Login / Signup

Communication-Efficient Soft Actor-Critic Policy Collaboration via Regulated Segment Mixture in Internet of Vehicles.

Xiaoxue YuRongpeng LiChengchao LiangZhifeng Zhao
Published in: CoRR (2023)
Keyphrases
  • actor critic
  • policy gradient
  • approximate dynamic programming
  • reinforcement learning
  • neuro fuzzy
  • temporal difference
  • multi agent
  • least squares
  • fuzzy sets
  • linear program
  • gradient method