Off-policy learning (OPL) aims at finding improved policies from logged bandit data, often by
minimizing the inverse propensity scoring (IPS) estimator of the risk. In this work, we …

A contextual bandit is a popular framework for online learning to act under uncertainty. In
practice, the number of actions is huge and their expected rewards are correlated. In this …

Many practical problems involve solving similar tasks. In recommender systems, the tasks
can be users with similar preferences; in search engines, the tasks can be items with similar …

The recent advances of conversational recommendations provide a promising way to
efficiently elicit users' preferences via conversational interactions. To achieve this, the …

Hierarchical reinforcement learning (HRL) exhibits remarkable potential in addressing large-
scale and long-horizon complex tasks. However, a fundamental challenge, which arises …

In this work, we initiate the idea of using denoising diffusion models to learn priors for online
decision making problems. Our special focus is on the meta-learning for bandit framework …

We study the problem of Bayesian fixed-budget best-arm identification (BAI) in structured
bandits. We propose an algorithm that uses fixed allocations based on the prior information …

Efficient exploration is a key challenge in contextual bandits due to the potentially large size
of their action space, where uninformed exploration can result in computational and …

We study a novel variant of a contextual bandit problem with multi-dimensional reward
feedback formulated as a mixed-effects model, where the correlations between multiple …

Most bandit algorithms assume that the reward variances or their upper bounds are known,
and that they are the same for all arms. This naturally leads to suboptimal performance and …