Private Reinforcement Learning

Private reinforcement learning (RL) focuses on developing RL algorithms that protect the privacy of sensitive data used during training, primarily using differential privacy mechanisms. Current research emphasizes extending these techniques to various RL settings, including multi-agent systems, offline learning scenarios, and those with heavy-tailed reward distributions, often employing model-based methods or adapting algorithms like Q-learning and value iteration. This field is crucial for enabling the safe and ethical deployment of RL in applications involving personal or sensitive information, such as personalized healthcare and mobile edge computing, where privacy is paramount.

Papers

November 18, 2024

June 25, 2024

Privacy Preserving Reinforcement Learning for Population Processes
Samuel Yang-Zhao, Kee Siong Ng
Reinforcement Learning Differential Privacy Population Dynamic Private Reinforcement Learning Pufferfish Privacy

April 11, 2024

Differentially Private Reinforcement Learning with Self-Play
Dan Qiao, Yu-Xiang Wang
Multi Agent Reinforcement Learning Differential Privacy Self Play Episodic Markov Decision Process Multi Agent RL Single Agent RL Private Reinforcement Learning

February 8, 2024

Differentially Private Deep Model-Based Reinforcement Learning
Alexandre Rio, Merwan Barlier, Igor Colin, Albert Thomas
Offline Reinforcement Learning Differential Privacy Guarantee Private Model RL Agent Model Based Policy Private Reinforcement Learning

June 1, 2023

Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards
Yulian Wu, Xingyu Zhou, Sayak Ray Chowdhury, Di Wang
Markov Decision Process Heavy Tailed Heavy Tailed Reward Private Reinforcement Learning Heavy Tailed Policy

February 9, 2023

Differentially Private Deep Q-Learning for Pattern Privacy Preservation in MEC Offloading
Shuying Gan, Marie Siew, Chao Xu, Tony Q. S. Quek
Privacy Preserving Mobile Edge Computing Task Offloading Private Reinforcement Learning

December 9, 2022

Near-Optimal Differentially Private Reinforcement Learning
Dan Qiao, Yu-Xiang Wang
Private Learning DP Algorithm Private Reinforcement Learning

January 18, 2022

Differentially Private Reinforcement Learning with Linear Function Approximation
Xingyu Zhou
Positive Reinforcement Linear Function Approximation Finite Horizon Linear Mixture Markov Decision Process Private Reinforcement Learning