CDR: Conservative Doubly Robust Learning for Debiased Recommendation.
Zijie SongJiawei ChenSheng ZhouQihao ShiYan FengChun ChenCan WangPublished in: CIKM (2023)
Keyphrases
- learning algorithm
- reinforcement learning
- learning tasks
- learning process
- prior knowledge
- empirical studies
- learning community
- learning systems
- real time
- support vector
- multi agent
- supervised learning
- computationally efficient
- learning scenarios
- incremental learning
- artificial intelligence
- inductive inference
- computer programming