Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Tasks.
Guogang LiaoZe WangXiaowen ShiXiaoxu WuChuheng ZhangYongkang WangXingxing WangDong WangPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- multiple tasks
- learning process
- learning algorithm
- active learning
- learning systems
- learning problems
- supervised learning
- background knowledge
- function approximation
- reinforcement learning agents
- machine learning
- state abstraction
- previously learned
- robot control
- multi task learning
- combining multiple
- learning tasks
- resource allocation
- knowledge acquisition
- online learning