Inference for Batched Bandits
–Neural Information Processing Systems
However, for many real-world problems it is not enough to just minimize regret on a particular problem instance. For example, suppose we have run an online education experiment using a bandit algorithm where we test different types of teaching strategies.
Neural Information Processing Systems
Oct-3-2025, 05:07:09 GMT
- Country:
- Europe
- Sweden > Stockholm
- Stockholm (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Sweden > Stockholm
- North America
- Canada (0.04)
- United States > California (0.04)
- Europe
- Genre:
- Research Report > Experimental Study (0.94)