Login / Signup
An Actor-Critic Contextual Bandit Algorithm for Personalized Mobile Health Interventions.
Huitian Lei
Ambuj Tewari
Susan A. Murphy
Published in:
CoRR (2017)
Keyphrases
</>
learning algorithm
search space
k means
monte carlo
information extraction
data mining
contextual bandit
actor critic
model free
probabilistic model
upper confidence bound
mathematical model
linear programming
dynamic programming
cost function
optimal solution
reinforcement learning
machine learning