On Regret with Multiple Best Arms
–Neural Information Processing Systems
We study a regret minimization problem with the existence of multiple best/near-optimal arms in the multi-armed bandit setting.
Neural Information Processing Systems
Nov-14-2025, 04:13:06 GMT
- Country:
- Europe
- North America
- Canada (0.04)
- United States > Wisconsin
- Dane County > Madison (0.14)
- Technology: