mlsanityData to 7 Oct 2026

Identifying Decision Points for Safe and Interpretable Reinforcement Learning in Hypotension Treatment

arXiv 2101.03309 ↗First posted 9 Jan 2021cs.LGcited by 4

On the map: Offline RL and imitation learning from data → Safe offline RL

Abstract (arXiv)

Many batch RL health applications first discretize time into fixed intervals. However, this discretization both loses resolution and forces a policy computation at each (potentially fine) interval. In this work, we develop a novel framework to compress continuous trajectories into a few, interpretable decision points --places where the batch data support multiple alternatives. We apply our approach to create recommendations from a cohort of hypotensive patients dataset. Our reduced state space results in faster planning and allows easy inspection by a clinical expert.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Safe offline RL, one of 13 directions in Offline RL and imitation learning from data. Builds on 2 of its 11 references that are in the map. First posted on arXiv 9 Jan 2021.

Builds on

2 of 11 references.

References · 2

  1. 2020POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learningcited by 36
  2. 2020Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEscited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 1; 2024: 0; 2025: 1; 2026: 1.

4 papers.

  1. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  2. 2023Bayesian Inverse Transition Learning for Offline Settingscited by 0
  3. 2025Learning optimal treatment strategies for intraoperative hypotension using deep reinforcement learningcited by 0
  4. 2026Insulin4RL: Real-Time Insulin Management in the Intensive Care Unit for Offline Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning to Compress Time-to-Control: A Reinforcement Learning Framework for Chronic Disease Management
  2. 2025Realistic CDSS Drug Dosing with End-to-end Recurrent Q-learning for Dual Vasopressor Control
  3. 2022Predicting the Need for Blood Transfusion in Intensive Care Units with Reinforcement Learning
  4. 2025Exploring Time-Step Size in Reinforcement Learning for Sepsis Treatment
  5. 2024Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare
  6. 2024Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment
  7. 2023Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning
  8. 2022Semi-Markov Offline Reinforcement Learning for Healthcare