Satisficing in Time-Sensitive Bandit Learning.
Daniel RussoBenjamin Van RoyPublished in: Math. Oper. Res. (2022)
Keyphrases
- learning algorithm
- empirical studies
- learning systems
- knowledge acquisition
- online learning
- prior knowledge
- reinforcement learning
- learning process
- supervised learning
- search algorithm
- machine learning
- unsupervised learning
- artificial intelligence
- mobile learning
- learning tasks
- incremental learning
- learning scheme
- inductive inference
- computer programming
- elementary school