Login / Signup
An Asynchronous Advantage Actor-Critic Reinforcement Learning Method for Stock Selection and Portfolio Management.
Qinma Kang
Huizhuo Zhou
Yunfan Kang
Published in:
ICBDR (2018)
Keyphrases
</>
reinforcement learning
dynamic programming
cost function
clustering algorithm
k means
support vector machine svm
optimization method
function approximation
state action