A Deep Reinforcement Learning Based Feature Selector.

Yiran Cheng Kazuhiko Komatsu Masayuki Sato Hiroaki Kobayashi

Published in: PAAP (2020)

Keyphrases

reinforcement learning
real time
learning algorithm
state space
markov decision processes
temporal difference
training data
image features
supervised learning
optimal policy
learning problems
function approximation
model free