RA-RL: Reputation-Aware Edge Device Selection Method based on Reinforcement Learning.

Yanlei Dong Peng Gan Gagangeet Singh Aujla Peiying Zhang

Published in: WOWMOM (2021)

Keyphrases

reinforcement learning
model free
dynamic programming
high accuracy
edge detection
learning algorithm
pairwise
significant improvement
detection method
edge points
neural network
objective function
preprocessing