Hybrid Transfer in Deep Reinforcement Learning for Ads Allocation.
Ze WangGuogang LiaoXiaowen ShiXiaoxu WuChuheng ZhangBingqi ZhuYongkang WangXingxing WangDong WangPublished in: CIKM (2022)
Keyphrases
- reinforcement learning
- transfer learning
- function approximation
- keywords
- markov decision processes
- learning algorithm
- temporal difference
- learning process
- optimal control
- machine learning
- optimal allocation
- model free
- cross domain
- resource allocation
- supervised learning
- state space
- multi agent
- neural network
- knowledge transfer
- hybrid learning
- reinforcement learning algorithms
- markov decision process
- function approximators
- hybrid approaches
- transferring knowledge