mlsanityData to 7 Oct 2026

Randomized Least Squares Value Iteration itself is Joint Differentially Private

arXiv 2606.01952 ↗First posted 1 Jun 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

As reinforcement learning (RL) increasingly applies to sensitive domains, such as health care and recommendation systems, privacy-preserving techniques have become essential to protect users' sensitive information. We investigate privacy-preserving RL under an episodic setting, focusing on algorithms based on randomized exploration, such as Randomized Least Squares Value Iteration (RLSVI). The overall goal is to study how randomized exploration interacts with the injected noise required by privacy mechanisms. In this work, we show a new privacy analysis that characterizes how the noise in RLSVI set for exploration simultaneously provides privacy protection. Specifically, we prove that RLSVI is (varepsilon(δ),δ)-joint differentially private in tabular MDP as is with varepsilon(δ) = frac2AKH2log(2HSA) + 2√frac2AKlog(1/δ)H2log(2HSA), where S and A are the number of states and actions respectively, H is the length of an episode and K is the number of episodes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 37 references that are in the map. First posted on arXiv 1 Jun 2026.

Builds on

27 of 37 references.

References · 27

  1. 2018Exploration by Random Network Distillationcited by 966
  2. 2017Renyi Differential Privacycited by 643
  3. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 555
  4. 2018Is Q-learning Provably Efficient?cited by 485
  5. 2018Randomized Prior Functions for Deep Reinforcement Learningcited by 218
  6. 2017Deep Exploration via Randomized Value Functionscited by 155
  7. 2018Distributed Differential Privacy via Shufflingcited by 115
  8. 2020A Sharp Analysis of Model-based Reinforcement Learning with Self-Playcited by 104
  9. 2019Frequentist Regret Bounds for Randomized Least-Squares Value Iterationcited by 100
  10. 2018Differentially Private Contextual Linear Banditscited by 82
  11. 2019Worst-Case Regret Bounds for Exploration via Randomized Value Functionscited by 57
  12. 2020Locally Differentially Private (Contextual) Bandits Learningcited by 52
15 more
  1. 2020Private Reinforcement Learning with PAC and Regret Guaranteescited by 51
  2. 2015Algorithms for Differentially Private Multi-Armed Banditscited by 44
  3. 2019An Optimal Private Stochastic-MAB Algorithm Based on an Optimal Private Stopping Rulecited by 37
  4. 2022When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Banditscited by 28
  5. 2019Differential Privacy for Multi-armed Bandits: What Is It and What Is Its Cost?cited by 27
  6. 2013Private Matchings and Allocationscited by 23
  7. 2021Differentially Private Regret Minimization in Episodic Markov Decision Processescited by 23
  8. 2020Local Differential Privacy for Regret Minimization in Reinforcement Learningcited by 22
  9. 2020Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iterationcited by 19
  10. 2022Near-Optimal Differentially Private Reinforcement Learningcited by 16
  11. 2021Near-Optimal Randomized Exploration for Tabular Markov Decision Processescited by 14
  12. 2022New Challenges in Reinforcement Learning: A Survey of Security and Privacycited by 7
  13. 2024Thompson Sampling Itself is Differentially Privatecited by 4
  14. 2024Differentially Private Reinforcement Learning with Self-Playcited by 1
  15. 2024Near-Optimal Reinforcement Learning with Shuffle Differential Privacycited by 1

Built on by

Not cited yet.