Optimal Learning for Structured Bandits.
Bart P. G. Van ParysNegin GolrezaeiPublished in: Manag. Sci. (2024)
Keyphrases
- learning algorithm
- multi armed bandits
- learning process
- active learning
- online learning
- reinforcement learning
- structured output
- learning problems
- learning tasks
- learning systems
- knowledge acquisition
- worst case
- supervised learning
- artificial intelligence
- empirical studies
- unsupervised learning
- upper bound
- artificial neural networks
- information systems
- information retrieval