AI RESEARCH
Towards Differentially Private Reinforcement Learning with General Function Approximation
arXiv CS.AI
•
ArXi:2605.07049v1 Announce Type: cross We present the first theoretical guarantees for differentially private online reinforcement learning (RL) with general function approximation, extending beyond prior work restricted to tabular and linear settings. Our approach combines a batched policy update scheme with the exponential mechanism, together with a novel regret analysis.