K-armed bandits
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
K-armed bandits Gaussian rewards
114.4Regret
4
K-armed bandits
1Minimax Ratio
3
K-armed bandits Exponential Family rewards
1Finite-Time Regret (Minimax Ratio)
2
K-armed bandits [0, 1] rewards
1Finite-Time Regret (Minimax Ratio)
2
K-armed bandits sub-Gaussian rewards
—Primary metric
0