arXiv · Machine Learning· Himadri S. Pandey, Mark V. Mai, Naveen Muthu, Kai Wang, Gian-Gabriel P. Garcia·· 8 小时前AI 评分54
MILOP 神经索引策略优化儿科病房患者升级护理资源分配
Who Gets Watched? Allocating Scarce Escalation Resources on Pediatric Wards with Neural Index Policies
AI 导读
研究提出 Multi-action Index Learning and Optimization Policy(MILOP),利用多动作 restless multi-armed bandit 模型和决策导向学习,协调儿科病房的 Watcher 监测、重症护理外展团队评估及 ICU 转运决策。
来源:arXiv · Machine Learning · arxiv.org