Semi-Markov Offline Reinforcement Learning for Healthcare.
Mehdi FatemiMary WuJeremy PetchWalter NelsonStuart J. ConnollyAlexander BenzAnthony CarnicelliMarzyeh GhassemiPublished in: CHIL (2022)
Keyphrases
- semi markov
- reinforcement learning
- information systems
- function approximation
- state space
- conditional random fields
- learning algorithm
- biomedical informatics
- real time
- learning problems
- dynamic programming
- transfer learning
- function approximators
- health care
- supervised learning
- prior knowledge
- information technology
- transition model
- policy search
- medical information
- health information
- healthcare systems
- clinical trials
- temporal difference
- model free
- optimal control
- optimal policy
- graphical models
- medical images
- multi agent
- machine learning