A constrained RL framework combining impulse and switching control achieves the highest time-in-range and zero simulated hypoglycemia for T1DM insulin dosing.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reinforcement Learning for Target Zone Blood Glucose Control
A constrained RL framework combining impulse and switching control achieves the highest time-in-range and zero simulated hypoglycemia for T1DM insulin dosing.