Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning.
Jiatai HuangYan DaiLongbo HuangPublished in: CoRR (2023)
Keyphrases
- online learning
- learning systems
- passive aggressive
- elementary school
- supervised learning
- active learning
- prior knowledge
- learning process
- data sets
- online environment
- online training
- decision trees
- knowledge base
- knowledge acquisition
- learning algorithm
- learning scenarios
- online communities
- computer mediated
- learning scheme
- inductive inference
- online education
- real time