Deep Reinforcement Learning-Guided Task Reverse Offloading in Vehicular Edge Computing.

Anqi Gu Huaming Wu Huijun Tang Chaogang Tang

Published in: GLOBECOM (2022)

Keyphrases

reinforcement learning
edge detection
model free
reinforcement learning algorithms
learning process
state space

edge information
data dissemination
dynamic programming
function approximation
traffic flow
edge map

machine learning
robotic control
traffic management
database
temporal difference

urban areas
optimal control
markov decision processes
multi agent
social networks