Sign in
Combining Model-Based and Model-Free Reinforcement Learning Policies for More Efficient Sepsis Treatment.
Xiangyu Liu
Chao Yu
Qikai Huang
Luhao Wang
Jianfeng Wu
Xiangdong Guan
Published in:
ISBRA (2021)
Keyphrases
</>
neural network
np hard
optimal policy
matrix factorization
initial stage