An Empirical Study Of Representation Learning For Reinforcement Learning In Healthcare

Abstract

Reinforcement Learning (RL) has recently been applied to sequential estimation and prediction problems identifying and developing hypothetical treatment strategies for septic patients, with a particular focus on offline learning with observational data. In practice, successful RL relies on informative latent states derived from sequential observations to develop optimal treatment strategies. To date, how best to construct such states in a healthcare setting is an open question. In this paper, we perform an empirical study of several information encoding architectures using data from septic patients in the MIMIC-III dataset to form representations of a patient state. We evaluate the impact of representation dimension, correlations with established acuity scores, and the treatment policies derived from them. We find that sequentially formed state representations facilitate effective policy learning in batch settings, validating a more thoughtful approach to representation learning that r

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykillian2020an

Related papers

• Stable CDE Autoencoders With Acuity Regularization For Offline Reinforcement Learning In Sepsis Treatment (2025)0.00
• Missingness As Stability: Understanding The Structure Of Missingness In Longitudinal EHR Data And Its Impact On Reinforcement Learning In Healthcare (2019)0.00
• Reinforcement Learning In Dynamic Treatment Regimes Needs Critical Reexamination (2024)2.35
• Semi-supervised Off Policy Reinforcement Learning (2020)0.00
• Leveraging Factored Action Spaces For Efficient Offline Reinforcement Learning In Healthcare (2023)2.26
• Clinician-in-the-loop Decision Making: Reinforcement Learning With Near-optimal Set-valued Policies (2020)0.00
• Sample-efficient Reinforcement Learning Via Counterfactual-based Data Augmentation (2020)0.00
• Learning Temporally-consistent Representations For Data-efficient Reinforcement Learning (2021)0.00