Off-policy Learning for Multiple Loggers.
Li HeLong XiaWei ZengZhi-Ming MaYihong ZhaoDawei YinPublished in: KDD (2019)
Keyphrases
- learning process
- learning algorithm
- prior knowledge
- learning systems
- active learning
- data sets
- supervised learning
- inter related
- combining multiple
- inductive inference
- learning community
- learning problems
- mobile learning
- background knowledge
- empirical studies
- reinforcement learning
- data mining
- online learning
- mobile robot
- domain knowledge
- training data
- learning tasks
- case study
- information systems
- learning scheme
- search engine
- artificial intelligence
- computer programming
- multiple tasks