Regret minimization on K-armed bandits Gaussian rewards
114.4RegretUCB1
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| UCB1Number of time steps T=10,000, Confidence bounds=two-sigma2024.02 | 114.4 | — | — | — | |
| RSENumber of time steps T=10,000, Confidence bounds=two-sigma2024.02 | 683.1 | — | — | — | |
| RASMABNumber of time steps T=10,000, Confidence bounds=two-sigma2024.02 | 883.7 | — | — | — | |
| RECNumber of time steps T=10,000, Confidence bounds=two-sigma2024.02 | 1,956.9 | — | — | — | |
| AdaUCBAnytime=false2022.06 | — | — | 1 | — |