Aiming at promoting the safe real-world deployment of Reinforcement Learning (RL), research on safe RL has made significant progress in recent years.However, most existing works in the literature still focus on the online setting where risky violations of the safety budget are likely to be incurred during training.Besides, in many real-world applications, the learned policy is required to respond to different or dynamically changing safety budgets in real time.In this paper, we target at the abo…