Login / Signup
A Distributed Dependency-Aware Offloading Scheme for Vehicular Edge Computing Based on Policy Gradient.
Haoqiang Liu
Hongbo Zhao
Liwei Geng
Yujie Wang
Wenquan Feng
Published in:
CSCloud/EdgeCom (2021)
Keyphrases
</>
policy gradient
multi agent
cooperative
variance reduction
parametric optimization
reinforcement learning
function approximation
average reward
actor critic