Deep Page-Level Interest Network in Reinforcement Learning for Ads Allocation.
Guogang LiaoXiaowen ShiZe WangXiaoxu WuChuheng ZhangYongkang WangXingxing WangDong WangPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- network model
- keywords
- website
- allocation scheme
- application level
- wireless sensor networks
- state space
- network architecture
- learning algorithm
- action selection
- network management
- network structure
- dynamic programming
- network traffic
- markov decision processes
- quality of service
- temporal difference
- network flow
- learning process
- neural network
- service requests