Reinforcement Learning Method with Internal World Model Training.

Kenji Hirata Hiroyuki Iizuka Masahito Yamamoto

Published in: SII (2020)

Keyphrases

reinforcement learning
pairwise
training phase
significant improvement
supervised learning
high accuracy
clustering method
detection method
world model
cost function
dynamic programming
machine learning
training process
function approximation
general purpose
training samples
similarity measure
computer vision