A Flexible Framework for Incorporating Patient Preferences Into Q-Learning.
Joshua P. ZitovskyLeslie WilsonMichael R. KosorokPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- cooperative
- function approximation
- patient data
- multi agent
- learning algorithm
- user preferences
- state space
- medical records
- medical data
- preference elicitation
- decision making
- clinical practice
- reinforcement learning algorithms
- multi agent reinforcement learning
- soft constraints
- clinical data
- model free
- multi attribute
- optimal policy
- neural network
- learning rate
- clinical trials
- medical experts
- electronic health records
- blood pressure
- multi agent systems
- intensive care
- information systems
- qualitative preferences