Regret Minimization on Episodic MNL mixture MDP
1Regret BoundHwang and Oh
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Hwang and OhBound Type=Upper Bound2026.05 | 1 | — | — | — | |
| This work (Theorem 5)Bound Type=Upper Bound2026.05 | 1 | — | — | — | |
| This work (Theorem 7)Bound Type=Lower Bound2026.05 | 1 | — | — | — | |
| Cho et al.Bound Type=Upper Bound2026.05 | 2 | — | — | — | |
| Li et al.Bound Type=Upper Bound2026.05 | 2 | — | — | — | |
| This work (Corollary 9)Bound Type=Upper Bound2026.05 | 3 | — | — | — | |
| Park et al.Bound Type=Lower Bound2026.05 | 3 | — | — | — | |
| Hwang and Oh (2023)Bound Type=Upper bound2026.05 | — | 2 | — | — | |
| Li et al. (2024)Bound Type=Upper bound2026.05 | — | 2 | — | — | |
| LIVAROT (Theorem 3)Bound Type=Upper bound2026.05 | — | 2 | — | — | |
| LIVAROT (Theorem 4)Bound Type=Lowerbound2026.05 | — | 2 | — | — | |
| Park et al. (2024)Bound Type=Lowerbound2026.05 | — | 3 | — | — |