Sequential Banner Design Optimization with Deep Reinforcement Learning.
Yusuke KondoXueting WangHiroyuki SeshimeToshihiko YamasakiPublished in: ISM (2021)
Keyphrases
- reinforcement learning
- state space
- sequential search
- markov decision processes
- control problems
- temporal difference
- multi agent
- optimal policy
- belief nets
- real time
- deep learning
- optimal control
- case study
- learning algorithm
- machine learning
- supervised learning
- action selection
- search engine
- temporal difference learning
- transition model
- neural network