mlsanityData to 7 Oct 2026

Privacy Preserving Reinforcement Learning with One-Sided Feedback

arXiv 2605.18246 ↗First posted 18 May 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We study reinforcement learning (RL) in multi-dimensional continuous state and action spaces with one-sided feedback, where the agent receives partial observations of the state and obtains reward information for only a subset of the state-action space at each time step. This setting introduces substantial challenges in both learning efficiency and privacy preservation. To address these challenges, we propose POOL, a novel privacy-preserving RL algorithm. We conduct a comprehensive theoretical analysis of POOL, deriving a sample complexity bound that matches the known lower bounds for non-private RL. Here, E_rho denotes the privacy parameter, H is the time horizon, and alpha is the optimality-gap parameter. Our findings show that it is possible to enforce strong privacy guarantees while maintaining high learning efficiency, marking a significant step toward practical, privacy-aware RL in multi-dimensional environments with one-sided feedback.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 34 references that are in the map. First posted on arXiv 18 May 2026.

Builds on

18 of 34 references.

References · 18

  1. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  2. 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 339
  3. 2018Differentially Private Contextual Linear Banditscited by 82
  4. 2021Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithmscited by 76
  5. 2017Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approachcited by 68
  6. 2020Private Reinforcement Learning with PAC and Regret Guaranteescited by 51
  7. 2017Learning to Bid Without Knowing your Valuecited by 34
  8. 2023Policy Optimization for Continuous Reinforcement Learningcited by 30
  9. 2016Multidimensional Binary Search for Contextual Decision-Makingcited by 27
  10. 2020Privacy-Preserving Dynamic Personalized Pricing with Demand Learningcited by 23
  11. 2020Local Differential Privacy for Regret Minimization in Reinforcement Learningcited by 22
  12. 2022Offline Reinforcement Learning with Differential Privacycited by 19
6 more
  1. 2022Near-Optimal Differentially Private Reinforcement Learningcited by 16
  2. 2022Federated Offline Reinforcement Learningcited by 13
  3. 2019Online Second Price Auction with Semi-bandit Feedback Under the Non-Stationary Settingcited by 6
  4. 2023Federated Ensemble-Directed Offline Reinforcement Learningcited by 6
  5. 2019Stochastic One-Sided Full-Information Banditcited by 5
  6. 2023Hiding in Plain Sight: Differential Privacy Noise Exploitation for Evasion-resilient Localized Poisoning Attacks in Multiagent Reinforcement Learningcited by 2

Built on by

Not cited yet.