential-Decision Making Human-in-the-Loop Systemscited by 6
  7. 2023Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewardscited by 4
  8. 2023Privacy Risks in Reinforcement Learning for Household Robotscited by 4
  9. 2025Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learningcited by 3
  10. 2025SquarechiPO: Differentially Private and Robust chi2-Preference Optimization in Offline Direct Alignmentcited by 3
  11. 2023Differential Privacy in Cooperative Multiagent Planningcited by 2
  12. 2023Concurrent Shuffle Differential Privacy Under Continual Observationcited by 2
10 more
  1. 2022Privacy-Preserving Reinforcement Learning Beyond Expectationcited by 1
  2. 2023Locally Differentially Private Distributed Online Learning with Guaranteed Optimalitycited by 1
  3. 2023DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learningcited by 1
  4. 2024Differentially Private Deep Model-Based Reinforcement Learningcited by 1
  5. 2024Differentially Private Reinforcement Learning with Self-Playcited by 1
  6. 2024Privacy Preserving Reinforcement Learning for Population Processescited by 1
  7. 2024Near-Optimal Reinforcement Learning with Shuffle Differential Privacycited by 1
  8. 2025Private Selection with Heterogeneous Sensitivitiescited by 0
  9. 2026Privacy Preserving Reinforcement Learning with One-Sided Feedbackcited by 0
  10. 2026Randomized Least Squares Value Iteration itself is Joint Differentially Privatecited by 0