A Swapping Target Q-Value Technique for Data Augmentation in Offline Reinforcement Learning.

Ho-Taek Joo In-Chang Baek Kyung-Joong Kim

Published in: IEEE Access (2022)

Keyphrases

reinforcement learning
data sets
data processing
data collection
data structure
end users
raw data
test data
high dimensional data
computer systems
input data
database
data sources
mobile robot
high dimensional
data analysis
databases
image data
small number
xml documents
data distribution
real time