A PPO reinforcement learning method using atomic actions, partially-shared policies, and queueing-informed value approximation scales inpatient overflow optimization to hospital systems with 20 patient classes and wards, matching or beating benchmarks where prior methods fail.
Emergency Medicine Journal 39(3):168--173
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Inpatient Overflow Management with Proximal Policy Optimization
A PPO reinforcement learning method using atomic actions, partially-shared policies, and queueing-informed value approximation scales inpatient overflow optimization to hospital systems with 20 patient classes and wards, matching or beating benchmarks where prior methods fail.