Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed 文章

ArXiv CS.AI2026-05-26NEWSen作者: Minjae Kwon, Josephine Lamp, Lu Feng
查看原文 →
关系图谱

Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed · 相关技术

相关技术

learned dynamics modelstest-time shieldingCPOPPO-Lagreinforcement learning