mlsanityData to 7 Oct 2026

adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential-Decision Making Human-in-the-Loop Systems

arXiv 2303.04257 ↗First posted 7 Mar 2023cs.LG cs.AI cs.CRcited by 6

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning (RL) presents numerous benefits compared to rule-based approaches in various applications. Privacy concerns have grown with the widespread use of RL trained with privacy-sensitive data in IoT devices, especially for human-in-the-loop systems. On the one hand, RL methods enhance the user experience by trying to adapt to the highly dynamic nature of humans. On the other hand, trained policies can leak the user's private information. Recent attention has been drawn to designing privacy-aware RL algorithms while maintaining an acceptable system utility. A central challenge in designing privacy-aware RL, especially for human-in-the-loop systems, is that humans have intrinsic variability and their preferences and behavior evolve. The effect of one privacy leak mitigation can be different for the same human or across different humans over time. Hence, we can not design one fixed model for privacy-aware RL that fits all. To that end, we propose adaPARL, an adaptive approach for privacy-aware RL, especially for human-in-the-loop IoT systems. adaPARL provides a personalized privacy-utility trade-off depending on human behavior and preference. We validate the proposed adaPARL on two IoT applications, namely (i) Human-in-the-Loop Smart Home and (ii) Human-in-the-Loop Virtual Reality (VR) Smart Classroom. Results obtained on these two applications validate the generality of adaPARL and its ability to provide a personalized privacy-utility trade-off. On average, for the first application, adaPARL improves the utility by 57% over the baseline and by 43% over randomization. adaPARL also reduces the privacy leak by 23% on average. For the second application, adaPARL decreases the privacy leak to 44% before the utility drops by 15%.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 12 of its 58 references that are in the map. First posted on arXiv 7 Mar 2023.

Builds on

12 of 58 references.

References · 12

  1. 2016Cooperative Inverse Reinforcement Learningcited by 298
  2. 2019Privacy-preserving Q-Learning with Functional Noise in Continuous State Spacescited by 29
  3. 2019How You Act Tells a Lot: Privacy-Leakage Attack on Deep Reinforcement Learningcited by 29
  4. 2020Local Differential Privacy for Regret Minimization in Reinforcement Learningcited by 22
  5. 2021Privacy Amplification via Shuffling for Linear Contextual Banditscited by 17
  6. 2021FaiR-IoT: Fairness-aware Human-in-the-Loop Reinforcement Learning for Harnessing Human Variability in Personalized IoTcited by 15
  7. 2021Deceptive Reinforcement Learning for Privacy-Preserving Planningcited by 14
  8. 2020Privacy-Aware Time-Series Data Sharing with Deep Reinforcement Learningcited by 11
  9. 2021Two steps to risk sensitivitycited by 8
  10. 2019Privacy-Preserving Banditscited by 6
  11. 2020Privacy-Constrained Policies via Mutual Information Regularized Policy Gradientscited by 6
  12. 2022VindiCo: Privacy Safeguard Against Adaptation Based Spyware in Human-in-the-Loop IoTcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 1; 2025: 1; 2026: 1.

6 papers.

  1. 2023Privacy Risks in Reinforcement Learning for Household Robotscited by 4
  2. 2025FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Riskcited by 2
  3. 2024PEARL: Structural Privacy-Utility Control in Human-Centric CPS via Personalized Early-Exit Deep Reinforcement Learningcited by 1
  4. 2023FAIRO: Fairness-aware Adaptation in Sequential-Decision Making for Human-in-the-Loop Systemscited by 0
  5. 2023FinA: Fairness of Adverse Effects in Decision-Making of Human-Cyber-Physical-Systemcited by 0
  6. 2026Position: Embodied AI Requires a Privacy-Utility Trade-offcited by 0