An Optimal-Transport-Based Reinforcement Learning Approach for Computation Offloading.

Zhuo Li Xu Zhou Taixin Li Yang Liu

Published in: WCNC (2021)

Keyphrases

reinforcement learning
dynamic programming
optimal control
optimal design
database
state space
function approximation
reinforcement learning algorithms
real time
machine learning
information retrieval
sufficient conditions
closed form
efficient computation
action selection
temporal difference