Importance sampling (IS) is a popular technique in off-policy evaluation, which re-weights
the return of trajectories in the replay buffer to boost sample efficiency. However, training …

Sepsis is the main cause of mortality in intensive care units (ICUs), but the optimal treatment
strategy still remains unclear. Managing the treatment of sepsis is challenging because …

We consider the problem of off-policy evaluation (OPE) in reinforcement learning (RL),
where the goal is to estimate the performance of an evaluation policy, pie, using a fixed …

Sepsis is the third leading cause of death worldwide. Antibiotics are an important component
in the treatment of sepsis. The use of antibiotics is currently facing the challenge of …

Recently, deep learning has been successfully applied to a variety of networking problems.
A fundamental challenge is that when the operational environment for a learning …

Aim To review and appraise the quality of studies that present models for causal inference of
time-varying treatment effects in the adult intensive care unit (ICU) and give …

Many sequential decision-making systems leverage data collected using prior policies to
propose a new policy. For critical applications, it is important that high-confidence …

We study the properties of off-policy reinforcement learning algorithms when applied to a
real world clinical scenario. Towards this end, we evaluate standard off-policy training …

Learning a high-quality transition model is of great importance for sequential decision-
making tasks, especially in offline settings. Nevertheless, the complex behaviors of transition …

In reinforcement learning, it is crucial to have an accurate environment dynamics model to
evaluate different policies' value in downstream tasks like offline policy optimization and …