Value function assessment to different RL algorithms for heparin treatment policy of patients with sepsis in ICU.
Jiang LiuYihao XieXin ShuYuwen ChenYizhu SunKunhua ZhongHao LiangYujie LiChunyong YangYan HanYuwei ZouZiting ZhuyiJiahao HuangJunhong LiXiaoyan HuBin YiPublished in: Artif. Intell. Medicine (2024)
Keyphrases
- rl algorithms
- function approximators
- intensive care units
- reinforcement learning
- clinical data
- intensive care unit
- initial stage
- average reward
- model free
- optimal policy
- learning problems
- intensive care
- neural network
- function approximation
- medical data
- infinite horizon
- high risk
- optimal control
- supervised learning
- dynamic programming