Deep Reinforcement Learning based Node Pairing Scheme in Edge-chain for IoT Applications.

Yang Gao Wenjun Wu Junyu Dong Yufeng Yin Pengbo Si

Published in: GLOBECOM (2020)

Keyphrases

reinforcement learning
management system
undirected graph
disjoint paths
state space
edge detection
reinforcement learning algorithms
function approximation
temporal difference
destination node
multiscale
markov decision processes
directed graph
location information
edge information
strongly connected