mlsanityData to 14 Oct 2026

Advancing Safe Mechanical Ventilation Using Offline RL With Hybrid Actions and Clinically Aligned Rewards

arXiv 2506.14375 ↗First posted 17 Jun 2025cs.LG cs.AIcited by 3

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

Abstract (arXiv)

Invasive mechanical ventilation (MV) is a life-sustaining therapy commonly used in the intensive care unit (ICU) for patients with severe and acute conditions. These patients frequently rely on MV for breathing. Given the high risk of death in such cases, optimal MV settings can reduce mortality, minimize ventilator-induced lung injury, shorten ICU stays, and ease the strain on healthcare resources. However, optimizing MV settings remains a complex and error-prone process due to patient-specific variability. While Offline Reinforcement Learning (RL) shows promise for optimizing MV settings, current methods struggle with the hybrid (continuous and discrete) nature of MV settings. Discretizing continuous settings leads to exponential growth in the action space, which limits the number of optimizable settings. Converting the predictions back to continuous can cause a distribution shift, compromising safety and performance. To address this challenge, in the IntelliLung project, we are developing an AI-based approach where we constrain the action space and employ factored action critics. This approach allows us to scale to six optimizable settings compared to 2-3 in previous studies. We adapt SOTA offline RL algorithms to operate directly on hybrid action spaces, avoiding the pitfalls of discretization. We also introduce a clinically grounded reward function based on ventilator-free days and physiological targets. Using multiobjective optimization for reward selection, we show that this leads to a more equitable consideration of all clinically relevant objectives. Notably, we develop a system in close collaboration with healthcare professionals that is aligned with real-world clinical objectives and designed with future deployment in mind.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Safe offline RL, one of 13 directions in Offline RL and imitation learning from data. Builds on 11 of its 35 references that are in the map. First posted on arXiv 17 Jun 2025.

Builds on

11 of 35 references.

References · 11

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  3. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,293
  4. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  5. 2019Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learningcited by 782
  6. 2017Distributional Reinforcement Learning with Quantile Regressioncited by 474
  7. 2019Batch Policy Learning under Constraintscited by 244
  8. 2019Soft Actor-Critic for Discrete Action Settingscited by 174
  9. 2017A Reinforcement Learning Approach to Weaning of Mechanical Ventilation in Intensive Care Unitscited by 50
  10. 2023Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcarecited by 42
  11. 2019Discrete and Continuous Action Representation for Practical RL in Video Gamescited by 39

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Guardian: Decoupling Exploration from Safety in Reinforcement Learningcited by 0
  2. 2026medR: Reward Engineering for Clinical Offline Reinforcement Learning via Tri-Drive Potential Functionscited by 0
  3. 2026Ensuring Safety in Automated Mechanical Ventilation through Offline Reinforcement Learning and Digital Twin Verificationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Methodology for Interpretable Reinforcement Learning for Optimizing Mechanical Ventilation
  2. 2022Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning
  3. 2025Inferring Relative Consequences of Mechanical Ventilation from Observational Data Using Game-Based Comparisons
  4. 2024Distribution-Free Uncertainty Quantification in Mechanical Ventilation Treatment: A Conformal Deep Q-Learning Framework
  5. 2024Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare
  6. 2025Guardian-regularized Safe Offline Reinforcement Learning for Smart Weaning of Mechanical Circulatory Devices
  7. 2026VentAgent: When LLMs Learn to Breathe -- Multi-Objective Arbitration for ARDS Ventilation
  8. 2024Measurement Scheduling for ICU Patients with Offline Reinforcement Learning