Offline Reward Perturbation Boosts Distributional Shift in Online RL.Zishun Yu,Siteng Kang,Xinhua ZhangUAI 2024(2024)引用 0|浏览8关键词data poisoning attack,machine learning safety,offline to online reinforcement learningAI 理解论文溯源树样例生成溯源树,研究论文发展脉络Chat Paper正在生成论文摘要