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.
BMC medical informatics and decision making 13(1):1--19
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.