Login / Signup

An Actor-critic Reinforcement Learning Model for Optimal Bidding in Online Display Advertising.

Congde YuanMengzhuo GuoChaoneng XiangShuangyang WangGuoqing SongQingpeng Zhang
Published in: CIKM (2022)
Keyphrases
  • reinforcement learning
  • dynamic programming
  • mathematical model
  • optimal control
  • neural network
  • model free
  • temporal difference
  • objective function
  • optimal solution
  • function approximation
  • control problems