Login / Signup

A Distributed Dependency-Aware Offloading Scheme for Vehicular Edge Computing Based on Policy Gradient.

Haoqiang LiuHongbo ZhaoLiwei GengYujie WangWenquan Feng
Published in: CSCloud/EdgeCom (2021)
Keyphrases
  • policy gradient
  • multi agent
  • cooperative
  • variance reduction
  • parametric optimization
  • reinforcement learning
  • function approximation
  • average reward
  • actor critic