Model-Based Reinforcement Learning for Sepsis Treatment

Abstract

Sepsis is a dangerous condition that is a leading cause of patient mortality. Treating sepsis is highly challenging, because individual patients respond very differently to medical interventions and there is no universally agreed-upon treatment for sepsis. In this work, we explore the use of continuous state-space model-based reinforcement learning (RL) to discover high-quality treatment policies for sepsis patients. Our quantitative evaluation reveals that by blending the treatment strategy discovered with RL with what clinicians follow, we can obtain improved policies, potentially allowing for better medical treatment for sepsis.

arXiv commentMachine Learning for Health (ML4H) Workshop at NeurIPS 2018 arXiv:1811.07216

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Evaluating Reinforcement Learning Algorithms in Observational Health Settings
• Deep Reinforcement Learning for Sepsis Treatment
• Behaviour Policy Estimation in Off-Policy Policy Evaluation: Calibration Matters
• Representation Balancing MDPs for Off-Policy Policy Evaluation

Cited by in corpus (6)

• Reinforcement Learning in Healthcare: A Survey
• MGP-AttTCN: An Interpretable Machine Learning Model for the Prediction of Sepsis
• An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare
• Feature-Based Interpretable Reinforcement Learning based on State-Transition Models
• Challenges for Reinforcement Learning in Healthcare
• Models, Pixels, and Rewards: Evaluating Design Trade-offs in Visual Model-Based Reinforcement Learning