Compositional Q-learning for electrolyte repletion with imbalanced patient sub-populations.
Aishwarya MandyamAndrew JonesJiayu YaoKrzysztof LaudanskiBarbara E. EngelhardtPublished in: ML4H@NeurIPS (2023)
Keyphrases
- reinforcement learning
- cooperative
- multi agent
- function approximation
- learning algorithm
- state space
- learning rate
- class imbalance
- clinical practice
- heart rate
- medical experts
- stochastic approximation
- medical records
- clinical trials
- clinical data
- optimal policy
- multi agent reinforcement learning
- multi population
- medical treatment
- medical center
- treatment planning
- model free
- medical data
- binary classification problems
- potential field
- reinforcement learning algorithms
- dynamic programming