Hybrid Transfer in Deep Reinforcement Learning for Ads Allocation.
Guogang LiaoZe WangXiaowen ShiXiaoxu WuChuheng ZhangBingqi ZhuYongkang WangXingxing WangDong WangPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- transfer learning
- markov decision processes
- function approximation
- machine learning
- optimal allocation
- knowledge transfer
- learning algorithm
- hybrid approaches
- reinforcement learning algorithms
- model free
- optimal control
- resource allocation
- optimal policy
- supervised learning
- state space
- transferring knowledge
- temporal difference
- temporal difference learning
- reinforcement learning methods
- previously learned
- multi agent reinforcement learning
- learning process
- allocation problems