However, it is not directly applicable to Reinforcement Learning (RL) due to the inaccessibility of explicit action-value functions.

Existing regularization methods merely minimize the norms of embeddings to regularize the model, leading to suboptimal performance.

The various clustering problems that have been studied intensively include, e.g., the

From the learning theory perspective, the learning guarantees of SCO algorithms with known derivatives have been studied in the literature.

We further design an expert-wise training strategy to alleviate the impact of unhelpful demonstrations when optimizing the retriever model.

While some adaptive experimental strategies exist for the identification of the single best subgroup, they commonly do not enable the identification of the best set of subgroups.