activity
20192025
most citedModel Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings

23 citations · 38 across the 11 of their papers we have counts for

collaborators
Showing cs.LGShow all

12 papers · 1 filter

cs.LG2025

Exploring Time-Step Size in Reinforcement Learning for Sepsis Treatment

Yingchuan Sun, Shengpu Tang

Existing studies on reinforcement learning (RL) for sepsis management have mostly followed an established problem setup, in which patient data are aggregated into 4-hour time steps…

cs.LG2025

Reflections from Research Roundtables at the Conference on Health, Inference, and Learning (CHIL) 2025

Emily Alsentzer, Marie-Laure Charpignon, Bill Chen +90

The 6th Annual Conference on Health, Inference, and Learning (CHIL 2025), hosted by the Association for Health Learning and Inference (AHLI), was held in person on June 25-27, 2025…

cs.LG2025

Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning

Ziyan Wang, Zheng Wang, Xingwei Qu +5

Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs). Yet on-policy algorithms such as Group Relative Policy Optimization (GRPO) of…

cs.LG2024

CANDOR: Counterfactual ANnotated DOubly Robust Off-Policy Evaluation

Aishwarya Mandyam, Shengpu Tang, Jiayu Yao +2

Off-policy evaluation (OPE) is critical for applying contextual bandit algorithms to high-stakes decision-making settings such as healthcare, where new treatment policies must be e…

cs.LG2023

Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation

Shengpu Tang, Jenna Wiens

In applying reinforcement learning (RL) to high-stakes domains, quantitative and qualitative evaluation using observational data can help practitioners understand the generalizatio…

cs.LG2023

Leveraging Factored Action Spaces for Off-Policy Evaluation

Aaman Rebello, Shengpu Tang, Jenna Wiens +1

Off-policy evaluation (OPE) aims to estimate the benefit of following a counterfactual sequence of actions, given data collected from executed sequences. However, existing OPE esti…