Wheel Bandit
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Wheel Bandit delta=0.9
7,654.6Final Cumulative Regret (Mean)
10
Wheel Bandit delta=0.95
8,211.9Mean Cumulative Regret
10
Wheel Bandit delta=0.99
86.03Normalized Cumulative Regret
9
Wheel Bandit delta=0.95
63.3Normalized Cumulative Regret
9
Wheel Bandit delta=0.90
36.54Normalized Cumulative Regret
9
Wheel Bandit (delta=0.70)
13.72Normalized Cumulative Regret
9
Wheel Bandit delta=0.50
12.49Normalized Cumulative Regret
9