Bwk work Liu et al. (2022), we do not require a bounded global variation.

The interaction is usually modeled as Markov Decision Processes (MDPs). Research on MDPs can be broadly divided into two lines based on the reward generation mechanism. The first line of work [Jaksch et al., 2010, Azar et al., 2013, 2017, He et al., 2021] considers the

Despite growing interest, much of the existing research has focused on varied unlearning method designs to boost effectiveness and efficiency. However, the inherent relationship between model weights and LLM unlearning has not been extensively examined.

We adopt a multi-armed bandit framework for this process, enhancing prompt selection based on the returns from online trajectories.