Login / Signup
Robust Actor-Critic Contextual Bandit for Mobile Health (mHealth) Interventions.
Feiyun Zhu
Jun Guo
Ruoyu Li
Junzhou Huang
Published in:
CoRR (2018)
Keyphrases
</>
contextual bandit
actor critic
upper confidence bound
reinforcement learning
information extraction
function approximation
temporal difference
news recommendation
optimal control