Multi-Armed Sampling (Finite-Armed Theoretical Bounds)
-1RegretTheorem 5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Theorem 5Statistical distance=TV, Regret level=P, Regret scope=S2025.07 | -1 | -1 | |
| Theorem 5Statistical distance=TV, Regret level=A, Regret scope=S2025.07 | -1 | -1 | |
| Online Iterative GSHFStatistical distance=r-KL, Regret level=P, Regret scope=S2025.07 | -1 | -1 | |
| Two-Stage Mixed-Policy SamplingStatistical distance=r-KL, Regret level=P, Regret scope=S2025.07 | -1 | -1 | |
| KL-UCBStatistical distance=r-KL, Regret level=P, Regret scope=S2025.07 | -1 | -1 | |
| Theorem 5Statistical distance=r-KL, Regret level=P, Regret scope=S2025.07 | -1 | -1 | |
| Theorem 5Statistical distance=r-KL, Regret level=A, Regret scope=S2025.07 | -1 | -1 | |
| Theorem 5Statistical distance=f-KL, Regret level=P, Regret scope=S2025.07 | -1 | -1 | |
| Theorem 5Statistical distance=f-KL, Regret level=A, Regret scope=S2025.07 | -1 | -1 | |
| Theorem 5Statistical distance=TV, Regret level=P, Regret scope=C2025.07 | 1 | 1 | |
| Theorem 5Statistical distance=TV, Regret level=A, Regret scope=C2025.07 | 1 | 1 | |
| KL-UCBStatistical distance=r-KL, Regret level=P, Regret scope=C2025.07 | 1 | 1 | |
| Theorem 5Statistical distance=r-KL, Regret level=P, Regret scope=C2025.07 | 1 | 1 | |
| Theorem 5Statistical distance=r-KL, Regret level=A, Regret scope=C2025.07 | 1 | 1 | |
| DAISEEStatistical distance=f-KL, Regret level=P, Regret scope=C2025.07 | 1 | 1 | |
| Theorem 5Statistical distance=f-KL, Regret level=P, Regret scope=C2025.07 | 1 | 1 | |
| Theorem 5Statistical distance=f-KL, Regret level=A, Regret scope=C2025.07 | 1 | 1 |