Reinforcement Learning (RL) is a class of machine learning algorithms able to make a series of decisions over time, particularly promising for managing chronic or psychiatric diseases.
Benchmarks have driven improvement across machine learning applications, including computer vision, natural language processing, and self-driving cars. We hope they will now push RL progress in healthcare.
Our findings show that while current methods are promising, they are exceedingly data hungry. Current RL agents must train on thousands of simulated treatment episodes for effective use.
We introduce 'Episodes of Care' (EpiCare), the first RL benchmark for health care, which aims to improve decision-making in personalized patient care.
Collection
[
|
...
]