Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Regret minimization on K-armed bandits Gaussian rewards
Loading...
114.4
Regret
UCB1
40.7
538.175
1,035.65
1,533.125
Feb 12, 2024
Regret
Asymptotic Optimality Achieved
Finite-Time Regret (Minimax Ratio)
Sub-UCB Configuration
Updated 18d ago
Evaluation Results
Method
Method
Links
Regret
Asymptotic Optimality Achieved
Finite-Time Regret (Minimax Ratio)
Sub-UCB Configuration
UCB1
Number of time steps T...
2024.02
114.4
-
-
-
RSE
Number of time steps T...
2024.02
683.1
-
-
-
RASMAB
Number of time steps T...
2024.02
883.7
-
-
-
REC
Number of time steps T...
2024.02
1,956.9
-
-
-
AdaUCB
Anytime=false
2022.06
-
-
1
-
Feedback
Search any
task
Search any
task
