Privacy-Preserving Reinforcement Learning with One-Sided Feedback

Lin Cong; Guangyan Gan; Hanzhang Qin; Zhenzhen Yan

IJCAI 20260 citations

Privacy-Preserving Reinforcement Learning with One-Sided Feedback

Lin Cong, Guangyan Gan, Hanzhang Qin, Zhenzhen Yan

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.

AI Ethics, Trust, Fairnes: OtherMachine Learning: Reinforcement learningMultidisciplinary Topics and Applications: Other

BibTeX

@inproceedings{ijcai2026_privacypreservin,
  title = {Privacy-Preserving Reinforcement Learning with One-Sided Feedback},
  author = {Lin Cong and Guangyan Gan and Hanzhang Qin and Zhenzhen Yan},
  booktitle = {IJCAI 2026},
  year = {2026}
}