Learning from eXtreme Bandit Feedback.
Romain LopezInderjit S. DhillonMichael I. JordanPublished in: CoRR (2020)
Keyphrases
- learning algorithm
- learning systems
- learning scheme
- lower bound
- supervised learning
- online learning
- learning process
- upper bound
- learning tasks
- unsupervised learning
- creative problem solving
- real time
- incremental learning
- learning scenarios
- knowledge acquisition
- semi supervised
- artificial neural networks
- reinforcement learning
- social networks
- information retrieval