Towards Off-Policy Learning for Ranking Policies with Logged Feedback.
Teng XiaoSuhang WangPublished in: AAAI (2022)
Keyphrases
- learning process
- learning systems
- supervised learning
- online learning
- data sets
- training data
- learning tasks
- active learning
- web search
- motor skills
- learning gains
- learning scheme
- learning outcomes
- background knowledge
- knowledge acquisition
- relevance feedback
- prior knowledge
- support vector
- reinforcement learning
- decision trees
- information retrieval