SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration 事件

SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration arXiv:2606.10228v1 Announce Type: cross Abstract: Safe exploration is a prerequisite for deploying reinforcement learning (RL) agents in safety-critical domains. In this paper, we approach safe exploration through the lens of epistemic uncertainty, where the actor's sensitivity to parameter perturbations serves as a practical proxy for regions of high uncertainty. We propose Sharpness-Aware Policy Optimization (SHAPO), a sharpness-