---
title: "Privacy-Preserving Reinforcement Learning with One-Sided Feedback"
authors:
  - "Lin Cong"
  - "Guangyan Gan"
  - "Hanzhang Qin"
  - "Zhenzhen Yan"
doi: "10.24963/ijcai.2026/58"
url: "https://ijcai.org/proceedings/2026/58"
pdf: "https://ijcai.org/proceedings/2026/0058.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "509-517"
track: "Main Track"
keywords:
  - "Multidisciplinary Topics and Applications: Other"
  - "AI Ethics, Trust, Fairnes: Other"
  - "Machine Learning: Reinforcement learning"
---

# Privacy-Preserving Reinforcement Learning with One-Sided Feedback

Lin Cong, Guangyan Gan, Hanzhang Qin, Zhenzhen Yan

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 509-517. DOI: [10.24963/ijcai.2026/58](https://doi.org/10.24963/ijcai.2026/58)

## Abstract

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 of O~((1+E_rho) H^3 alpha^-2), which matches the known lower bounds for non-private RL. Here, E_rho denotes the privacy parameter, H is the time horizon, and alpha is 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.