mlsanityData to 7 Oct 2026

Reinforcement Learning For Survival, A Clinically Motivated Method For Critically Ill Patients

arXiv 2207.08040 ↗First posted 17 Jul 2022cs.LG math.OCcited by 0

Not on the map. Why?

Abstract (arXiv)

There has been considerable interest in leveraging RL and stochastic control methods to learn optimal treatment strategies for critically ill patients, directly from observational data. However, there is significant ambiguity on the control objective and on the best reward choice for the standard RL objective. In this work, we propose a clinically motivated control objective for critically ill patients, for which the value functions have a simple medical interpretation. Further, we present theoretical results and adapt our method to a practical Deep RL algorithm, which can be used alongside any value based Deep RL method. We experiment on a large sepsis cohort and show that our method produces results consistent with clinical knowledge.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 41 references that are in the map. First posted on arXiv 17 Jul 2022.

Builds on

16 of 41 references.

References · 16

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Concrete Problems in AI Safetycited by 1,582
  3. 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,227
  4. 2017A Distributional Perspective on Reinforcement Learningcited by 743
  5. 2019Reinforcement Learning in Healthcare: A Surveycited by 308
  6. 2019Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspectivecited by 107
  7. 2017Deep Reinforcement Learning for Sepsis Treatmentcited by 71
  8. 2021Risk-Averse Offline Reinforcement Learningcited by 65
  9. 2018Evaluating Reinforcement Learning Algorithms in Observational Health Settingscited by 60
  10. 2019Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learningcited by 34
  11. 2020An Empirical Study of Representation Learning for Reinforcement Learning in Healthcarecited by 34
  12. 2021Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatmentcited by 16
4 more
  1. 2019Optimizing Sequential Medical Treatments with Auto-Encoding Heuristic Search in POMDPscited by 12
  2. 2021Enabling risk-aware Reinforcement Learning for medical interventions through uncertainty decompositioncited by 6
  3. 2019Defining Admissible Rewards for High Confidence Policy Evaluationcited by 3
  4. 2022Deep Normed Embeddings for Patient Representationcited by 1

Built on by

Not cited yet.