Proceedings

Privacy-Preserving Reinforcement Learning with One-Sided Feedback

Lin Cong, Guangyan Gan, Hanzhang Qin, Zhenzhen Yan

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 509-517.

https://doi.org/10.24963/ijcai.2026/58

Keywords

  • Multidisciplinary Topics and Applications: Other
  • AI Ethics, Trust, Fairnes: Other
  • Machine Learning: Reinforcement learning

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.

Lin Cong, Guangyan Gan, Hanzhang Qin, and Zhenzhen Yan. 2026. Privacy-Preserving Reinforcement Learning with One-Sided Feedback. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 509–517. https://doi.org/10.24963/ijcai.2026/58
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards