Policy2026-05-14
On the Sample Complexity of Differentially Private Policy Optimization
Source: Arxiv CS.AI
arXiv:2510.21060v3 Announce Type: replace-cross Abstract: Policy optimization (PO) is a cornerstone of modern reinforcement learning (RL), with diverse applications spanning robotics, healthcare, and large language model training. The increasing deployment of PO in sensitive domains, however,...
arxivpapers