Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Tasks.
Ze WangGuogang LiaoXiaowen ShiXiaoxu WuChuheng ZhangYongkang WangXingxing WangDong WangPublished in: CIKM (2022)
Keyphrases
- reinforcement learning
- multiple tasks
- learning process
- learning algorithm
- learning systems
- supervised learning
- knowledge acquisition
- learning agents
- active learning
- image representation
- learning problems
- multi task
- search engine
- temporal difference learning
- machine learning
- combining multiple
- multi task learning
- reinforcement learning algorithms
- autonomous learning