# Privacy Preserving Reinforcement Learning with One-Sided Feedback

arXiv: https://arxiv.org/abs/2605.18246 · HTML: https://mlsanity.com/paper/2605.18246/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 18 May 2026.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 18 of 18)

- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds](https://mlsanity.com/paper/1605.02065/) (2016)
- [Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithms](https://mlsanity.com/paper/2111.11232/) (2021)
- [Differentially Private Contextual Linear Bandits](https://mlsanity.com/paper/1810.00068/) (2018)
- [Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach](https://mlsanity.com/paper/1705.08422/) (2017)
- [Private Reinforcement Learning with PAC and Regret Guarantees](https://mlsanity.com/paper/2009.09052/) (2020)
- [Learning to Bid Without Knowing your Value](https://mlsanity.com/paper/1711.01333/) (2017)
- [Policy Optimization for Continuous Reinforcement Learning](https://mlsanity.com/paper/2305.18901/) (2023)
- [Multidimensional Binary Search for Contextual Decision-Making](https://mlsanity.com/paper/1611.00829/) (2016)
- [Privacy-Preserving Dynamic Personalized Pricing with Demand Learning](https://mlsanity.com/paper/2009.12920/) (2020)
- [Local Differential Privacy for Regret Minimization in Reinforcement Learning](https://mlsanity.com/paper/2010.07778/) (2020)
- [Offline Reinforcement Learning with Differential Privacy](https://mlsanity.com/paper/2206.00810/) (2022)
- [Near-Optimal Differentially Private Reinforcement Learning](https://mlsanity.com/paper/2212.04680/) (2022)
- [Federated Offline Reinforcement Learning](https://mlsanity.com/paper/2206.05581/) (2022)
- [Online Second Price Auction with Semi-bandit Feedback Under the Non-Stationary Setting](https://mlsanity.com/paper/1911.05949/) (2019)
- [Federated Ensemble-Directed Offline Reinforcement Learning](https://mlsanity.com/paper/2305.03097/) (2023)
- [Stochastic One-Sided Full-Information Bandit](https://mlsanity.com/paper/1906.08656/) (2019)
- [Hiding in Plain Sight: Differential Privacy Noise Exploitation for Evasion-resilient Localized Poisoning Attacks in Multiagent Reinforcement Learning](https://mlsanity.com/paper/2307.00268/) (2023)

## 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.