mlsanityData to 7 Oct 2026

Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI

arXiv 2508.21101 ↗First posted 28 Aug 2025cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning (RL) marks a fundamental shift in how artificial intelligence is applied in healthcare. Instead of merely predicting outcomes, RL actively decides interventions with long term goals. Unlike traditional models that operate on fixed associations, RL systems learn through trial, feedback, and long-term reward optimization, introducing transformative possibilities and new risks. From an information fusion lens, healthcare RL typically integrates multi-source signals such as vitals, labs clinical notes, imaging and device telemetry using temporal and decision-level mechanisms. These systems can operate within centralized, federated, or edge architectures to meet real-time clinical constraints, and naturally span data, features and decision fusion levels. This survey explore RL's rise in healthcare as more than a set of tools, rather a shift toward agentive intelligence in clinical environments. We first structure the landscape of RL techniques including model-based and model-free methods, offline and batch-constrained approaches, and emerging strategies for reward specification and uncertainty calibration through the lens of healthcare constraints. We then comprehensively analyze RL applications spanning critical care, chronic disease, mental health, diagnostics, and robotic assistance, identifying their trends, gaps, and translational bottlenecks. In contrast to prior reviews, we critically analyze RL's ethical, deployment, and reward design challenges, and synthesize lessons for safe, human-aligned policy learning. This paper serves as both a a technical roadmap and a critical reflection of RL's emerging transformative role in healthcare AI not as prediction machinery, but as agentive clinical intelligence.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 63 of its 192 references that are in the map. First posted on arXiv 28 Aug 2025.

Builds on

63 of 192 references.

References · 63

  1. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  2. 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,227
  3. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  4. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  5. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  6. 2020MOPO: Model-based Offline Policy Optimizationcited by 630
  7. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 457
  8. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  9. 2015Doubly Robust Off-policy Value Evaluation for Reinforcement Learningcited by 337
  10. 2019Reinforcement Learning in Healthcare: A Surveycited by 308
  11. 2016Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivationcited by 282
  12. 2018Scalable and accurate deep learning for electronic health recordscited by 275
38 more
  1. 2016Safe and Efficient Off-Policy Reinforcement Learningcited by 260
  2. 2024Reinforcement learningcited by 236
  3. 2023A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethicscited by 162
  4. 2015Learning Continuous Control Policies by Stochastic Value Gradientscited by 156
  5. 2017Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysiscited by 145
  6. 2015Variational Information Maximisation for Intrinsically Motivated Reinforcement Learningcited by 142
  7. 2018More Robust Doubly Robust Off-policy Evaluationcited by 141
  8. 2019What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Usecited by 134
  9. 2018Deep Variational Reinforcement Learning for POMDPscited by 122
  10. 2024SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learningcited by 113
  11. 2018Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendationcited by 101
  12. 2024RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMscited by 89
  13. 2020Learning from Suboptimal Demonstration via Self-Supervised Reward Regressioncited by 84
  14. 2017Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approachcited by 68
  15. 2021Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settingscited by 68
  16. 2017A Reinforcement Learning Approach to Weaning of Mechanical Ventilation in Intensive Care Unitscited by 50
  17. 2023Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcarecited by 41
  18. 2020POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learningcited by 36
  19. 2019Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learningcited by 34
  20. 2020Meta-AAD: Active Anomaly Detection with Deep Reinforcement Learningcited by 34
  21. 2020An Empirical Study of Representation Learning for Reinforcement Learning in Healthcarecited by 34
  22. 2025Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Modelscited by 22
  23. 2023Deep Reinforcement Learning for Cost-Effective Medical Diagnosiscited by 20
  24. 2022Semi-Markov Offline Reinforcement Learning for Healthcarecited by 18
  25. 2022Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learningcited by 16
  26. 2022Federated Offline Reinforcement Learningcited by 13
  27. 2025A Survey on Explainable Deep Reinforcement Learningcited by 12
  28. 2021Reinforcement Learning based Disease Progression Model for Alzheimer's Diseasecited by 10
  29. 2023Situation-Dependent Causal Influence-Based Cooperative Multi-agent Reinforcement Learningcited by 10
  30. 2024Development of a Large Language Model-based Multi-Agent Clinical Decision Support System for Korean Triage and Acuity Scale (KTAS)-Based Triage and Treatment Planning in Emergency Departmentscited by 10
  31. 2021Edge Intelligence for Empowering IoT-based Healthcare Systemscited by 8
  32. 2021Challenges for Reinforcement Learning in Healthcarecited by 7
  33. 2018The Actor Search Tree Critic (ASTC) for Off-Policy POMDP Learning in Medical Decision Makingcited by 6
  34. 2023Off-Policy Evaluation for Human Feedbackcited by 6
  35. 2024From Decision to Action in Surgical Autonomy: Multi-Modal Large Language Models for Robot-Assisted Blood Suctioncited by 6
  36. 2025Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimationcited by 6
  37. 2022Towards Trustworthy Automatic Diagnosis Systems by Emulating Doctors' Reasoning with Deep Reinforcement Learningcited by 5
  38. 2023Model Based Reinforcement Learning for Personalized Heparin Dosingcited by 5

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generationcited by 0
  2. 2026Neurosymbolic Alignment for Physiologically-Safe Clinical Language Modelscited by 0
  3. 2026The Evidence Ladder for Reinforcement Learning in Healthcare: From Retrospective Policies to Trusted Interventionscited by 0