Efficient Counterfactual Learning from Bandit Feedback.
Yusuke NaritaShota YasuiKohei YataPublished in: AAAI (2019)
Keyphrases
- learning algorithm
- learning process
- efficient learning
- supervised learning
- e learning
- prior knowledge
- knowledge acquisition
- learning systems
- learning analytics
- learning problems
- erroneous examples
- neural network
- inductive inference
- random sampling
- learning scenarios
- background knowledge
- computationally efficient
- online learning
- semi supervised
- reinforcement learning