Controlling Blood Glucose For Patients With Type 1 DiabetesUsing Deep Reinforcement Learning - The Influence OfChanging The Reward Function.
Miguel Angel Tejedor HernandezJonas Nordhaug MyhrePublished in: NLDL (2020)
Keyphrases
- reward function
- blood glucose
- reinforcement learning
- reinforcement learning algorithms
- blood pressure
- diabetic patients
- markov decision processes
- state space
- short term and long term
- diabetes mellitus
- optimal policy
- inverse reinforcement learning
- partially observable
- markov decision process
- long term
- multiple agents
- transition probabilities
- function approximation
- short term
- transition model
- machine learning
- temporal difference
- medical data
- initially unknown
- dynamic programming
- model free
- learning agent
- statistical model
- probabilistic model
- optimal solution
- multi agent
- learning algorithm