Related papers: Identifying Decision Points for Safe and Interpret…

This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research. We assume that while…

We study estimation and inference using data collected by reinforcement learning (RL) algorithms. These algorithms adaptively experiment by interacting with individual units over multiple stages, updating their strategies based on past…

Medical treatments often involve a sequence of decisions, each informed by previous outcomes. This process closely aligns with reinforcement learning (RL), a framework for optimizing sequential decisions to maximize cumulative rewards under…

In this paper, we investigate dynamic feature selection within multivariate time-series scenario, a common occurrence in clinical prediction monitoring where each feature corresponds to a bio-test result. Many existing feature selection…

Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces. In this paper, we propose LightThinker, a method that enables LLMs to dynamically compress…

Building upon our previous investigations of O1 replication (Part 1: Journey Learning [Qin et al., 2024] and Part 2: Distillation [Huang et al., 2024]), this work explores the potential of inference-time scaling in large language models…

Reasoning large language models (LLMs) excel in complex tasks, which has drawn significant attention to reinforcement learning (RL) for LLMs. However, existing approaches allocate an equal number of rollouts to all questions during the RL…

Timely and personalized treatment decisions are essential across a wide range of healthcare settings where patient responses can vary significantly and evolve over time. Clinical data used to support these treatment decisions are often…

We present a two-step hybrid reinforcement learning (RL) policy that is designed to generate interpretable and robust hierarchical policies on the RL problem with graph-based input. Unlike prior deep reinforcement learning policies…

Many diagnostic errors occur because clinicians cannot easily access relevant information in patient Electronic Health Records (EHRs). In this work we propose a method to use LLMs to identify pieces of evidence in patient EHR data that…

Time series forecasting in real-world applications requires both high predictive accuracy and interpretable uncertainty quantification. Traditional point prediction methods often fail to capture the inherent uncertainty in time series data,…

We propose a reinforcement learning (RL) framework under a broad class of risk objectives, characterized by convex scoring functions. This class covers many common risk measures, such as variance, Expected Shortfall, entropic Value-at-Risk,…

Most practical recommender systems focus on estimating immediate user engagement without considering the long-term effects of recommendations on user behavior. Reinforcement learning (RL) methods offer the potential to optimize…

Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its…

Mediation analysis learns the causal effect transmitted via mediator variables between treatments and outcomes and receives increasing attention in various scientific domains to elucidate causal relations. Most existing works focus on…

Most clinical prediction studies are developed from retrospective cohorts and reported as if all patient information were observed at once. In practice, clinicians face a more consequential question: \emph{when is there already enough…

Randomized controlled trials typically analyze the effectiveness of treatments with the goal of making treatment recommendations for patient subgroups. With the advance of electronic health records, a great variety of data has been…

Hierarchical Reinforcement Learning (HRL) enhances the scalability of decision-making in long-horizon tasks by introducing temporal abstraction through options-policies that span multiple timesteps. Despite its theoretical appeal, the…

Reinforcement learning (RL) is concerned with how intelligence agents take actions in a given environment to maximize the cumulative reward they receive. In healthcare, applying RL algorithms could assist patients in improving their health…

We present a novel methodology for integrating high resolution longitudinal data with the dynamic prediction capabilities of survival models. The aim is two-fold: to improve the predictive power while maintaining interpretability of the…