Privacy Preserving Reinforcement Learning For Population Processes

Abstract

We consider the problem of privacy protection in Reinforcement Learning (RL) algorithms that operate over population processes, a practical but understudied setting that includes, for example, the control of epidemics in large populations of dynamically interacting individuals. In this setting, the RL algorithm interacts with the population over \(T\) time steps by receiving population-level statistics as state and performing actions which can affect the entire population at each time step. An individual's data can be collected across multiple interactions and their privacy must be protected at all times. We clarify the Bayesian semantics of Differential Privacy (DP) in the presence of correlated data in population processes through a Pufferfish Privacy analysis. We then give a meta algorithm that can take any RL algorithm as input and make it differentially private. This is achieved by taking an approach that uses DP mechanisms to privatize the state and reward signal at each time ste

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyangzhao2024privacy

Related papers

• Offline Reinforcement Learning With Differential Privacy (2022)0.00
• Privacy-preserving Reinforcement Learning Beyond Expectation (2022)0.00
• Near-optimal Differentially Private Reinforcement Learning (2022)0.00
• Privacy-preserving Reinforcement Learning From Human Feedback Via Decoupled Reward Modeling (2026)0.00
• Locally Private Distributed Reinforcement Learning (2020)0.00
• Local Differential Privacy For Regret Minimization In Reinforcement Learning (2020)0.00
• Differentially Private Policy Evaluation (2016)0.00
• Kl-regularization Itself Is Differentially Private In Bandits And RLHF (2025)0.00