Regret Minimization on F_LR Stochastic Low-Rank Reward
2RegretNoisy power method (NPM)
Evaluation results
| Method | Links | |
|---|---|---|
| Noisy power method (NPM)Reward Gap Condition=Gap2021.07 | 2 | |
| Noisy power method (NPM)Reward Gap Condition=Gap-free2021.07 | 2 | |
| Lower Bound2021.07 | 2 | |
| LinUCB/eluder2021.07 | 3 |